US20160148228A1 - Methods and apparatus to predict time-shifted exposure to media - Google Patents
Methods and apparatus to predict time-shifted exposure to media Download PDFInfo
- Publication number
- US20160148228A1 US20160148228A1 US14/951,454 US201514951454A US2016148228A1 US 20160148228 A1 US20160148228 A1 US 20160148228A1 US 201514951454 A US201514951454 A US 201514951454A US 2016148228 A1 US2016148228 A1 US 2016148228A1
- Authority
- US
- United States
- Prior art keywords
- ratings
- data
- media asset
- media
- audience measurement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000005259 measurement Methods 0.000 claims abstract description 113
- 230000000694 effects Effects 0.000 claims abstract description 10
- 238000003860 storage Methods 0.000 claims description 31
- 230000001131 transforming effect Effects 0.000 claims 8
- 238000013507 mapping Methods 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000015654 memory Effects 0.000 description 32
- 230000008569 process Effects 0.000 description 29
- 230000009466 transformation Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000000844 transformation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011012 sanitization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
- H04N21/44224—Monitoring of user activity on external systems, e.g. Internet browsing
- H04N21/44226—Monitoring of user activity on external systems, e.g. Internet browsing on social networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4665—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving classification methods, e.g. Decision trees
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/65—Transmission of management data between client and server
- H04N21/658—Transmission by the client directed to the server
- H04N21/6582—Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number
Definitions
- This disclosure relates generally to audience measurement, and, more particularly, to methods and apparatus to predict time-shifted exposure to media.
- Audience measurement of media is typically carried out by monitoring media exposure of panelists that are statistically selected to represent particular demographic groups. Audience measurement companies, such as The Nielsen Company (US), LLC, enroll households and persons to participate in measurement panels. By enrolling in these measurement panels, households and persons agree to allow the corresponding audience measurement company to monitor their exposure to information presentations, such as media output via a television, a radio, a computer, etc. Using various statistical methods, the collected media exposure data is processed to determine the size and/or demographic composition of the audience(s) for media of interest.
- panelists that are statistically selected to represent particular demographic groups. Audience measurement companies, such as The Nielsen Company (US), LLC, enroll households and persons to participate in measurement panels. By enrolling in these measurement panels, households and persons agree to allow the corresponding audience measurement company to monitor their exposure to information presentations, such as media output via a television, a radio, a computer, etc.
- US The Nielsen Company
- the collected media exposure data is processed to determine the size and/or demographic composition of the audience(s) for media of
- audience size and/or demographic information is valuable to, for example, advertisers, broadcasters, content providers, manufacturers, retailers, product developers, and/or other entities.
- audience size and demographic information is a factor in the placement of advertisements, in valuing commercial time slots during a particular program and/or generating ratings for piece(s) of media.
- FIG. 1 illustrates an example system for audience measurement analysis implemented in accordance with the teachings of this disclosure to predict time-shifted exposure to media.
- FIG. 2 is an example data table that may be used by the example central facility of FIG. 1 to store raw data variables in the example raw data database of FIG. 1 .
- FIG. 3 is an example calculation of estimated current television ratings that may be performed by the example program ratings estimator of FIG. 1 .
- FIG. 5 is an example data table that may be used by the example data translator of FIGS. 1 and/or 4 to translate ratings data variables.
- FIG. 6 is an example calculation of estimated current television ratings that may be performed by the example ratings handler of FIG. 4 .
- FIG. 7 is an example data table that may be used by the example data translator of FIGS. 1 and/or 4 to translate program attributes data variables.
- FIG. 8 is an example data table that may be used by the example data translator of FIGS. 1 and/or 4 to translate social media data variables.
- FIG. 9 is an example schema that may be used by the example central facility of FIG. 1 to determine lift prediction models based on season-episode groupings.
- FIG. 10 is an example data table that may be used by the example central facility of FIG. 1 to associate translated data variables to corresponding lift prediction models.
- FIG. 11 is a flowchart representative of example machine-readable instructions that may be executed by the example central facility of FIG. 1 to predict time-shifted exposure to media.
- FIG. 12 is a flowchart representative of example machine-readable instructions that may be executed by the example data translator of FIGS. 1 and/or 4 to normalize raw audience measurement data.
- FIG. 13 is a flowchart representative of example machine-readable instructions that may be executed by the example model builder of FIG. 1 to build a lift prediction model.
- FIG. 14 is a flowchart representative of example machine-readable instructions that may be executed by the example program ratings estimator of FIG. 1 to predict time-shifted exposure to media.
- FIG. 15 is a block diagram of an example processing platform structured to execute the example machine-readable instructions of FIGS. 11-13 and/or 14 to implement the example central facility and/or the example data translator of FIGS. 1 and/or 4 .
- Examples disclosed herein facilitate predicting time-shifted exposure to media. For example, disclosed examples enable prediction of television ratings for households tuned to (or persons exposed to) a program or time-period of a specific station or cable network at the actual time that the program was telecast (e.g., live ratings), and any delayed viewing of the program during a predetermined time period.
- live+7 ratings represent the percentage of an audience that was exposed to media during the original telecast of the media (e.g., the live ratings) and the incremental viewing that takes place during the 7 days following the original telecast.
- Exposure information may be useful for determining a marketing campaign and/or evaluating the effectiveness of a marketing campaign. For example, an advertiser who wants exposure of their asset (e.g., a product, a service, etc.) to reach a specific audience will place advertisements in media (e.g., a television program) whose audience represents the characteristics of the target market.
- networks determine the cost of including an advertisement in their media based on the ratings of the media. For example, a high rating for a television program represents a large number of audience members who tuned to (or were exposed to) the television program. In such instances, the larger the audience of a television program (e.g., a higher rating), the more networks can charge for advertisements during the program.
- live ratings were used as the metric for evaluating the performance of media.
- DVR digital video recorder
- video-on-demand service at a time that is convenient to them.
- time-shifted viewing may account for fifty percent of the viewership of a television program.
- live ratings do not accurately represent the audience size of the television program.
- Live+7 ratings more accurately represent how viewers are watching media. “Live+7” ratings reflect viewing done via DVR services and/or video-on-demand services within seven days (e.g., 168 hours) of the original telecast of the program. In some instances, the additional viewership that is included in “live+7” ratings can make or break whether a low profile program is renewed or cancelled. However, measuring “live+7” ratings involves waiting at least seven days to determine the time-shifted viewing.
- Examples disclosed herein facilitate predicting time-shifted viewing of media.
- Examples disclosed herein collect and/or develop audience measurement data related to media. For example, disclosed examples measure audience exposure to television programs via people meters and/or by monitoring social media messages referencing television programs. Examples disclosed herein use the audience measurement data to build and/or train lift prediction models that may be used to estimate ratings lift. For example, disclosed examples determine a relationship between features of the audience measurement data and historical ratings lifts.
- features of the audience measurement data include, but are not limited to, current and historical ratings-related information, social media indicators, characteristics of the media asset, etc.
- Examples disclosed herein apply data related to a media asset of interest to a lift prediction model to determine a predicted lift for the media asset.
- different lift prediction models are developed based on characteristics of the media asset. For example, disclosed examples may characterize media assets based on season-episode groupings. In some such examples, the data applied to a lift prediction model to determine estimated ratings lift may depend on the season-episode grouping.
- FIG. 1 is a diagram of an example environment in which a system 100 constructed in accordance with the teachings of this disclosure operates to predict time-shifted exposure to media of interest.
- the example system 100 of FIG. 1 includes one or more audience measurement system(s) 105 and a central facility 125 to facilitate predicting time-shifted exposure to media of interest in accordance with the teachings of this disclosure.
- the central facility 125 estimates an increase in viewership (e.g., a “lift”) over a period of seven days after the initial (e.g., live) broadcast of media of interest (e.g., a television show).
- any other time-shifted period may additionally or alternatively be used.
- the example system 100 of FIG. 1 includes the one or more audience measurement system(s) 105 to collect audience measurement data 110 from panelists and non-panelists.
- the example audience measurement system(s) 105 of FIG. 1 collect panelist media measurement data 110 A via, for example, people meters operating in statistically-selected households, set-top boxes and/or other media devices (e.g., such as digital video recorders, personal computers, tablet computers, smartphones, etc.) capable of monitoring and returning monitored data for media presentations, etc.
- media exposure data such as live exposure data, delayed exposure data (e.g., relative to time-shifted viewing of media via, for example, a digital video recorder and/or video on-demand), media performance data such as TV ratings (e.g., historical TV ratings and current TV ratings), program characteristics (e.g., attributes) such as broadcast day-of-week information, broadcast time information, originator information (e.g., a network or channel that broadcast the media) and/or genre information, etc.
- the panelist media measurement data 110 A is associated with demographic information (e.g., gender, age, income, etc.) of the panelists exposed to the media.
- media includes any type of content and/or advertisement delivered via any type of distribution medium.
- media includes television programming or advertisements, radio programming or advertisements, movies, web sites, streaming media, etc.
- Example methods, apparatus, and articles of manufacture disclosed herein monitor media presentations at media devices.
- Such media devices may include, for example, Internet-enabled televisions, personal computers, Internet-enabled mobile handsets (e.g., a smartphone), video game consoles (e.g., Xbox®, PlayStation®), tablet computers (e.g., an iPad®), digital media players (e.g., a Roku® media player, a Slingbox®, etc.), etc.
- media monitoring information is aggregated to determine ownership and/or usage statistics of media devices, relative rankings of usage and/or ownership of media devices, types of uses of media devices (e.g., whether a device is used for browsing the Internet, streaming media from the Internet, etc.), and/or other types of media device information.
- monitoring information includes, but is not limited to, media identifying information (e.g., media-identifying metadata, codes, signatures, watermarks, and/or other information that may be used to identify presented media), application usage information (e.g., an identifier of an application, a time and/or duration of use of the application, a rating of the application, etc.), and/or user-identifying information (e.g., demographic information, a user identifier, a panelist identifier, a username, etc.).
- media identifying information e.g., media-identifying metadata, codes, signatures, watermarks, and/or other information that may be used to identify presented media
- application usage information e.g., an identifier of an application, a time and/or duration of use of the application, a rating of the application, etc.
- user-identifying information e.g., demographic information, a user identifier, a panelist identifier, a username, etc.
- the example audience measurement system(s) 105 of FIG. 1 also collect social media activity data 110 B related to media via, for example, social media servers that provide social media services to users of the social media server.
- social media services is defined to be a service provided to users to enable users to share information (e.g., text, images, data, etc.) in a virtual community and/or network.
- Example social media services may include, for example, Internet forums (e.g., a message board), blogs, micro-blogs (e.g., Twitter®), social networks (e.g., Facebook®, LinkedIn, Instagram, etc.), etc.
- the audience measurement system(s) 105 may monitor social media messages communicated via social media services and identify media-exposure social media messages (e.g., social media messages that reference at least one media asset (e.g., media and/or a media event)).
- the example audience measurement system(s) 105 may filter the media-exposure social media messages for media-exposure social media messages of interest (e.g., social media messages that reference media of interest).
- the example social media activity data 110 B of FIG. 1 includes one or more of message identifying information (e.g., a message identifier, a message author, etc.), timestamp information indicative of when the social media message was posted and/or viewed, the content of the social media message and an identifier of the media asset referenced in the media-exposure social media message.
- message identifying information e.g., a message identifier, a message author, etc.
- timestamp information indicative of when the social media message was posted and/or viewed
- the content of the social media message e.g., a message author, etc.
- the audience measurement system(s) 105 may process the media-exposure social media messages of interest and aggregate information related to the social media messages.
- the audience measurement system(s) 105 may determine a count of the media-exposure social media messages of interest, may determine a number of unique authors who posted the media-exposure social media messages of interest and/or may determine a number of impressions of (e.g., exposure to) the media-exposure social media messages of interest.
- the audience measurement system(s) 105 send the audience measurement data 110 to the central facility 125 via an example network 115 .
- the example network 115 of the illustrated example of FIG. 1 is the Internet.
- the example network 115 may be implemented using any suitable wired and/or wireless network(s) including, for example, one or more data buses, one or more Local Area Networks (LANs), one or more wireless LANs, one or more cellular networks, one or more private networks, one or more public networks, etc.
- the example network 115 enables the central facility 125 to be in communication with the audience measurement system(s) 105 .
- the phrase “in communication,” including variances therefore, encompasses direct communication and/or indirect communication through one or more intermediary components and does not require direct physical (e.g., wired) communication and/or constant communication, but rather includes selective communication at periodic or aperiodic intervals, as well as one-time events.
- the central facility 125 is operated by an audience measurement entity (AME) 120 .
- AME 120 of the illustrated example of FIG. 1 is an entity such as The Nielsen Company (US), LLC that monitors and/or reports exposure to media and operates as a neutral third party. That is, in the illustrated example, the audience measurement entity 120 does not provide media (e.g., content and/or advertisements) to end users. This un-involvement with the media production and/or delivery ensures the neutral status of the audience measurement entity 120 and, thus, enhances the trusted nature of the data the AME 120 collects and processes.
- media e.g., content and/or advertisements
- the reports generated by the audience measurement entity may identify aspects of media usage such as the number of people who are watching television programs and characteristics of the audiences (e.g., demographic information of who is watching the television programs, when they are watching the television programs, etc.).
- the example AME 120 of FIG. 1 operates the central facility 125 to predict time-shifted exposure to media such as a lift in ratings associated with a media asset of interest over a course of 7 days (e.g., 168 hours) after the initial broadcast of the media asset.
- a media asset of interest is a particular media program (e.g., identified via an episode number and season number) that is being analyzed (e.g., for a report).
- a first media asset of interest may be episode 3 of season 2 of a program “Sports Stuff” and a second media asset of interest may be episode 4 of season 2 of the program “Sports Stuff.”
- the central facility 125 of the illustrated example includes a server and/or database that collects and/or receives audience measurement data related to media assets (e.g., media and/or media events) and predicts time-shifted (or delayed) exposure to media assets of interest.
- the central facility 125 is implemented using multiple devices and/or the audience measurement system(s) 105 is (are) implemented using multiple devices.
- the central facility 125 and/or the audience measurement system(s) 105 may include disk arrays and/or multiple workstations (e.g., desktop computers, workstation servers, laptops, etc.) in communication with one another.
- the central facility 125 is in communication with the audience measurement system(s) 105 via one or more wired and/or wireless networks represented by the network 115 .
- the example central facility 125 of the illustrated example of FIG. 1 processes the audience measurement data 110 returned by the audience measurement system(s) 105 to predict time-shifted exposure to media.
- the central facility 125 may process the audience measurement data 110 to determine a relationship between features (sometimes referred to herein as “variables,” “predictors” or “factors”) of the audience measurement data 110 and measured lift to build one or more prediction models.
- the example central facility 125 may then apply data associated with a media asset of interest to a prediction model to determine a predicted lift for the media asset.
- the central facility 125 includes an example data interface 130 , an example raw data database 135 , an example data translator 140 , an example translated data database 145 , an example model builder 150 , an example models data store 155 and an example program ratings estimator 160 .
- the example central facility 125 includes the example data interface 130 to provide an interface between the network 115 and the central facility 125 .
- the data interface 130 may be a wired network interface, a wireless network interface, a Bluetooth® network interface, etc. and may include the associated software and/or libraries needed to facilitate communication between the network 115 and the central facility 125 .
- the data interface 130 receives the audience measurement data 110 returned by the example audience measurement system(s) 105 of FIG. 1 .
- the example data interface 130 records the audience measurement data 110 in the example raw data database 135 .
- the example central facility 125 includes the example raw data database 135 to record data (e.g., the example audience measurement data 110 ) provided by the audience measurement system(s) 105 via the example data interface 130 .
- An example data table 200 of the illustrated example of FIG. 2 illustrates example raw data variables that may be recorded in the example raw data database 135 .
- the example raw data database 135 may be implemented by a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM), etc.) and/or a non-volatile memory (e.g., flash memory).
- SDRAM Synchronous Dynamic Random Access Memory
- DRAM Dynamic Random Access Memory
- RDRAM RAMBUS Dynamic Random Access Memory
- non-volatile memory e.g., flash memory
- the example raw data database 135 may additionally or alternatively be implemented by one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc.
- DDR double data rate
- the example raw data database 135 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the raw data database 135 is illustrated as a single database, the raw data database 135 may be implemented by any number and/or type(s) of databases.
- the example central facility 125 of the illustrated example of FIG. 1 combines multiple disparate data sets to enable modeling and assessment of multiple inputs simultaneously.
- at least some of the variables are translated (e.g., modified and/or manipulated) from their raw form to be more meaningfully handled when building the prediction models and estimating the ratings lift.
- raw data may be multiplied, aggregated, averaged, etc., and stored as translated data (sometimes referred to herein as “sanitized,” “normalized” or “recoded” data) prior to generating the prediction models used to estimate ratings lift.
- the example central facility 125 includes the example data translator 140 to translate the audience measurement data 110 received from the example audience measurement system(s) 105 into a form more meaningfully handled by the example model builder 150 .
- the data translator 140 of FIG. 1 may retrieve and/or query the audience measurement data 110 recorded in the example raw data database 135 and normalize the disparate data to a common scale.
- the example data translator 140 modifies and/or manipulates audience measurement data 110 based on the type of data.
- the data translator 140 may translate (e.g., map) data that is a string data type (e.g., “Day-of-Week” is “Tuesday”) to a Boolean data type (e.g., “Day Tues” is set to true (e.g., “1”)).
- a string data type e.g., “Day-of-Week” is “Tuesday”
- Boolean data type e.g., “Day Tues” is set to true (e.g., “1”)
- the audience measurement data 110 may be in different data formats and/or different units of measure.
- program characteristic information such as program title, episode and season identifying information, day of week, broadcast time, broadcast network and genre may be stored as string data types.
- Current and historical ratings information may be represented via television rating scores (e.g., floating data types).
- Social media indicators e.g., message identifiers, message timestamps, message content, message author identifiers, message impression information, etc.
- the data translator 140 normalizes the audience measurement data 110 into numerical data types (e.g., Boolean data types, integer data types and/or floating data types).
- the example data translator 140 of FIG. 1 records translated data in the example translated data database 145 .
- the example central facility 125 includes the example translated data database 145 to record translated data provided by the example data translator 140 .
- Example data tables 500 , 600 , 700 and 800 of the illustrated examples of FIGS. 5, 6, 7 and 8 , respectively, illustrate example translated data variables that may be recorded in the example translated data database 145 .
- the example translated data database 145 may be implemented by a volatile memory (e.g., an SDRAM, DRAM, RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
- the example translated data database 145 may additionally or alternatively be implemented by one or more DDR memories, such as DDR, DDR2, DDR3, mDDR, etc.
- the example translated data database 145 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the translated data database 145 is illustrated as a single database, the translated data database 145 may be implemented by any number and/or type(s) of databases.
- the central facility 125 includes the example model builder 150 to build one or more prediction model(s) that may be used to estimate ratings lift for media assets of interest over a time-shifted period (e.g., seven days after the initial broadcast of media assets of interest).
- the model builder 150 determines a relationship between one or more translated data variables retrieved from the example translated data database 145 and ratings lifts to build one or more prediction model(s). Equation 1 below is an example equation representative of a prediction model that may be built by the example model builder 150 .
- the lift (lift) for a media asset of interest is calculated using live ratings information (Live Ratings) associated with the media asset of interest (e.g., current ratings) and values of translated data variables (X i ) that are modified by coefficients (a i ).
- Live Ratings live ratings information
- the model builder 150 applies historical values of lift and live ratings data, and historical values of one or more translated data variables from the translated data database 145 to Equation 1 above to train the model of Equation 1 to determine the value of the coefficients (a i ).
- the example model builder 150 of FIG. 1 uses logistic regression to determine the value of the coefficients (a i ).
- any other technique may additionally or alternatively be used to determine the value of the coefficients (a i ).
- a linear equation represented by Equation 2 below may additionally or alternatively be used.
- the example model builder 150 builds different models to estimate ratings lift for a media asset of interest based on season and episode number attribute of the media asset of interest. For example, the model builder 150 may apply different sets of the translated data variables to Equation 1 above to determine the coefficient values (a i ) of the translated data variables (X i ) based on season-episode groupings.
- An example schema 900 of the illustrated example of FIG. 9 illustrates example ratings lift models based on season-episode groupings.
- the example model builder 150 selects the translated data variables (X i ) to apply to Equation 1 above based on season and episode number attributes of media assets. For example, the model builder 150 may build a first lift prediction model by applying data related to episodes one through three of the first season of a media asset to Equation 1 above. The example model builder 150 may build a second lift prediction model by applying data related to episodes four through six of the first season of a media asset and/or data related to episodes one through six of subsequent seasons of the media asset to Equation 1 above. The example model builder 150 may build a third lift prediction model by applying data related to episodes seven and later of any season of a media asset to Equation 1 above.
- Equation 1 While the general form of Equation 1 is used to build lift prediction models, the translated data variables included in the corresponding models is different and, as a result, the coefficient values (a i ) of the translated data variables (X i ) differ between the three models. While the illustrated example describes three example season-episode groupings, any other number of season-episode groupings may additionally or alternatively be used.
- the example model builder 150 of FIG. 1 stores the generated lift prediction models in the example models data store 155 .
- the example central facility 125 includes the example models data store 155 to store lift prediction models generated by the example model builder 150 .
- the example models data store 155 may be implemented by a volatile memory (e.g., SDRAM, DRAM, RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
- the example models data store 155 may additionally or alternatively be implemented by one or more DDR memories, such as DDR, DDR2, DDR3, mDDR, etc.
- the example models data store 155 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the models data store 155 is illustrated as a single database, the models data store 155 may be implemented by any number and/or type(s) of databases.
- the central facility 125 includes the example program ratings estimator 160 to use the lift prediction models generated by the example model builder 150 to estimate ratings lift for a media asset of interest.
- the program ratings estimator 160 may apply data related to the media asset of interest to predict a lift in viewership of the media asset of interest over a period (e.g., within seven days of the original broadcast of the media asset of interest).
- the program ratings estimator 160 uses program characteristics of the media asset of interest to select a lift prediction model to apply.
- the program ratings estimator 160 may determine a lift prediction model based on the season and episode number associated with the media asset of interest.
- the example program ratings estimator 160 retrieves data related to the media asset of interest from the translated data database 145 .
- the program ratings estimator 160 estimates current ratings information related to the media asset of interest based on real-time ratings information. For example, fast affiliate reports provide first national ratings for a media asset the day after telecast.
- the fast affiliate ratings (sometimes referred to as “overnight ratings”) are time-period information based on the scheduled broadcast time of media assets rather than the actual broadcast time of media assets.
- fast affiliate ratings for a media asset of interest may include stations that did not air the media asset, that cut away from the media asset for local programming (e.g., local breaking news), etc.
- the example program ratings estimator 160 estimates current ratings information based on a fast affiliate reports and actual broadcast information obtained from, for example, the affiliate stations. For example, the program ratings estimator 160 may adjust fast affiliate ratings for a media asset of interest based on actual broadcast information.
- FIG. 3 illustrates an example calculation 300 of estimated current TV ratings based on fast affiliate reports 305 and actual broadcast information 310 .
- the program ratings estimator 160 combines the fast affiliate reports 305 with the actual broadcast information 310 to estimate current TV ratings 320 .
- the example fast affiliate reports 305 provide “live” ratings and “live+same day” ratings for thirty-minute periods, any other time period may additionally or alternatively be used.
- the fast affiliate reports 305 may provide ratings on a minute-by-minute basis to increase the granularity of the ratings information.
- the example program ratings estimator 160 of the illustrated example of FIG. 1 applies the estimated current ratings and data related to a media asset of interest to the generated lift prediction models stored in the example models data store 155 to generate reports 165 estimating the ratings lift for the media asset of interest.
- the program ratings estimator 160 may estimate the ratings lift for a media asset of interest by applying program attributes information, social media indicators information and/or media performance information to a lift prediction model.
- program attributes information includes genre information of the media asset of interest, day-of-week information related to the media asset of interest, broadcast time related to the media asset of interest, originator (e.g., network or channel) information related to the media asset of interest, etc.
- social media indicators information includes a social media messages count related to the number of media-exposure social media messages of interest, a social media unique authors count related to the number of unique authors who posted media-exposure social media messages of interest, a social media impressions count related to the number of users who were exposed to the media-exposure social media messages of interest, etc.
- media performance information includes current ratings associated with the media asset of interest (e.g., “live” ratings and “live+same day” ratings), historical ratings associated with the media asset of interest (e.g., historical “live” ratings and historical “live+same day” ratings), program lead-in ratings associated with the media asset of interest (e.g., “live” ratings and “live+same day” ratings of the program that was broadcast prior to the media asset of interest), a program loyalty score associated with the media asset of interest (e.g., average number of episodes of the media asset watched by viewers during a time period (e.g., five weeks)), etc.
- current ratings associated with the media asset of interest e.g., “live” ratings and “live+same day” ratings
- historical ratings associated with the media asset of interest e.g., historical “live” ratings and historical “live+same day” ratings
- program lead-in ratings associated with the media asset of interest e.g., “live” ratings and “live+same day
- FIG. 2 is an example data table 200 that lists raw audience measurement data variables that the example data interface 130 of FIG. 1 may store in the example raw data database 135 of FIG. 1 .
- the raw audience measurement data variables represent the data collected and/or provided by the audience measurement system(s) 105 of FIG. 1 .
- the raw audience measurement data variables may include the panelist media measurement data 110 A collected via, for example, people meters operating in statistically-selected households, set-top boxes and/or other media devices (e.g., such as digital video recorders, personal computers, tablet computers, smartphones, etc.) capable of monitoring and returning monitored data for media presentations, etc.
- the example raw audience measurement data variables included in the data table 200 may also include the social media activity data 110 B associated with media of interest referenced by social media messages collected via, for example, social media servers that provide social media services to users of the social media server.
- the example data table 200 of the illustrated example of FIG. 2 includes a variable name identifier column 205 , a variable data type identifier column 210 and a variable meaning identifier column 215 .
- the example variable name identifier column 205 indicates example variables that may be associated with a telecast and/or useful for predicting time-shifted exposure to media.
- the example variable data type identifier column 210 indicates a data type of the corresponding variable.
- the example variable meaning identifier column 215 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 200 of FIG. 2 , more or fewer variable identifier columns may be represented in the example data table 200 .
- the example data table 200 may additionally or alternatively include a variable identifier column indicative of the source of the corresponding data (e.g., the example panelist media measurement data 110 A, the example social media activity data 110 B, etc.).
- the example data table 200 of the illustrated example of FIG. 2 includes eighteen example rows corresponding to example raw audience measurement data variables.
- the first example block of rows 250 identifies attributes and/or characteristics of a media asset and is stored as strings.
- the “Title” variable identifies the name of the media asset (e.g., “Sports Stuff”)
- the “Episode Identifier” variable identifies the season and episode number associated with the media asset (e.g., Season 2, Episode 4)
- the “Day of Week” variable identifies the day of the week that the media asset was broadcast (e.g., “Tuesday”)
- the “Broadcast Time” variable identifies the time during which the media asset was broadcast (e.g., “20:00-20:30”)
- the “Network” variable identifies on which network the media asset was broadcast (e.g., Channel “ABC”)
- the “Genre” variable identifies the genre that the media asset is classified (e.g., a “
- the second example block of rows 255 identifies ratings information associated with a media asset and the corresponding information is stored as floating type data.
- the “Ratings Live” variable identifies the program ratings during the original broadcast of the program (e.g., “1.01”).
- the example “Ratings LiveSameDay” variable and example “Ratings LivePlus7” variable identify the program ratings during the original broadcast of the program and also include time-shifted incremental viewing that takes place via, for example, a DVR or video-on-demand (VOD) service.
- VOD video-on-demand
- the “Ratings LiveSameDay” variable represents the number of people who viewed the media asset during its original broadcast time and/or during the same day as the original broadcast (e.g., “Live+Same Day” ratings).
- the example “Ratings LivePlus7” variable represents the number of people who viewed the media asset during its original broadcast time and/or within seven days following the original telecast (e.g., “Live+7” or “L7” ratings).
- the example data table 200 includes three example ratings (e.g., “Live” ratings, “Live+Same Day” ratings and “Live+7” ratings), in other examples, the ratings information may be associated with more or fewer time-shifted periods.
- the example row 260 indicates the “Lead-In Ratings” variable is stored as a floating data type and corresponds to the program ratings for a media asset preceding the media asset of interest.
- the “lead-in ratings” information corresponds to the media asset that is broadcast on “Tuesday” at “19:30-20:00” on Channel “ABC.”
- the example row 265 indicates the “Panelist ID” variable is stored as a string and uniquely identifies the panelist who provided the viewership information.
- panelists who are provided people meters may be assigned a panelist identifier to monitor the media exposure of the panelist.
- the panelist identifier is an obfuscated alphanumeric string to protect the identity of the panelist.
- the panelist identifier is obfuscated in a manner so that the same obfuscated panelist identifier information corresponds to the same panelist. In this manner, user activities may be monitored for particular users without exposing sensitive information regarding the panelist.
- the panelist identifier is used to identify demographic information associated with the panelist. For example, the panelist identifier “0123” may link to demographic information indicating the panelist is a male, age 18-49.
- the third example block of rows 270 identifies information regarding social media messages.
- the “Message ID” variable is stored as a string and is a unique identifier of a social media message.
- the example “Message Timestamp” variable is stored as a string data type and identifies the date and/or time when the corresponding social media message was posted.
- the example “Message Content” variable is stored as a string data type and identifies the content of corresponding social media message.
- the example “Message Author” variable is stored as a string data type and identifies the author of the corresponding social media message.
- the fourth example block of rows 275 represents overnight time-period ratings that may be used to estimate current ratings for a media asset.
- the example “Overnight Live” variable and the example “Overnight LiveSameDay” variable are stored as floating data types and represent “Live” ratings and “Live+Same Day” ratings based on time-periods.
- the “overnight live” ratings for the media asset “Sports Stuff” may represent the number of viewers who were tuned to Channel “ABC” between “20:00-20:30” on “Tuesday” (e.g., the broadcast time and network when “Sports Stuff” is scheduled to air).
- the media asset may not air at the scheduled time.
- the media asset “Sports Stuff” may have actually aired between “20:08-20:35.”
- the example “Actual Broadcast” variable 280 is stored as a string and identifies the actual broadcast time of the media asset (e.g., “20:08-20:35”).
- example raw data variables are represented in the example data table 200 of FIG. 2
- more or fewer raw data variables may be represented in the example data table 200 corresponding to the many raw audience measurement data variables that may be collected and/or provided by the audience measurement system(s) 105 of FIG. 1 .
- FIG. 4 is a block diagram of an example implementation of the data translator 140 of FIG. 1 that may facilitate manipulating and/or modifying raw audience measurement data 110 retrieved from the example raw data database 135 .
- the example data translator 140 translates the raw audience measurement data 110 to a form that may be meaningfully handled by the example model builder 150 to generate one or more lift prediction models.
- the example data translator 140 of FIG. 4 includes an example ratings handler 405 , an example attributes handler 410 and an example social media handler 415 .
- the ratings handler 405 , the attributes handler 410 and the social media handler 415 record the translated information in the example translated data database 145 of FIG. 1 .
- the example data translator 140 includes the example ratings handler 405 to process ratings-related information representative of media assets.
- the ratings handler 405 may query and/or retrieve ratings-related information from the raw data database 135 (e.g., current ratings information, historical ratings information, etc.) to translate into a form meaningfully handled by the example model builder 150 .
- An example data table 500 of the illustrated example of FIG. 5 illustrates example translated ratings data variables that may be recorded by the ratings handler 405 in the example translated data database 145 .
- the example data table 500 of the illustrated example of FIG. 5 includes a variable name identifier column 505 , a variable data type identifier column 510 and a variable meaning identifier column 515 .
- the example variable name identifier column 505 indicates example variables that may be associated with a media asset broadcast and/or useful for predicting time-shifted exposure to the media asset.
- the example variable data type identifier column 510 indicates a data type of the corresponding variable.
- the example variable meaning identifier column 515 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 500 of FIG. 5 , more or fewer variable identifier columns may be represented in the example data table 500 .
- the example data table 500 of the illustrated example of FIG. 5 includes five example rows corresponding to example translated ratings data variables.
- the first example row 550 indicates the ratings handler 405 of FIG. 4 stores the “Same Day Lift” variable as a floating data type.
- the ratings handler 405 determines a “Same Day Lift” value associated with a media asset of interest based on the “Ratings LiveSameDay” variable and the “Ratings Live” variable retrieved from the example raw data database 135 .
- the ratings handler 405 may query the raw data database 135 for the “Ratings LiveSameDay” rating and the “Ratings Live” rating related to a media asset of interest (e.g., season 2, episode 4 of “Sports Stuff”).
- the ratings handler 405 calculates the difference between the “Ratings LiveSameDay” rating and the “Ratings Live” rating and records the logarithm transformation of the calculated difference as the “Same Day Lift” of the media asset of interest in the example translated data database 145 .
- the second example row 555 indicates the ratings handler 405 determines a “Program Lead-In” value associated with a media asset of interest based on the “Lead-In Ratings” variable retrieved from the example raw data database 135 .
- the ratings handler 405 may query the raw data database 135 for the “Lead-In Ratings” rating related to a media asset of interest (e.g., season 2, episode 4 of “Sports Stuff”).
- the ratings handler 405 records the logarithm transformation of the returned rating as the “Program Lead-In” of the media asset of interest in the example translated data database 145 .
- the third example row 560 indicates the ratings handler 405 determines an “L7 Lift” value based on the “Ratings LivePlus7” variable and the “Ratings Live” variable retrieved from the example raw data database 135 .
- the ratings handler 405 may query the raw data database 135 for the “Ratings LivePlus7” rating and the “Ratings Live” rating related to a media asset of interest (e.g., season 2, episode 4 of “Sports Stuff”).
- the ratings handler 405 calculates the difference between the “Ratings LivePlus7” rating and the “Ratings Live” rating and records the logarithm transformation of the calculated difference as the “L7 Lift” of the media asset of interest in the example translated data database 145 .
- the fourth example row 565 indicates the ratings handler 405 determines a “Historical Ratings Lift” value based on the “Ratings LivePlus7” variable and the “Ratings Live” variable retrieved from the example raw data database 135 .
- the ratings handler 405 may query the raw data database 135 for the “Ratings LivePlus7” rating and the “Ratings Live” rating related to a media asset of interest.
- the ratings handler 405 calculates the “historical ratings lift” based on an average of “L7 Lift” values over, for example, two previous weeks (or episodes).
- the example ratings handler 405 retrieves the “Ratings LivePlus7” rating and the “Ratings Live” rating for season 2, episodes 2 and 3 of “Sports Stuff.” In the illustrated example, the ratings handler 405 calculates an average of the “L7 Lift” value for episode 2 of season 2 and the “L7 Lift” value for episode 3 of season 2. The example ratings handler 405 records the logarithm transformation of the average of the “L7 Lift” values as the “Historical Ratings Lift” of the media asset of interest in the example translated data database 145 .
- the fifth example row 570 indicates the ratings handler 405 determines a “Program Loyalty” score for a media asset based on an average number of episodes of the media viewed per user over a period (e.g., five weeks).
- the ratings handler 405 queries the raw data database 135 for panelist identifiers associated with panelists who viewed previously aired episodes of the media asset.
- the ratings handler 405 may determine the “program loyalty” score for episode 7 of season 1 of “Sports Stuff” by (1) identifying panelists who viewed at least one of episodes 2-6 of season 1 of “Sports Stuff,” (2) determining the total number of episodes 2-6 of season 1 that were viewed by each of the panelists and (3) calculating a ratio of the total number of episodes 2-6 of season 1 that were watched by each of the panelists and the total number of identified panelists.
- the ratings handler 405 records the calculated ratio as the “program loyalty” score of the media asset of interest (e.g., episode 7 of season 1 of “Sports Stuff”) in the example translated data database 145 .
- the example ratings handler 405 applies a logarithm transformation to the “Same Day Lift” variable (row 550 ), the “Program Lead-In” variable (row 555 ), the “L7 Lift” variable (row 560 ) and the example “Historical Ratings Lift” variable (row 565 ).
- the ratings handler 405 may additionally or alternatively apply different transformations, including no transformations, to the variables.
- FIG. 6 illustrates an example program loyalty score calculation.
- a “program loyalty” score 600 for a media asset is calculated based on the number of weeks a panelist viewed media over a five week period.
- three example panelists 605 , 610 , 615 are identified as panelists who viewed at least one episode of a program over a period of five weeks.
- the first example panelist 605 viewed four total episodes (e.g., watched during weeks 1-3 and week 5)
- the second example panelist 610 viewed three total episodes (e.g., watched during weeks 1, 2 and 5)
- the third example panelist 615 viewed one total episode (e.g., watched during week 1).
- a five-week period is used to determine a program loyalty score.
- any other period over which program loyalty is assessed may additionally or alternatively be used.
- any other technique for calculating program loyalty scores may additionally or alternatively be used.
- raw data related to a media asset may not be immediately available.
- panelist identifiers associated with panelists who viewed an episode may not be available, for example, for two weeks after the media asset is broadcast.
- the example ratings handler 405 may not determine a program loyalty score for a media asset that is earlier than, for example, episode seven of a season.
- the example data translator 140 includes the example attributes handler 410 to process attributes and/or characteristics representative of media assets.
- the attributes handler 410 may query and/or retrieve program attributes information from the raw data database 135 (e.g., genre-identifying information, day-of-week information, broadcast time-identifying information, etc.) to translate into a form meaningfully handled by the example model builder 150 .
- program attributes information e.g., genre-identifying information, day-of-week information, broadcast time-identifying information, etc.
- An example data table 700 of the illustrated example of FIG. 7 illustrates example translated program attributes data variables that may be recorded by the attributes handler 410 in the example translated data database 145 .
- the example data table 700 of the illustrated example of FIG. 7 includes a variable name identifier column 705 , a variable data type identifier column 710 and a variable meaning identifier column 715 .
- the example variable name identifier column 705 indicates example variables that may be associated with a media asset and/or useful for predicting time-shifted exposure to the media asset.
- the example variable data type identifier column 710 indicates a data type of the corresponding variable.
- the example variable meaning identifier column 715 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 700 of FIG. 7 , more or fewer variable identifier columns may be represented in the example data table 700 .
- the example data table 700 of the illustrated example of FIG. 7 includes thirteen example rows corresponding to example translated program attributes data variables.
- the example translated program attributes data variables of the data table 700 represent four example characteristics of a media asset.
- the first example block of rows 750 indicates that the example attributes handler 410 stores day-of-week information as Boolean variables.
- the attributes handler 410 translates day-of-week information that is stored as a string data type at the raw data database 135 to one or more day-of-week Boolean variables.
- the attributes handler 410 may retrieve day-of-week information related to a media asset indicating the date of the week that the media asset is broadcast (e.g., “Tuesday”) and set the corresponding day-of-week Boolean variable to true (e.g., “1”) and set (or reset) other day-of-week Boolean variables to false (e.g., “0”).
- day-of-week information related to a media asset indicating the date of the week that the media asset is broadcast (e.g., “Tuesday”) and set the corresponding day-of-week Boolean variable to true (e.g., “1”) and set (or reset) other day-of-week Boolean variables to false (e.g., “0”).
- the example attributes handler 410 in response to determining that the raw day-of-week information indicates the media asset is broadcast on a “Tuesday,” the example attributes handler 410 sets the value of the corresponding “Day Tues” variable to true (e.g., “1”) and sets (or resets) the values of the other day-of-week Boolean variables (e.g., “Day Mon,” “Day Wed,” “Day Thurs,” “Day Fri” and “Day SatSun”) to false (e.g., “0”).
- the example day-of-week information is represented as six example Boolean variables in the example data table 700 of FIG. 7 , any other number of Boolean variables may additionally or alternatively be used.
- the attributes handler 410 may group the days-of-week information into weekday or weekend Boolean variables.
- the second example block of rows 755 of the data table 700 of FIG. 7 indicates that the example attributes handler 410 stores genre-identifying information as Boolean variables.
- the attributes handler 410 translates genre-identifying information that is stored as a string data type at the raw data database 135 to one or more genre-related Boolean variables.
- the attributes handler 410 may retrieve genre-identifying information indicative of the genre classification of a media asset (e.g., a documentary, drama, variety, comedy, etc.) and set the corresponding genre-related Boolean variable to true (e.g., “1”) and set (or reset) other genre-related Boolean variables to false (e.g., “0”).
- the example attributes handler 410 in response to determining that retrieved raw genre-identifying information indicates the corresponding media asset is a “comedy,” the example attributes handler 410 sets the value of the corresponding “Genre Comedy” variable to true (e.g., “1”) and sets (or resets) the values of the other genre-related Boolean variables (e.g., “Genre Documentary,” “Genre Drama” and “Genre Variety”) to false (e.g., “0”).
- the example genre-identifying information is represented as four example genre-related Boolean variables in the example data table 700 of FIG. 7 , any other number of Boolean variables representative of the genre of a media asset may additionally or alternatively be used.
- the third example block of rows 760 of the data table 700 of FIG. 7 indicates that the example attributes handler 410 stores originator-identifying information as Boolean variables.
- the attributes handler 410 translates originator-identifying information that is stored as a string data type at the raw data database 135 to one or more originator-related Boolean variables.
- the attributes handler 410 may retrieve originator-identifying information indicative of the network (or channel) that broadcasts a media asset (e.g., channel “ABC,” channel “XYZ,” etc.) and set the corresponding originator-related Boolean variable to true (e.g., “1”) and set (or reset) other originator-related Boolean variables to false (e.g., “0”).
- the example attributes handler 410 in response to determining that retrieved raw originator-identifying information indicates the corresponding media asset is broadcast on channel “ABC,” the example attributes handler 410 sets the value of the corresponding “Originator ABC” variable to true (e.g., “1”) and sets (or resets) the values of the other originator-related Boolean variables (e.g., “Originator XYZ”) to false (e.g., “0”). While two example originators are represented in the example data table 700 of FIG. 7 , more or fewer originators may be represented in the example data table 700 corresponding to the many broadcast networks and cable networks that broadcast media assets.
- the example row 765 of the data table 700 of FIG. 7 indicates that the example attributes handler 410 stores broadcast time-identifying information as an integer data type.
- the attributes handler 410 maps broadcast time-identifying information that is stored as a string data type at the raw data database 135 to an integer.
- the attributes handler 410 may retrieve broadcast time-identifying information indicative of when a media asset is broadcast (e.g., “00:00-00:30,” “00:30-01:00,” . . . “23:30-00:00”) and set the “HH Block” variable value based on a corresponding half-hour block.
- the attributes handler 410 may map the broadcast time “00:00-00:00” to half-hour block “0,” may map the broadcast time “00:30-01:00” to half-hour block “1,” etc.
- the example broadcast time-identifying information is represented as half-hour blocks, any other granularity may additionally or alternatively be used.
- the broadcast times may be based on quarter-hours, full hours, etc.
- example data table 700 of FIG. 7 includes four example program attributes related to a media asset (e.g., day-of-week, genre, originator and broadcast time), any other number of program attributes may additionally or alternatively be used.
- a media asset e.g., day-of-week, genre, originator and broadcast time
- any other number of program attributes may additionally or alternatively be used.
- the example data translator 140 includes the example social media handler 415 to process social media messages representative of media assets.
- the social media handler 415 may query and/or retrieve social media messages and/or social media messages-related information from the raw data database 135 (e.g., message identifiers, message timestamps, message content, message authors, etc.) to translate into a form meaningfully handled by the example model builder 150 .
- the raw data database 135 e.g., message identifiers, message timestamps, message content, message authors, etc.
- An example data table 800 of the illustrated example of FIG. 8 illustrates example translated social media data variables that may be recorded by the social media handler 415 in the example translated data database 145 .
- the example data table 800 of the illustrated example of FIG. 8 includes a variable name identifier column 805 , a variable data type identifier column 810 and a variable meaning identifier column 815 .
- the example variable name identifier column 805 indicates example variables that may be associated with a media asset broadcast and/or information useful for predicting time-shifted exposure to the media asset.
- the example variable data type identifier column 810 indicates a data type of the corresponding variable.
- the example variable meaning identifier column 815 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 800 of FIG. 8 , more or fewer variable identifier columns may be represented in the example data table 800 .
- the example data table 800 of the illustrated example of FIG. 8 includes three example rows corresponding to example translated social media data variables.
- the first example row 850 indicates the social media handler 415 of FIG. 4 stores a “SM Count” variable as a floating data type in the example translated data database 145 .
- the social media handler 415 determines a “SM Count” value associated with a media asset of interest based on a number of posted social media messages of interest. For example, the social media handler 415 may inspect the social media messages returned by the raw data database 135 for social media messages that indicate exposure to a media asset.
- a media asset may be “Sports Stuff.”
- a social media message of interest may include the text “Jon is my favorite character on Sports Stuff!” and may include a message timestamp indicating that the social media message was posted by the message author during broadcast of the media asset.
- the social media handler 415 may count the number of social media messages identified as of interest and record a logarithm transformation of the number of social media messages of interest (e.g., the social media messages that indicate exposure to a media asset) as the “SM Count” corresponding to the media asset of interest in the example translated data database 145 .
- the second example row 855 of the data table 800 of FIG. 8 indicates that the example social media handler 415 stores a value related to the number of unique authors who posted social media messages of interest as a floating data type in the example translated data database 145 .
- the second example row 855 of the data table 800 of FIG. 8 indicates the social media handler 415 of FIG. 4 stores a “SM UAuthors” variable as a floating data type in the example translated data database 145 .
- the social media handler 415 determines a “SM UAuthors” value associated with a media asset of interest based on a number of unique authors who posted social media messages of interest.
- the social media handler 415 may inspect the social media messages returned by the raw data database 135 for social media messages that indicate exposure to a media asset.
- the social media handler 415 may count the number of unique authors who posted the social media messages identified as of interest and record a logarithm transformation of the number of unique authors as the “SM UAuthors” corresponding to the media asset of interest in the example translated data database 145 .
- the third example row 860 of the data table 800 of FIG. 8 indicates the social media handler 415 of FIG. 4 stores a “SM Impressions” variable as a floating data type in the example translated data database 145 .
- the social media handler 415 determines a “SM Impressions” value associated with a media asset of interest based on impression information associated with social media messages of interest. For example, the social media handler 415 may count the number of times social media messages identified as of interest were viewed by users of the social media service and record a logarithm transformation of the number of impressions of social media messages of interest as the “SM Impressions” corresponding to the media asset of interest in the example translated data database 145 .
- the example social media handler 415 applies a logarithm transformation to the “SM Count” variable (row 850 ), the “SM UAuthors” variable (row 855 ) and the example “SM Impressions” variable (row 860 ).
- the social media handler 415 may additionally or alternatively apply different transformations, including no transformations, to the variables.
- the example social media handler 415 inspects social media messages and/or social media messages-related information retrieved from the raw data database 135 to translate into a form meaningfully handled by the example model builder 150 .
- the raw audience measurement data 110 may be provided as aggregated data.
- the example audience measurement system(s) 105 of FIG. 1 may count the number of posted social media messages related to media assets of interest, may count the number of unique authors who posted social media messages related to media assets of interest and may count the number of impressions associated with posted social media messages related to media assets of interest, and provide the respective counts to the example central facility 125 .
- the example social media handler 415 may retrieve the respective counts and store the logarithm transformation of the corresponding numbers as the respective social media-related variables.
- any other technique may be used to determine the number of posted social media messages related to media assets of interest, the number of unique authors who posted social media messages related to media assets of interest and the number of impressions associated with posted social media messages related to media assets of interest.
- An example schema 900 of the illustrated example of FIG. 9 illustrates example ratings lift models based on season-episode groupings that may be used by the example model builder 150 when building lift prediction models and/or used by the example program ratings estimator 160 when applying data to a lift prediction model to predict a ratings list for a media asset of interest.
- the example schema 900 of the illustrated example of FIG. 9 includes a season identifier column 905 to identify a season number of a media asset, an episode number identifier column 910 to identify an episode number of a media asset and a lift prediction model identifier column 915 to identify a lift prediction model applicable to the corresponding season-episode grouping.
- the example schema 900 of FIG. 9 indicates that, in the illustrated example, during the first season of a media asset (corresponding section 930 of the schema 900 ), three different lift prediction models may be used.
- the first three episodes are associated with a first lift prediction model (Model 1 ).
- the example schema 900 also indicates that the next three episodes (e.g., episodes four through six of season one) are associated with a second lift prediction model (Model 2 ).
- the example schema 900 also indicates that episode seven and subsequent episodes of season one are associated with a third lift prediction model (Model 3 ).
- the example schema 900 indicates that during the second and subsequent seasons (corresponding to section 935 of schema 900 ), two different lift prediction models may be used. For example, the first six episodes of the second season are associated with the second lift prediction model (Model 2 ) while episodes seven and later are associated with the third lift prediction model (Model 3 ). While three example lift prediction models are represented in the example schema 900 of FIG. 9 , more or fewer lift prediction models may be represented in the example schema 900 based on different season-episode groupings.
- An example data table 1000 of the illustrated example of FIG. 10 illustrates example sets of translated data variables that are used when generating (e.g., training) lift prediction models and/or that are applied to a lift prediction model when estimating ratings lift for media assets of interest.
- the example data table 1000 of the illustrated example of FIG. 10 includes a variable identifier column 1005 , a first lift prediction model identifier column 1010 , a second lift prediction model identifier column 1015 and a third lift prediction model identifier column 1020 .
- the three example lift prediction models of FIG. 10 correspond to the three example lift prediction models of FIG. 9 .
- the example data table 1000 of the illustrated example of FIG. 10 includes example rows corresponding to example translated ratings data variables (e.g., features) that are applied to the respective lift prediction models.
- the first example row 1050 corresponds to different demographic groupings (e.g., households, persons age two and up, persons between the ages of 25 and 54 and persons between the ages of 19 and 49).
- social media indicators may not be a predictive variable for media assets whose audience(s) tends to not use social media services.
- example data table 1000 indicates that twelve lift prediction models are generated and/or applied (e.g., four demographic groupings for each of the three lift prediction models), any other number of lift prediction models may additionally or alternatively be used.
- the number of demographic groupings for one or more of the example lift prediction models vary based on, for example, client preference.
- the example data table 1000 of the illustrated example of FIG. 10 indicates that current TV ratings 1055 (e.g., “live+same day” ratings and “live” ratings), program lead-in 1060 (e.g., program lead-in ratings), program characteristics 1065 (e.g., day-of-week, genre, originator and half-hour block broadcast time) and social media indicators 1070 are used when training each of the lift prediction models and/or when applying each of lift prediction models.
- the current TV ratings 1055 correspond to the example audience measurement data 110 provided from the audience measurement system(s) 105 and used when building and/or training the lift prediction models.
- the current TV ratings 1055 correspond to the estimated current TV ratings determined by the example program ratings estimator 160 of FIG. 1 .
- historical TV ratings data 1075 is not used when generating and/or applying the first example lift predictor model, but is used with respect to the second and third example lift predictor models. Excluding the historical TV ratings data may be beneficial in connection with the first example lift predictor model because, as described above, the historical TV ratings data includes determining an average of previous TV ratings of the media asset. In some such instances, because the media asset is a new program (e.g., one of the first three episodes of the program), previous TV ratings may not be available (e.g., when the media asset of interest is the pilot) and/or may not be a reliable predictor of ratings lift. For example, consumers may switch between different pilots and/or episodes as they evaluate whether the program is worth their time, resulting in skewed TV ratings for the first and/or second episodes.
- program loyalty scores 1080 are excluded from the first and second example lift prediction models, but are included with respect to the third example lift prediction model.
- excluding program loyalty scores may be beneficial in connection with the first and second example lift prediction models because, as described above, the program loyalty scores are determined based on five previous episodes and, in some examples, may also include a two-week lag. In some such instances, because seven episodes-worth of audience measurement data is needed to develop the program loyalty scores, including such scores in the first and/or second example lift prediction models would not be useful in estimating ratings lift for the media asset.
- While an example manner of implementing the central facility 125 of FIG. 1 is illustrated in FIG. 1 , one or more of the elements, processes and/or devices illustrated in FIG. 1 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way.
- the example data interface 130 , the example raw data database 135 , the example data translator 140 , the example translated data database 145 , the example model builder 150 , the example models database 155 , the example program ratings estimator 160 and/or, more generally, the example central facility 125 of FIG. 1 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware.
- any of the example data interface 130 , the example raw data database 135 , the example data translator 140 , the example translated data database 145 , the example model builder 150 , the example models database 155 , the example program ratings estimator 160 and/or, more generally, the example central facility 125 of FIG. 1 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)).
- ASIC application specific integrated circuit
- PLD programmable logic device
- FPLD field programmable logic device
- the example central facility 125 of FIG. 1 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware.
- the example central facility 125 of FIG. 1 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 1 , and/or may include more than one of any or all of the illustrated elements, processes and devices.
- FIG. 4 While an example manner of implementing the data translator 140 of FIG. 1 is illustrated in FIG. 4 , one or more of the elements, processes and/or devices illustrated in FIG. 4 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way.
- the example ratings handler 405 , the example attributes handler 410 , the example social media handler 415 and/or, more generally, the example data translator 140 of FIG. 4 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware.
- example data translator 140 of FIG. 1 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 4 , and/or may include more than one of any or all of the illustrated elements, processes and devices.
- FIGS. 11-13 and/or 14 Flowcharts representative of example machine readable instructions for implementing the example central facility of FIG. 1 are shown in FIGS. 11-13 and/or 14 .
- the machine readable instructions comprise a program for execution by a processor such as the processor 1512 shown in the example processor platform 1500 discussed below in connection with FIG. 15 .
- the program may be embodied in software stored on a tangible computer readable storage medium such as a CD-ROM, a floppy disk, a hard drive, a digital versatile disk (DVD), a Blu-ray disk, or a memory associated with the processor 1512 , but the entire program and/or parts thereof could alternatively be executed by a device other than the processor 1512 and/or embodied in firmware or dedicated hardware.
- example program is described with reference to the flowcharts illustrated in FIGS. 11-13 and/or 14 , many other methods of implementing the example central facility 125 may alternatively be used.
- order of execution of the blocks may be changed, and/or some of the blocks described may be changed, eliminated, or combined.
- FIGS. 11-13 and/or 14 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a tangible computer readable storage medium such as a hard disk drive, a flash memory, a read-only memory (ROM), a compact disk (CD), a digital versatile disk (DVD), a cache, a random-access memory (RAM) and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information).
- coded instructions e.g., computer and/or machine readable instructions
- a tangible computer readable storage medium such as a hard disk drive, a flash memory, a read-only memory (ROM), a compact disk (CD), a digital versatile disk (DVD), a cache, a random-access memory (RAM) and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for
- tangible computer readable storage medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media.
- tangible computer readable storage medium and “tangible machine readable storage medium” are used interchangeably. Additionally or alternatively, the example processes of FIGS.
- 11-13 and/or 14 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a non-transitory computer and/or machine readable medium such as a hard disk drive, a flash memory, a read-only memory, a compact disk, a digital versatile disk, a cache, a random-access memory and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information).
- a non-transitory computer readable medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media.
- FIG. 11 is a flowchart representative of example machine-readable instructions 1100 that may be executed by the example central facility 125 of FIG. 1 to predict time-shifted exposure to media.
- the example instructions 1100 of FIG. 11 begin at block 1102 when the example central facility 125 receives audience measurement data 110 from the example audience measurement system(s) of FIG. 1 .
- the example data interface 130 may periodically obtain and/or retrieve example panelist media measurement data 110 A and/or example social media activity data 110 B.
- the data interface 130 may obtain and/or retrieve the example audience measurement data 110 aperiodically and/or as a one-time event.
- the example data interface 130 stores the audience measurement data 110 in the example raw data database 135 ( FIG. 1 ).
- the example central facility 125 normalizes the audience measurement data 110 .
- the example data translator 140 may manipulate and/or modify features of the audience measurement data 110 from their raw form to be more meaningfully handled when building the prediction models and estimating the ratings lift.
- the example data translator 140 stores the translated data variables in the example translated data database 145 ( FIG. 1 ). An example approach to normalize audience measurement data 110 is described below in connection with FIG. 12 .
- the example central facility 125 builds a lift prediction model.
- the example model builder 150 ( FIG. 1 ) determines a relationship between translated data variables stored in the example translated data database 145 and ratings lifts.
- the example model builder 150 stores the generated model(s) in the example models data store 155 ( FIG. 1 ).
- An example approach to build a lift prediction model is described below in connection with FIG. 13 .
- the example central facility 125 determines an estimated ratings lift for a media asset of interest.
- the example program ratings estimator 160 may apply data related to the media asset of interest to a lift prediction model to estimate a ratings lift for the media asset.
- An example approach to determine an estimated ratings lift is described below in connection with FIG. 14 .
- the example process 1100 of FIG. 11 ends.
- example instructions 1100 of FIG. 11 represent a single iteration of predicting time-shifted exposure to media
- example instructions 1100 of the illustrated example of FIG. 11 may be executed in parallel (e.g., in separate threads) to allow the central facility 125 to handle multiple requests for ratings lift estimations at a time.
- FIG. 12 is a flowchart representative of example machine-readable instructions 1200 that may be executed by the example data translator 140 of FIGS. 1 and/or 4 to normalize raw audience measurement data.
- the example process 1200 of the illustrated example of FIG. 12 begins at block 1202 when the example data translator 140 obtains ratings-related information associated with media assets.
- the data translator 140 may retrieve and/or query “live+same day” ratings, “live” ratings, “live+7” ratings and/or information representative of whether a panelist viewed a particular episode of a media asset from the example raw data database 135 .
- the example data translator 140 translates the ratings-related information to ratings data variables for use by the example model builder 150 and/or the example program ratings estimator 160 .
- the data translator translates the ratings-related information in accordance with the example translated ratings data variables table 500 of FIG. 5 .
- the example data translator 140 determines whether there is additional ratings-related information to translate. If, at block 1206 , the data translator 140 determined that there is additional ratings-related information to translate, control returns to block 1202 .
- the example data translator 140 obtains program attributes information associated with media assets. For example, the data translator 140 may retrieve and/or query the example raw data database 135 for day-of-week information, genre information, originator information and/or broadcast time information.
- the example data translator 140 translates the program attributes information to program attributes data variables for use by the example model builder 150 and/or the example program ratings estimator 160 . In the illustrated example, the data translator translates the program attributes information in accordance with the example translated program attributes data variables table 700 of FIG. 7 .
- the example data translator 140 determines whether there is additional program attributes information to translate. If, at block 1212 , the data translator 140 determined that there is additional program attributes information to translate, control returns to block 1208 .
- the example data translator 140 obtains social media messages-related information associated with media assets. For example, the data translator 140 may retrieve and/or query the example raw data database 135 for a number of posted social media messages of interest, a number of unique authors who posted social media messages of interest and/or a number of impressions of social media messages of interest.
- the example data translator 140 translates the social media messages-related information to social media data variables for use by the example model builder 150 and/or the example program ratings estimator 160 . In the illustrated example, the data translator translates the social media messages-related information in accordance with the example translated social media data variables table 800 of FIG. 8 .
- the example data translator 140 determines whether there is additional social media messages-related information to translate. If, at block 1218 , the data translator 140 determined that there is additional social media messages-related information to translate, control returns to block 1214 .
- the example data translator 140 determines whether to continue normalizing audience measurement data. If, at block 1220 , the example data translator 140 determined to continue normalizing audience measurement data, control returns to block 1202 to wait to obtain ratings-related information for translating.
- the example data translator 140 determines not to continue normalizing audience measurement data, the example process 1200 of FIG. 12 ends.
- example instructions 1200 of FIG. 12 represent a single iteration of normalizing audience measurement data
- example instructions 1200 of the illustrated example of FIG. 12 may be executed in parallel (e.g., in separate threads) to allow the central facility 125 to handle multiple requests for normalizing audience measurement data at a time.
- FIG. 13 is a flowchart representative of example machine-readable instructions 1300 that may be executed by the example model builder 150 of FIG. 1 to build a lift prediction model used to estimate ratings lift for media assets of interest.
- the example instructions 1300 of FIG. 13 begin at block 1302 when the example model builder 150 selects a lift prediction model to build based on the translated data variables stored in the example translated data database 145 of FIG. 1 .
- the model builder 150 may select a lift prediction model based on season-episode groupings of a particular media asset of interest for which ratings list is to be predicted.
- the example model builder 150 selects a demographic grouping associated with the lift prediction model.
- the model builder 150 may generate a plurality of lift prediction models corresponding to different demographic segments.
- the example model builder 150 obtains translated data variables based on the selected lift prediction model and the selected demographic grouping. For example, depending on the selected lift prediction model, the model builder 150 may obtain program characteristics, social media indicators, current ratings information, historical ratings information and/or program loyalty scores for different media assets. In some examples, the model builder 150 may consult the example data table 1000 of the illustrated example of FIG. 10 to determine the translated data variables associated with the selected lift prediction model.
- the example model builder 150 determines a relationship between the obtained translated data variables and rating lifts.
- the model builder 150 may represent the lift prediction model via an equation (e.g., the example Equation 1 described above) and by applying logistic regression to the translated data variables, the model builder 150 may solve for coefficients of the equation.
- the example model builder 150 records the generated lift prediction model. For example, the model builder 150 may store the determined coefficients in the example models data store 155 of FIG. 1 .
- the example model builder 150 determines whether there is another demographic grouping to process for the selected lift prediction model. If, at 1312 , the model builder 150 determined that there is another demographic grouping to process, then control returns to block 1304 to select a demographic grouping to process.
- the example model builder 150 determines whether there is another lift prediction model to build. For example, the model builder 150 may determine whether to build lift prediction models for a different season-episode grouping of a different media asset for which ratings lift is to be predicted. If, at block 1314 , the model builder 150 determined that there is another lift prediction model to build, then control returns to block 1302 to select a lift prediction model.
- FIG. 14 is a flowchart representative of example machine-readable instructions 1400 that may be executed by the example program ratings estimator 160 of FIG. 1 to predict time-shifted exposure to media.
- the example instructions 1400 of FIG. 14 begin at block 1402 when the example program ratings estimator 160 selects a lift prediction model to use to estimate ratings lift for a media asset of interest.
- the example program ratings estimator 160 may select a lift prediction model based on season and episode number information associated with the media asset of interest.
- the program ratings estimator 160 may consult the example schema 900 of the illustrated example of FIG. 9 to identify a lift prediction model based on season-episode groupings.
- the example program ratings estimator 160 obtains translated data variables based on the selected lift prediction model. For example, depending on the selected lift prediction model, the program ratings estimator 160 may obtain, for the media asset of interest, program characteristics, social media indicators, historical ratings information and/or program loyalty scores. In some examples, the program ratings estimator 160 may consult the example data table 1000 of the illustrated example of FIG. 10 to determine the translated data variables associated with the selected lift prediction model.
- the example program ratings estimator 160 determines estimated current ratings information for the media asset of interest. For example, the program ratings estimator 160 may process time-period ratings (e.g., overnight ratings provided via a fast affiliates report) and actual broadcast information to estimate current ratings (e.g., “live” ratings and “live+same day” ratings) associated with the media asset of interest to determine estimated current ratings for the media asset. In some examples, the program ratings estimator 160 may further process such information to estimate program lead-in ratings associated with the program that precedes the media asset of interest.
- time-period ratings e.g., overnight ratings provided via a fast affiliates report
- actual broadcast information e.g., current ratings and “live+same day” ratings
- the example program ratings estimator 160 applies the translated data variables and the estimated current ratings to the selected lift prediction model to determine the estimated ratings lift for the media asset of interest.
- the example program ratings estimator 160 determines whether there is another media asset of interest to process. If, at block 1410 , the example program ratings estimator 160 determined that there is another media asset of interest to process, then control returns to block 1402 to select a lift prediction model.
- the example program ratings estimator 160 determines that there is not another media asset of interest to process. If, at block 1410 , the example program ratings estimator 160 determined that there is not another media asset of interest to process, the example process 1400 of FIG. 14 ends.
- FIG. 15 is a block diagram of an example processor platform 1500 capable of executing the instructions of FIGS. 11-13 and/or 14 to implement the central facility 125 of FIG. 1 and/or the data translator 140 of FIGS. 1 and/or 4 .
- the processor platform 1500 can be, for example, a server, a personal computer, or any other type of computing device.
- the processor platform 1500 of the illustrated example includes a processor 1512 .
- the processor 1512 of the illustrated example is hardware.
- the processor 1512 can be implemented by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired family or manufacturer.
- the processor 1512 of the illustrated example includes a local memory 1513 (e.g., a cache).
- the processor 1512 of the illustrated example executes the instructions to implement the example data interface 130 , the example raw data database 135 , the example data translator 140 , the example translated data database 145 , the example model builder 150 , the example models database 155 , the example program ratings estimator 160 , the example ratings handler 405 , the example attributes handler 410 and the example social media handler 415 .
- the processor 1512 of the illustrated example is in communication with a main memory including a volatile memory 1514 and a non-volatile memory 1516 via a bus 1518 .
- the volatile memory 1514 may be implemented by Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM) and/or any other type of random access memory device.
- the non-volatile memory 1516 may be implemented by flash memory and/or any other desired type of memory device. Access to the main memory 1514 , 1516 is controlled by a memory controller.
- the processor platform 1500 of the illustrated example also includes an interface circuit 1520 .
- the interface circuit 1520 may be implemented by any type of interface standard, such as an Ethernet interface, a universal serial bus (USB), and/or a PCI express interface.
- one or more input devices 1522 are connected to the interface circuit 1520 .
- the input device(s) 1522 permit(s) a user to enter data and commands into the processor 1512 .
- the input device(s) can be implemented by, for example, an audio sensor, a microphone, a camera (still or video), a keyboard, a button, a mouse, a touchscreen, a track-pad, a trackball, isopoint and/or a voice recognition system.
- One or more output devices 1524 are also connected to the interface circuit 1520 of the illustrated example.
- the output devices 1524 can be implemented, for example, by display devices (e.g., a light emitting diode (LED), an organic light emitting diode (OLED), a liquid crystal display, a cathode ray tube display (CRT), a touchscreen, a tactile output device, a printer and/or speakers).
- the interface circuit 1520 of the illustrated example thus, typically includes a graphics driver card, a graphics driver chip or a graphics driver processor.
- the interface circuit 1520 of the illustrated example also includes a communication device such as a transmitter, a receiver, a transceiver, a modem and/or network interface card to facilitate exchange of data with external machines (e.g., computing devices of any kind) via a network 1526 (e.g., an Ethernet connection, a digital subscriber line (DSL), a telephone line, coaxial cable, a cellular telephone system, etc.).
- a communication device such as a transmitter, a receiver, a transceiver, a modem and/or network interface card to facilitate exchange of data with external machines (e.g., computing devices of any kind) via a network 1526 (e.g., an Ethernet connection, a digital subscriber line (DSL), a telephone line, coaxial cable, a cellular telephone system, etc.).
- DSL digital subscriber line
- the processor platform 1500 of the illustrated example also includes one or more mass storage devices 1528 for storing software and/or data.
- mass storage devices 1528 include floppy disk drives, hard drive disks, compact disk drives, Blu-ray disk drives, RAID systems, and digital versatile disk (DVD) drives.
- the example mass storage 1528 implements the example raw data database 135 , the example translated data database 145 and the example models data store 155 .
- the coded instructions 1532 of FIGS. 11-13 and/or 14 may be stored in the mass storage device 1528 , in the volatile memory 1514 , in the non-volatile memory 1516 , and/or on a removable tangible computer readable storage medium such as a CD or DVD.
- disclosed examples include building a lift prediction model based on historical audience measurement data. Examples disclosed herein may then apply data related to the media to the lift prediction model to predict time-shifted viewing of the media. In some examples, real-time ratings information (e.g., overnight ratings) is also applied to the lift prediction model to predict the time-shifted viewing of the media.
- real-time ratings information e.g., overnight ratings
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Social Psychology (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
- This patent claims the benefit of, and priority from, U.S. Provisional Patent Application No. 62/083,716, filed Nov. 24, 2014, entitled “Methods and Apparatus to Predict TV Rating Lift.” U.S. Provisional Patent Application No. 62/083,716 is hereby incorporated by reference in its entirety.
- This disclosure relates generally to audience measurement, and, more particularly, to methods and apparatus to predict time-shifted exposure to media.
- Audience measurement of media (e.g., content and/or advertisements presented by any type of medium such as television, in theater movies, radio, Internet, etc.) is typically carried out by monitoring media exposure of panelists that are statistically selected to represent particular demographic groups. Audience measurement companies, such as The Nielsen Company (US), LLC, enroll households and persons to participate in measurement panels. By enrolling in these measurement panels, households and persons agree to allow the corresponding audience measurement company to monitor their exposure to information presentations, such as media output via a television, a radio, a computer, etc. Using various statistical methods, the collected media exposure data is processed to determine the size and/or demographic composition of the audience(s) for media of interest. The audience size and/or demographic information is valuable to, for example, advertisers, broadcasters, content providers, manufacturers, retailers, product developers, and/or other entities. For example, audience size and demographic information is a factor in the placement of advertisements, in valuing commercial time slots during a particular program and/or generating ratings for piece(s) of media.
-
FIG. 1 illustrates an example system for audience measurement analysis implemented in accordance with the teachings of this disclosure to predict time-shifted exposure to media. -
FIG. 2 is an example data table that may be used by the example central facility ofFIG. 1 to store raw data variables in the example raw data database ofFIG. 1 . -
FIG. 3 is an example calculation of estimated current television ratings that may be performed by the example program ratings estimator ofFIG. 1 . -
FIG. 4 is an example block diagram of an example implementation of the data translator ofFIG. 1 . -
FIG. 5 is an example data table that may be used by the example data translator ofFIGS. 1 and/or 4 to translate ratings data variables. -
FIG. 6 is an example calculation of estimated current television ratings that may be performed by the example ratings handler ofFIG. 4 . -
FIG. 7 is an example data table that may be used by the example data translator ofFIGS. 1 and/or 4 to translate program attributes data variables. -
FIG. 8 is an example data table that may be used by the example data translator ofFIGS. 1 and/or 4 to translate social media data variables. -
FIG. 9 is an example schema that may be used by the example central facility ofFIG. 1 to determine lift prediction models based on season-episode groupings. -
FIG. 10 is an example data table that may be used by the example central facility ofFIG. 1 to associate translated data variables to corresponding lift prediction models. -
FIG. 11 is a flowchart representative of example machine-readable instructions that may be executed by the example central facility ofFIG. 1 to predict time-shifted exposure to media. -
FIG. 12 is a flowchart representative of example machine-readable instructions that may be executed by the example data translator ofFIGS. 1 and/or 4 to normalize raw audience measurement data. -
FIG. 13 is a flowchart representative of example machine-readable instructions that may be executed by the example model builder ofFIG. 1 to build a lift prediction model. -
FIG. 14 is a flowchart representative of example machine-readable instructions that may be executed by the example program ratings estimator ofFIG. 1 to predict time-shifted exposure to media. -
FIG. 15 is a block diagram of an example processing platform structured to execute the example machine-readable instructions ofFIGS. 11-13 and/or 14 to implement the example central facility and/or the example data translator ofFIGS. 1 and/or 4 . - Wherever possible, the same reference numbers will be used throughout the drawing(s) and accompanying written description to refer to the same or like parts.
- Examples disclosed herein facilitate predicting time-shifted exposure to media. For example, disclosed examples enable prediction of television ratings for households tuned to (or persons exposed to) a program or time-period of a specific station or cable network at the actual time that the program was telecast (e.g., live ratings), and any delayed viewing of the program during a predetermined time period. For example, “live+7” ratings represent the percentage of an audience that was exposed to media during the original telecast of the media (e.g., the live ratings) and the incremental viewing that takes place during the 7 days following the original telecast.
- Exposure information (e.g., ratings) may be useful for determining a marketing campaign and/or evaluating the effectiveness of a marketing campaign. For example, an advertiser who wants exposure of their asset (e.g., a product, a service, etc.) to reach a specific audience will place advertisements in media (e.g., a television program) whose audience represents the characteristics of the target market. In some examples, networks determine the cost of including an advertisement in their media based on the ratings of the media. For example, a high rating for a television program represents a large number of audience members who tuned to (or were exposed to) the television program. In such instances, the larger the audience of a television program (e.g., a higher rating), the more networks can charge for advertisements during the program.
- Traditionally, live ratings were used as the metric for evaluating the performance of media. However, as the methods for consuming media have evolved, there is an increasing trend in time-shifted viewing of media. For example, it is becoming more common for consumers to watch a television program via a digital video recorder (DVR) or video-on-demand service at a time that is convenient to them. In some instances, time-shifted viewing may account for fifty percent of the viewership of a television program. In such instances, live ratings do not accurately represent the audience size of the television program.
- “Live+7” ratings more accurately represent how viewers are watching media. “Live+7” ratings reflect viewing done via DVR services and/or video-on-demand services within seven days (e.g., 168 hours) of the original telecast of the program. In some instances, the additional viewership that is included in “live+7” ratings can make or break whether a low profile program is renewed or cancelled. However, measuring “live+7” ratings involves waiting at least seven days to determine the time-shifted viewing.
- Examples disclosed herein facilitate predicting time-shifted viewing of media. Examples disclosed herein collect and/or develop audience measurement data related to media. For example, disclosed examples measure audience exposure to television programs via people meters and/or by monitoring social media messages referencing television programs. Examples disclosed herein use the audience measurement data to build and/or train lift prediction models that may be used to estimate ratings lift. For example, disclosed examples determine a relationship between features of the audience measurement data and historical ratings lifts. As used herein, features of the audience measurement data include, but are not limited to, current and historical ratings-related information, social media indicators, characteristics of the media asset, etc.
- Examples disclosed herein apply data related to a media asset of interest to a lift prediction model to determine a predicted lift for the media asset. In some disclosed examples, different lift prediction models are developed based on characteristics of the media asset. For example, disclosed examples may characterize media assets based on season-episode groupings. In some such examples, the data applied to a lift prediction model to determine estimated ratings lift may depend on the season-episode grouping.
-
FIG. 1 is a diagram of an example environment in which asystem 100 constructed in accordance with the teachings of this disclosure operates to predict time-shifted exposure to media of interest. Theexample system 100 ofFIG. 1 includes one or more audience measurement system(s) 105 and acentral facility 125 to facilitate predicting time-shifted exposure to media of interest in accordance with the teachings of this disclosure. In the illustrated example ofFIG. 1 , thecentral facility 125 estimates an increase in viewership (e.g., a “lift”) over a period of seven days after the initial (e.g., live) broadcast of media of interest (e.g., a television show). However, any other time-shifted period may additionally or alternatively be used. - The
example system 100 ofFIG. 1 includes the one or more audience measurement system(s) 105 to collectaudience measurement data 110 from panelists and non-panelists. The example audience measurement system(s) 105 ofFIG. 1 collect panelistmedia measurement data 110A via, for example, people meters operating in statistically-selected households, set-top boxes and/or other media devices (e.g., such as digital video recorders, personal computers, tablet computers, smartphones, etc.) capable of monitoring and returning monitored data for media presentations, etc. The example panelistmedia measurement data 110A ofFIG. 1 includes media exposure data such as live exposure data, delayed exposure data (e.g., relative to time-shifted viewing of media via, for example, a digital video recorder and/or video on-demand), media performance data such as TV ratings (e.g., historical TV ratings and current TV ratings), program characteristics (e.g., attributes) such as broadcast day-of-week information, broadcast time information, originator information (e.g., a network or channel that broadcast the media) and/or genre information, etc. In some examples, the panelistmedia measurement data 110A is associated with demographic information (e.g., gender, age, income, etc.) of the panelists exposed to the media. - As used herein, the term “media” includes any type of content and/or advertisement delivered via any type of distribution medium. Thus, media includes television programming or advertisements, radio programming or advertisements, movies, web sites, streaming media, etc.
- Example methods, apparatus, and articles of manufacture disclosed herein monitor media presentations at media devices. Such media devices may include, for example, Internet-enabled televisions, personal computers, Internet-enabled mobile handsets (e.g., a smartphone), video game consoles (e.g., Xbox®, PlayStation®), tablet computers (e.g., an iPad®), digital media players (e.g., a Roku® media player, a Slingbox®, etc.), etc. In some examples, media monitoring information is aggregated to determine ownership and/or usage statistics of media devices, relative rankings of usage and/or ownership of media devices, types of uses of media devices (e.g., whether a device is used for browsing the Internet, streaming media from the Internet, etc.), and/or other types of media device information. In examples disclosed herein, monitoring information includes, but is not limited to, media identifying information (e.g., media-identifying metadata, codes, signatures, watermarks, and/or other information that may be used to identify presented media), application usage information (e.g., an identifier of an application, a time and/or duration of use of the application, a rating of the application, etc.), and/or user-identifying information (e.g., demographic information, a user identifier, a panelist identifier, a username, etc.).
- The example audience measurement system(s) 105 of
FIG. 1 also collect socialmedia activity data 110B related to media via, for example, social media servers that provide social media services to users of the social media server. As used herein, the term social media services is defined to be a service provided to users to enable users to share information (e.g., text, images, data, etc.) in a virtual community and/or network. Example social media services may include, for example, Internet forums (e.g., a message board), blogs, micro-blogs (e.g., Twitter®), social networks (e.g., Facebook®, LinkedIn, Instagram, etc.), etc. For example, the audience measurement system(s) 105 may monitor social media messages communicated via social media services and identify media-exposure social media messages (e.g., social media messages that reference at least one media asset (e.g., media and/or a media event)). The example audience measurement system(s) 105 may filter the media-exposure social media messages for media-exposure social media messages of interest (e.g., social media messages that reference media of interest). - The example social
media activity data 110B ofFIG. 1 includes one or more of message identifying information (e.g., a message identifier, a message author, etc.), timestamp information indicative of when the social media message was posted and/or viewed, the content of the social media message and an identifier of the media asset referenced in the media-exposure social media message. In some examples, the audience measurement system(s) 105 may process the media-exposure social media messages of interest and aggregate information related to the social media messages. For example, the audience measurement system(s) 105 may determine a count of the media-exposure social media messages of interest, may determine a number of unique authors who posted the media-exposure social media messages of interest and/or may determine a number of impressions of (e.g., exposure to) the media-exposure social media messages of interest. - In the illustrated example of
FIG. 1 , the audience measurement system(s) 105 send theaudience measurement data 110 to thecentral facility 125 via anexample network 115. Theexample network 115 of the illustrated example ofFIG. 1 is the Internet. However, theexample network 115 may be implemented using any suitable wired and/or wireless network(s) including, for example, one or more data buses, one or more Local Area Networks (LANs), one or more wireless LANs, one or more cellular networks, one or more private networks, one or more public networks, etc. Theexample network 115 enables thecentral facility 125 to be in communication with the audience measurement system(s) 105. As used herein, the phrase “in communication,” including variances therefore, encompasses direct communication and/or indirect communication through one or more intermediary components and does not require direct physical (e.g., wired) communication and/or constant communication, but rather includes selective communication at periodic or aperiodic intervals, as well as one-time events. - In the illustrated example, the
central facility 125 is operated by an audience measurement entity (AME) 120. Theexample AME 120 of the illustrated example ofFIG. 1 is an entity such as The Nielsen Company (US), LLC that monitors and/or reports exposure to media and operates as a neutral third party. That is, in the illustrated example, theaudience measurement entity 120 does not provide media (e.g., content and/or advertisements) to end users. This un-involvement with the media production and/or delivery ensures the neutral status of theaudience measurement entity 120 and, thus, enhances the trusted nature of the data theAME 120 collects and processes. The reports generated by the audience measurement entity (sometimes referred to as an “audience analytics entity” (AAE)) may identify aspects of media usage such as the number of people who are watching television programs and characteristics of the audiences (e.g., demographic information of who is watching the television programs, when they are watching the television programs, etc.). - The
example AME 120 ofFIG. 1 operates thecentral facility 125 to predict time-shifted exposure to media such as a lift in ratings associated with a media asset of interest over a course of 7 days (e.g., 168 hours) after the initial broadcast of the media asset. As used herein, a media asset of interest is a particular media program (e.g., identified via an episode number and season number) that is being analyzed (e.g., for a report). For example, a first media asset of interest may beepisode 3 ofseason 2 of a program “Sports Stuff” and a second media asset of interest may beepisode 4 ofseason 2 of the program “Sports Stuff.” Thecentral facility 125 of the illustrated example includes a server and/or database that collects and/or receives audience measurement data related to media assets (e.g., media and/or media events) and predicts time-shifted (or delayed) exposure to media assets of interest. - In some examples, the
central facility 125 is implemented using multiple devices and/or the audience measurement system(s) 105 is (are) implemented using multiple devices. For example, thecentral facility 125 and/or the audience measurement system(s) 105 may include disk arrays and/or multiple workstations (e.g., desktop computers, workstation servers, laptops, etc.) in communication with one another. In the illustrated example, thecentral facility 125 is in communication with the audience measurement system(s) 105 via one or more wired and/or wireless networks represented by thenetwork 115. - The example
central facility 125 of the illustrated example ofFIG. 1 processes theaudience measurement data 110 returned by the audience measurement system(s) 105 to predict time-shifted exposure to media. For example, thecentral facility 125 may process theaudience measurement data 110 to determine a relationship between features (sometimes referred to herein as “variables,” “predictors” or “factors”) of theaudience measurement data 110 and measured lift to build one or more prediction models. The examplecentral facility 125 may then apply data associated with a media asset of interest to a prediction model to determine a predicted lift for the media asset. - In the illustrated example of
FIG. 1 , thecentral facility 125 includes anexample data interface 130, an exampleraw data database 135, anexample data translator 140, an example translateddata database 145, anexample model builder 150, an examplemodels data store 155 and an exampleprogram ratings estimator 160. In the illustrated example ofFIG. 1 , the examplecentral facility 125 includes theexample data interface 130 to provide an interface between thenetwork 115 and thecentral facility 125. For example, thedata interface 130 may be a wired network interface, a wireless network interface, a Bluetooth® network interface, etc. and may include the associated software and/or libraries needed to facilitate communication between thenetwork 115 and thecentral facility 125. In the illustrated example ofFIG. 1 , thedata interface 130 receives theaudience measurement data 110 returned by the example audience measurement system(s) 105 ofFIG. 1 . The example data interface 130 records theaudience measurement data 110 in the exampleraw data database 135. - In the illustrated example of
FIG. 1 , the examplecentral facility 125 includes the exampleraw data database 135 to record data (e.g., the example audience measurement data 110) provided by the audience measurement system(s) 105 via theexample data interface 130. An example data table 200 of the illustrated example ofFIG. 2 illustrates example raw data variables that may be recorded in the exampleraw data database 135. The exampleraw data database 135 may be implemented by a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM), etc.) and/or a non-volatile memory (e.g., flash memory). The exampleraw data database 135 may additionally or alternatively be implemented by one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The exampleraw data database 135 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example theraw data database 135 is illustrated as a single database, theraw data database 135 may be implemented by any number and/or type(s) of databases. - The example
central facility 125 of the illustrated example ofFIG. 1 combines multiple disparate data sets to enable modeling and assessment of multiple inputs simultaneously. As described below, at least some of the variables are translated (e.g., modified and/or manipulated) from their raw form to be more meaningfully handled when building the prediction models and estimating the ratings lift. For example, raw data may be multiplied, aggregated, averaged, etc., and stored as translated data (sometimes referred to herein as “sanitized,” “normalized” or “recoded” data) prior to generating the prediction models used to estimate ratings lift. - In the illustrated example of
FIG. 1 , the examplecentral facility 125 includes theexample data translator 140 to translate theaudience measurement data 110 received from the example audience measurement system(s) 105 into a form more meaningfully handled by theexample model builder 150. For example, thedata translator 140 ofFIG. 1 may retrieve and/or query theaudience measurement data 110 recorded in the exampleraw data database 135 and normalize the disparate data to a common scale. As described in detail below, theexample data translator 140 modifies and/or manipulatesaudience measurement data 110 based on the type of data. For example, thedata translator 140 may translate (e.g., map) data that is a string data type (e.g., “Day-of-Week” is “Tuesday”) to a Boolean data type (e.g., “Day Tues” is set to true (e.g., “1”)). - As described above and in connection with the example data table 200 of
FIG. 2 , theaudience measurement data 110 may be in different data formats and/or different units of measure. For example, program characteristic information such as program title, episode and season identifying information, day of week, broadcast time, broadcast network and genre may be stored as string data types. Current and historical ratings information may be represented via television rating scores (e.g., floating data types). Social media indicators (e.g., message identifiers, message timestamps, message content, message author identifiers, message impression information, etc.) may be represented as string data types. In the illustrated example ofFIG. 1 , thedata translator 140 normalizes theaudience measurement data 110 into numerical data types (e.g., Boolean data types, integer data types and/or floating data types). Theexample data translator 140 ofFIG. 1 records translated data in the example translateddata database 145. - In the illustrated example of
FIG. 1 , the examplecentral facility 125 includes the example translateddata database 145 to record translated data provided by theexample data translator 140. Example data tables 500, 600, 700 and 800 of the illustrated examples ofFIGS. 5, 6, 7 and 8 , respectively, illustrate example translated data variables that may be recorded in the example translateddata database 145. The example translateddata database 145 may be implemented by a volatile memory (e.g., an SDRAM, DRAM, RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory). The example translateddata database 145 may additionally or alternatively be implemented by one or more DDR memories, such as DDR, DDR2, DDR3, mDDR, etc. The example translateddata database 145 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the translateddata database 145 is illustrated as a single database, the translateddata database 145 may be implemented by any number and/or type(s) of databases. - In the illustrated example of
FIG. 1 , thecentral facility 125 includes theexample model builder 150 to build one or more prediction model(s) that may be used to estimate ratings lift for media assets of interest over a time-shifted period (e.g., seven days after the initial broadcast of media assets of interest). In the illustrated example, themodel builder 150 determines a relationship between one or more translated data variables retrieved from the example translateddata database 145 and ratings lifts to build one or more prediction model(s).Equation 1 below is an example equation representative of a prediction model that may be built by theexample model builder 150. -
- In
Equation 1 above, the lift (lift) for a media asset of interest is calculated using live ratings information (Live Ratings) associated with the media asset of interest (e.g., current ratings) and values of translated data variables (Xi) that are modified by coefficients (ai). In the illustrated example, themodel builder 150 applies historical values of lift and live ratings data, and historical values of one or more translated data variables from the translateddata database 145 toEquation 1 above to train the model ofEquation 1 to determine the value of the coefficients (ai). Theexample model builder 150 ofFIG. 1 uses logistic regression to determine the value of the coefficients (ai). However, any other technique may additionally or alternatively be used to determine the value of the coefficients (ai). For example, a linear equation (represented byEquation 2 below) may additionally or alternatively be used. -
lift=(100−Live Ratings)*Σ(X i *a i) Equation 2: - In the illustrated example of
FIG. 1 , theexample model builder 150 builds different models to estimate ratings lift for a media asset of interest based on season and episode number attribute of the media asset of interest. For example, themodel builder 150 may apply different sets of the translated data variables toEquation 1 above to determine the coefficient values (ai) of the translated data variables (Xi) based on season-episode groupings. Anexample schema 900 of the illustrated example ofFIG. 9 illustrates example ratings lift models based on season-episode groupings. - In the illustrated example of
FIG. 1 , theexample model builder 150 selects the translated data variables (Xi) to apply toEquation 1 above based on season and episode number attributes of media assets. For example, themodel builder 150 may build a first lift prediction model by applying data related to episodes one through three of the first season of a media asset toEquation 1 above. Theexample model builder 150 may build a second lift prediction model by applying data related to episodes four through six of the first season of a media asset and/or data related to episodes one through six of subsequent seasons of the media asset toEquation 1 above. Theexample model builder 150 may build a third lift prediction model by applying data related to episodes seven and later of any season of a media asset toEquation 1 above. In some such instances, while the general form ofEquation 1 is used to build lift prediction models, the translated data variables included in the corresponding models is different and, as a result, the coefficient values (ai) of the translated data variables (Xi) differ between the three models. While the illustrated example describes three example season-episode groupings, any other number of season-episode groupings may additionally or alternatively be used. Theexample model builder 150 ofFIG. 1 stores the generated lift prediction models in the examplemodels data store 155. - In the illustrated example of
FIG. 1 , the examplecentral facility 125 includes the examplemodels data store 155 to store lift prediction models generated by theexample model builder 150. The examplemodels data store 155 may be implemented by a volatile memory (e.g., SDRAM, DRAM, RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory). The examplemodels data store 155 may additionally or alternatively be implemented by one or more DDR memories, such as DDR, DDR2, DDR3, mDDR, etc. The examplemodels data store 155 may additionally or alternatively be implemented by one or more mass storage devices such as hard disk drive(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example themodels data store 155 is illustrated as a single database, themodels data store 155 may be implemented by any number and/or type(s) of databases. - In the illustrated example of
FIG. 1 , thecentral facility 125 includes the exampleprogram ratings estimator 160 to use the lift prediction models generated by theexample model builder 150 to estimate ratings lift for a media asset of interest. For example, theprogram ratings estimator 160 may apply data related to the media asset of interest to predict a lift in viewership of the media asset of interest over a period (e.g., within seven days of the original broadcast of the media asset of interest). In the illustrated example, theprogram ratings estimator 160 uses program characteristics of the media asset of interest to select a lift prediction model to apply. For example, theprogram ratings estimator 160 may determine a lift prediction model based on the season and episode number associated with the media asset of interest. - In the illustrated example of
FIG. 1 , in response to selecting the lift prediction model to apply, the exampleprogram ratings estimator 160 retrieves data related to the media asset of interest from the translateddata database 145. In some examples, theprogram ratings estimator 160 estimates current ratings information related to the media asset of interest based on real-time ratings information. For example, fast affiliate reports provide first national ratings for a media asset the day after telecast. In some examples, the fast affiliate ratings (sometimes referred to as “overnight ratings”) are time-period information based on the scheduled broadcast time of media assets rather than the actual broadcast time of media assets. For example, fast affiliate ratings for a media asset of interest may include stations that did not air the media asset, that cut away from the media asset for local programming (e.g., local breaking news), etc. - In the illustrated example of
FIG. 1 , the exampleprogram ratings estimator 160 estimates current ratings information based on a fast affiliate reports and actual broadcast information obtained from, for example, the affiliate stations. For example, theprogram ratings estimator 160 may adjust fast affiliate ratings for a media asset of interest based on actual broadcast information.FIG. 3 illustrates anexample calculation 300 of estimated current TV ratings based on fast affiliate reports 305 andactual broadcast information 310. In the illustrated example, theprogram ratings estimator 160 combines the fast affiliate reports 305 with theactual broadcast information 310 to estimatecurrent TV ratings 320. Although the example fast affiliate reports 305 provide “live” ratings and “live+same day” ratings for thirty-minute periods, any other time period may additionally or alternatively be used. For example, the fast affiliate reports 305 may provide ratings on a minute-by-minute basis to increase the granularity of the ratings information. - The example
program ratings estimator 160 of the illustrated example ofFIG. 1 applies the estimated current ratings and data related to a media asset of interest to the generated lift prediction models stored in the examplemodels data store 155 to generatereports 165 estimating the ratings lift for the media asset of interest. For example, theprogram ratings estimator 160 may estimate the ratings lift for a media asset of interest by applying program attributes information, social media indicators information and/or media performance information to a lift prediction model. As used herein, program attributes information includes genre information of the media asset of interest, day-of-week information related to the media asset of interest, broadcast time related to the media asset of interest, originator (e.g., network or channel) information related to the media asset of interest, etc. As used herein, social media indicators information includes a social media messages count related to the number of media-exposure social media messages of interest, a social media unique authors count related to the number of unique authors who posted media-exposure social media messages of interest, a social media impressions count related to the number of users who were exposed to the media-exposure social media messages of interest, etc. As used herein, media performance information includes current ratings associated with the media asset of interest (e.g., “live” ratings and “live+same day” ratings), historical ratings associated with the media asset of interest (e.g., historical “live” ratings and historical “live+same day” ratings), program lead-in ratings associated with the media asset of interest (e.g., “live” ratings and “live+same day” ratings of the program that was broadcast prior to the media asset of interest), a program loyalty score associated with the media asset of interest (e.g., average number of episodes of the media asset watched by viewers during a time period (e.g., five weeks)), etc. -
FIG. 2 is an example data table 200 that lists raw audience measurement data variables that theexample data interface 130 ofFIG. 1 may store in the exampleraw data database 135 ofFIG. 1 . In the illustrated example ofFIG. 2 , the raw audience measurement data variables represent the data collected and/or provided by the audience measurement system(s) 105 ofFIG. 1 . For example, the raw audience measurement data variables may include the panelistmedia measurement data 110A collected via, for example, people meters operating in statistically-selected households, set-top boxes and/or other media devices (e.g., such as digital video recorders, personal computers, tablet computers, smartphones, etc.) capable of monitoring and returning monitored data for media presentations, etc. The example raw audience measurement data variables included in the data table 200 may also include the socialmedia activity data 110B associated with media of interest referenced by social media messages collected via, for example, social media servers that provide social media services to users of the social media server. - The example data table 200 of the illustrated example of
FIG. 2 includes a variablename identifier column 205, a variable datatype identifier column 210 and a variablemeaning identifier column 215. The example variablename identifier column 205 indicates example variables that may be associated with a telecast and/or useful for predicting time-shifted exposure to media. The example variable datatype identifier column 210 indicates a data type of the corresponding variable. The example variablemeaning identifier column 215 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 200 ofFIG. 2 , more or fewer variable identifier columns may be represented in the example data table 200. For example, the example data table 200 may additionally or alternatively include a variable identifier column indicative of the source of the corresponding data (e.g., the example panelistmedia measurement data 110A, the example socialmedia activity data 110B, etc.). - The example data table 200 of the illustrated example of
FIG. 2 includes eighteen example rows corresponding to example raw audience measurement data variables. The first example block ofrows 250 identifies attributes and/or characteristics of a media asset and is stored as strings. For example, the “Title” variable identifies the name of the media asset (e.g., “Sports Stuff”), the “Episode Identifier” variable identifies the season and episode number associated with the media asset (e.g.,Season 2, Episode 4), the “Day of Week” variable identifies the day of the week that the media asset was broadcast (e.g., “Tuesday”), the “Broadcast Time” variable identifies the time during which the media asset was broadcast (e.g., “20:00-20:30”), the “Network” variable identifies on which network the media asset was broadcast (e.g., Channel “ABC”), and the “Genre” variable identifies the genre that the media asset is classified (e.g., a “comedy”). - In the example data table 200 of
FIG. 2 , the second example block ofrows 255 identifies ratings information associated with a media asset and the corresponding information is stored as floating type data. For example, the “Ratings Live” variable identifies the program ratings during the original broadcast of the program (e.g., “1.01”). The example “Ratings LiveSameDay” variable and example “Ratings LivePlus7” variable identify the program ratings during the original broadcast of the program and also include time-shifted incremental viewing that takes place via, for example, a DVR or video-on-demand (VOD) service. For example, the “Ratings LiveSameDay” variable represents the number of people who viewed the media asset during its original broadcast time and/or during the same day as the original broadcast (e.g., “Live+Same Day” ratings). The example “Ratings LivePlus7” variable represents the number of people who viewed the media asset during its original broadcast time and/or within seven days following the original telecast (e.g., “Live+7” or “L7” ratings). Although the example data table 200 includes three example ratings (e.g., “Live” ratings, “Live+Same Day” ratings and “Live+7” ratings), in other examples, the ratings information may be associated with more or fewer time-shifted periods. - In the illustrated example of
FIG. 2 , theexample row 260 indicates the “Lead-In Ratings” variable is stored as a floating data type and corresponds to the program ratings for a media asset preceding the media asset of interest. For example, when processing the “Sports Stuff” program, the “lead-in ratings” information corresponds to the media asset that is broadcast on “Tuesday” at “19:30-20:00” on Channel “ABC.” - In the illustrated example of
FIG. 2 , theexample row 265 indicates the “Panelist ID” variable is stored as a string and uniquely identifies the panelist who provided the viewership information. For example, panelists who are provided people meters may be assigned a panelist identifier to monitor the media exposure of the panelist. In the illustrated example, the panelist identifier is an obfuscated alphanumeric string to protect the identity of the panelist. In some examples, the panelist identifier is obfuscated in a manner so that the same obfuscated panelist identifier information corresponds to the same panelist. In this manner, user activities may be monitored for particular users without exposing sensitive information regarding the panelist. However, any other approach to protecting the privacy of a panelist may additionally or alternatively be used. In some examples, the panelist identifier is used to identify demographic information associated with the panelist. For example, the panelist identifier “0123” may link to demographic information indicating the panelist is a male, age 18-49. - In the example data table 200 of
FIG. 2 , the third example block ofrows 270 identifies information regarding social media messages. For example, the “Message ID” variable is stored as a string and is a unique identifier of a social media message. In the illustrated example, the example “Message Timestamp” variable is stored as a string data type and identifies the date and/or time when the corresponding social media message was posted. In the illustrated example, the example “Message Content” variable is stored as a string data type and identifies the content of corresponding social media message. In the illustrated example, the example “Message Author” variable is stored as a string data type and identifies the author of the corresponding social media message. - In the example data table 200 of
FIG. 2 , the fourth example block ofrows 275 represents overnight time-period ratings that may be used to estimate current ratings for a media asset. In the illustrated example, the example “Overnight Live” variable and the example “Overnight LiveSameDay” variable are stored as floating data types and represent “Live” ratings and “Live+Same Day” ratings based on time-periods. For example, the “overnight live” ratings for the media asset “Sports Stuff” may represent the number of viewers who were tuned to Channel “ABC” between “20:00-20:30” on “Tuesday” (e.g., the broadcast time and network when “Sports Stuff” is scheduled to air). However, in certain markets, the media asset may not air at the scheduled time. For example, due to a football game that went into overtime, the media asset “Sports Stuff” may have actually aired between “20:08-20:35.” The example “Actual Broadcast” variable 280 is stored as a string and identifies the actual broadcast time of the media asset (e.g., “20:08-20:35”). - While eighteen example raw data variables are represented in the example data table 200 of
FIG. 2 , more or fewer raw data variables may be represented in the example data table 200 corresponding to the many raw audience measurement data variables that may be collected and/or provided by the audience measurement system(s) 105 ofFIG. 1 . -
FIG. 4 is a block diagram of an example implementation of thedata translator 140 ofFIG. 1 that may facilitate manipulating and/or modifying rawaudience measurement data 110 retrieved from the exampleraw data database 135. As described above, theexample data translator 140 translates the rawaudience measurement data 110 to a form that may be meaningfully handled by theexample model builder 150 to generate one or more lift prediction models. Theexample data translator 140 ofFIG. 4 includes anexample ratings handler 405, an example attributeshandler 410 and an examplesocial media handler 415. In the illustrated example, theratings handler 405, theattributes handler 410 and thesocial media handler 415 record the translated information in the example translateddata database 145 ofFIG. 1 . - In the illustrated example of
FIG. 4 , theexample data translator 140 includes theexample ratings handler 405 to process ratings-related information representative of media assets. For example, theratings handler 405 may query and/or retrieve ratings-related information from the raw data database 135 (e.g., current ratings information, historical ratings information, etc.) to translate into a form meaningfully handled by theexample model builder 150. - An example data table 500 of the illustrated example of
FIG. 5 illustrates example translated ratings data variables that may be recorded by theratings handler 405 in the example translateddata database 145. The example data table 500 of the illustrated example ofFIG. 5 includes a variablename identifier column 505, a variable datatype identifier column 510 and a variablemeaning identifier column 515. The example variablename identifier column 505 indicates example variables that may be associated with a media asset broadcast and/or useful for predicting time-shifted exposure to the media asset. The example variable datatype identifier column 510 indicates a data type of the corresponding variable. The example variablemeaning identifier column 515 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 500 ofFIG. 5 , more or fewer variable identifier columns may be represented in the example data table 500. - The example data table 500 of the illustrated example of
FIG. 5 includes five example rows corresponding to example translated ratings data variables. Thefirst example row 550 indicates theratings handler 405 ofFIG. 4 stores the “Same Day Lift” variable as a floating data type. In the illustrated example, theratings handler 405 determines a “Same Day Lift” value associated with a media asset of interest based on the “Ratings LiveSameDay” variable and the “Ratings Live” variable retrieved from the exampleraw data database 135. For example, theratings handler 405 may query theraw data database 135 for the “Ratings LiveSameDay” rating and the “Ratings Live” rating related to a media asset of interest (e.g.,season 2,episode 4 of “Sports Stuff”). In the illustrated example, theratings handler 405 calculates the difference between the “Ratings LiveSameDay” rating and the “Ratings Live” rating and records the logarithm transformation of the calculated difference as the “Same Day Lift” of the media asset of interest in the example translateddata database 145. - In the illustrated example, the
second example row 555 indicates theratings handler 405 determines a “Program Lead-In” value associated with a media asset of interest based on the “Lead-In Ratings” variable retrieved from the exampleraw data database 135. For example, theratings handler 405 may query theraw data database 135 for the “Lead-In Ratings” rating related to a media asset of interest (e.g.,season 2,episode 4 of “Sports Stuff”). In the illustrated example, theratings handler 405 records the logarithm transformation of the returned rating as the “Program Lead-In” of the media asset of interest in the example translateddata database 145. - In the illustrated example, the
third example row 560 indicates theratings handler 405 determines an “L7 Lift” value based on the “Ratings LivePlus7” variable and the “Ratings Live” variable retrieved from the exampleraw data database 135. For example, theratings handler 405 may query theraw data database 135 for the “Ratings LivePlus7” rating and the “Ratings Live” rating related to a media asset of interest (e.g.,season 2,episode 4 of “Sports Stuff”). In the illustrated example, theratings handler 405 calculates the difference between the “Ratings LivePlus7” rating and the “Ratings Live” rating and records the logarithm transformation of the calculated difference as the “L7 Lift” of the media asset of interest in the example translateddata database 145. - In the illustrated example, the
fourth example row 565 indicates theratings handler 405 determines a “Historical Ratings Lift” value based on the “Ratings LivePlus7” variable and the “Ratings Live” variable retrieved from the exampleraw data database 135. For example, theratings handler 405 may query theraw data database 135 for the “Ratings LivePlus7” rating and the “Ratings Live” rating related to a media asset of interest. In the illustrated example, theratings handler 405 calculates the “historical ratings lift” based on an average of “L7 Lift” values over, for example, two previous weeks (or episodes). For example, to determine the “historical ratings lift” for a media asset of interest (e.g.,season 2,episode 4 of “Sports Stuff”), theexample ratings handler 405 retrieves the “Ratings LivePlus7” rating and the “Ratings Live” rating forseason 2,episodes ratings handler 405 calculates an average of the “L7 Lift” value forepisode 2 ofseason 2 and the “L7 Lift” value forepisode 3 ofseason 2. Theexample ratings handler 405 records the logarithm transformation of the average of the “L7 Lift” values as the “Historical Ratings Lift” of the media asset of interest in the example translateddata database 145. - In the illustrated example, the
fifth example row 570 indicates theratings handler 405 determines a “Program Loyalty” score for a media asset based on an average number of episodes of the media viewed per user over a period (e.g., five weeks). In the illustrated example, theratings handler 405 queries theraw data database 135 for panelist identifiers associated with panelists who viewed previously aired episodes of the media asset. For example, theratings handler 405 may determine the “program loyalty” score forepisode 7 ofseason 1 of “Sports Stuff” by (1) identifying panelists who viewed at least one of episodes 2-6 ofseason 1 of “Sports Stuff,” (2) determining the total number of episodes 2-6 ofseason 1 that were viewed by each of the panelists and (3) calculating a ratio of the total number of episodes 2-6 ofseason 1 that were watched by each of the panelists and the total number of identified panelists. In the illustrated example, theratings handler 405 records the calculated ratio as the “program loyalty” score of the media asset of interest (e.g.,episode 7 ofseason 1 of “Sports Stuff”) in the example translateddata database 145. - In the illustrated example of
FIG. 5 , theexample ratings handler 405 applies a logarithm transformation to the “Same Day Lift” variable (row 550), the “Program Lead-In” variable (row 555), the “L7 Lift” variable (row 560) and the example “Historical Ratings Lift” variable (row 565). However, theratings handler 405 may additionally or alternatively apply different transformations, including no transformations, to the variables. -
FIG. 6 illustrates an example program loyalty score calculation. In the illustrated example ofFIG. 6 , a “program loyalty”score 600 for a media asset is calculated based on the number of weeks a panelist viewed media over a five week period. In the illustrated example, threeexample panelists first example panelist 605 viewed four total episodes (e.g., watched during weeks 1-3 and week 5), thesecond example panelist 610 viewed three total episodes (e.g., watched duringweeks third example panelist 615 viewed one total episode (e.g., watched during week 1). In the illustrated example, the program loyalty score 600 (e.g., 2.67) is calculated as a ratio of the total number of episodes 1-5 that were viewed by each of panelists (e.g., 4+3+1=8) and the total number of panelists (e.g., 3). - In the illustrated example, a five-week period is used to determine a program loyalty score. However, any other period over which program loyalty is assessed may additionally or alternatively be used. Furthermore, any other technique for calculating program loyalty scores may additionally or alternatively be used. In some examples, raw data related to a media asset may not be immediately available. For example, panelist identifiers associated with panelists who viewed an episode may not be available, for example, for two weeks after the media asset is broadcast. In some such examples, the
example ratings handler 405 may not determine a program loyalty score for a media asset that is earlier than, for example, episode seven of a season. - In the illustrated example of
FIG. 4 , theexample data translator 140 includes the example attributeshandler 410 to process attributes and/or characteristics representative of media assets. For example, theattributes handler 410 may query and/or retrieve program attributes information from the raw data database 135 (e.g., genre-identifying information, day-of-week information, broadcast time-identifying information, etc.) to translate into a form meaningfully handled by theexample model builder 150. - An example data table 700 of the illustrated example of
FIG. 7 illustrates example translated program attributes data variables that may be recorded by theattributes handler 410 in the example translateddata database 145. The example data table 700 of the illustrated example ofFIG. 7 includes a variablename identifier column 705, a variable datatype identifier column 710 and a variablemeaning identifier column 715. The example variablename identifier column 705 indicates example variables that may be associated with a media asset and/or useful for predicting time-shifted exposure to the media asset. The example variable datatype identifier column 710 indicates a data type of the corresponding variable. The example variablemeaning identifier column 715 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 700 ofFIG. 7 , more or fewer variable identifier columns may be represented in the example data table 700. - The example data table 700 of the illustrated example of
FIG. 7 includes thirteen example rows corresponding to example translated program attributes data variables. In the illustrated example, the example translated program attributes data variables of the data table 700 represent four example characteristics of a media asset. The first example block ofrows 750 indicates that the example attributeshandler 410 stores day-of-week information as Boolean variables. In the illustrated example, theattributes handler 410 translates day-of-week information that is stored as a string data type at theraw data database 135 to one or more day-of-week Boolean variables. For example, theattributes handler 410 may retrieve day-of-week information related to a media asset indicating the date of the week that the media asset is broadcast (e.g., “Tuesday”) and set the corresponding day-of-week Boolean variable to true (e.g., “1”) and set (or reset) other day-of-week Boolean variables to false (e.g., “0”). In the illustrated example, in response to determining that the raw day-of-week information indicates the media asset is broadcast on a “Tuesday,” the example attributeshandler 410 sets the value of the corresponding “Day Tues” variable to true (e.g., “1”) and sets (or resets) the values of the other day-of-week Boolean variables (e.g., “Day Mon,” “Day Wed,” “Day Thurs,” “Day Fri” and “Day SatSun”) to false (e.g., “0”). Although the example day-of-week information is represented as six example Boolean variables in the example data table 700 ofFIG. 7 , any other number of Boolean variables may additionally or alternatively be used. For example, theattributes handler 410 may group the days-of-week information into weekday or weekend Boolean variables. - The second example block of
rows 755 of the data table 700 ofFIG. 7 indicates that the example attributeshandler 410 stores genre-identifying information as Boolean variables. In the illustrated example, theattributes handler 410 translates genre-identifying information that is stored as a string data type at theraw data database 135 to one or more genre-related Boolean variables. For example, theattributes handler 410 may retrieve genre-identifying information indicative of the genre classification of a media asset (e.g., a documentary, drama, variety, comedy, etc.) and set the corresponding genre-related Boolean variable to true (e.g., “1”) and set (or reset) other genre-related Boolean variables to false (e.g., “0”). In the illustrated example, in response to determining that retrieved raw genre-identifying information indicates the corresponding media asset is a “comedy,” the example attributeshandler 410 sets the value of the corresponding “Genre Comedy” variable to true (e.g., “1”) and sets (or resets) the values of the other genre-related Boolean variables (e.g., “Genre Documentary,” “Genre Drama” and “Genre Variety”) to false (e.g., “0”). Although the example genre-identifying information is represented as four example genre-related Boolean variables in the example data table 700 ofFIG. 7 , any other number of Boolean variables representative of the genre of a media asset may additionally or alternatively be used. - The third example block of
rows 760 of the data table 700 ofFIG. 7 indicates that the example attributeshandler 410 stores originator-identifying information as Boolean variables. In the illustrated example, theattributes handler 410 translates originator-identifying information that is stored as a string data type at theraw data database 135 to one or more originator-related Boolean variables. For example, theattributes handler 410 may retrieve originator-identifying information indicative of the network (or channel) that broadcasts a media asset (e.g., channel “ABC,” channel “XYZ,” etc.) and set the corresponding originator-related Boolean variable to true (e.g., “1”) and set (or reset) other originator-related Boolean variables to false (e.g., “0”). In the illustrated example, in response to determining that retrieved raw originator-identifying information indicates the corresponding media asset is broadcast on channel “ABC,” the example attributeshandler 410 sets the value of the corresponding “Originator ABC” variable to true (e.g., “1”) and sets (or resets) the values of the other originator-related Boolean variables (e.g., “Originator XYZ”) to false (e.g., “0”). While two example originators are represented in the example data table 700 ofFIG. 7 , more or fewer originators may be represented in the example data table 700 corresponding to the many broadcast networks and cable networks that broadcast media assets. - The
example row 765 of the data table 700 ofFIG. 7 indicates that the example attributeshandler 410 stores broadcast time-identifying information as an integer data type. In the illustrated example, theattributes handler 410 maps broadcast time-identifying information that is stored as a string data type at theraw data database 135 to an integer. For example, theattributes handler 410 may retrieve broadcast time-identifying information indicative of when a media asset is broadcast (e.g., “00:00-00:30,” “00:30-01:00,” . . . “23:30-00:00”) and set the “HH Block” variable value based on a corresponding half-hour block. For example, theattributes handler 410 may map the broadcast time “00:00-00:00” to half-hour block “0,” may map the broadcast time “00:30-01:00” to half-hour block “1,” etc. Although the example broadcast time-identifying information is represented as half-hour blocks, any other granularity may additionally or alternatively be used. For example, the broadcast times may be based on quarter-hours, full hours, etc. - While the example data table 700 of
FIG. 7 includes four example program attributes related to a media asset (e.g., day-of-week, genre, originator and broadcast time), any other number of program attributes may additionally or alternatively be used. - In the illustrated example of
FIG. 4 , theexample data translator 140 includes the examplesocial media handler 415 to process social media messages representative of media assets. For example, thesocial media handler 415 may query and/or retrieve social media messages and/or social media messages-related information from the raw data database 135 (e.g., message identifiers, message timestamps, message content, message authors, etc.) to translate into a form meaningfully handled by theexample model builder 150. - An example data table 800 of the illustrated example of
FIG. 8 illustrates example translated social media data variables that may be recorded by thesocial media handler 415 in the example translateddata database 145. The example data table 800 of the illustrated example ofFIG. 8 includes a variablename identifier column 805, a variable datatype identifier column 810 and a variablemeaning identifier column 815. The example variablename identifier column 805 indicates example variables that may be associated with a media asset broadcast and/or information useful for predicting time-shifted exposure to the media asset. The example variable datatype identifier column 810 indicates a data type of the corresponding variable. The example variablemeaning identifier column 815 provides a brief description of the value associated with the corresponding variable. While three example variable identifier columns are represented in the example data table 800 ofFIG. 8 , more or fewer variable identifier columns may be represented in the example data table 800. - The example data table 800 of the illustrated example of
FIG. 8 includes three example rows corresponding to example translated social media data variables. Thefirst example row 850 indicates thesocial media handler 415 ofFIG. 4 stores a “SM Count” variable as a floating data type in the example translateddata database 145. In the illustrated example, thesocial media handler 415 determines a “SM Count” value associated with a media asset of interest based on a number of posted social media messages of interest. For example, thesocial media handler 415 may inspect the social media messages returned by theraw data database 135 for social media messages that indicate exposure to a media asset. For example, a media asset may be “Sports Stuff.” In such instances, a social media message of interest may include the text “Jon is my favorite character on Sports Stuff!” and may include a message timestamp indicating that the social media message was posted by the message author during broadcast of the media asset. In the illustrated example, thesocial media handler 415 may count the number of social media messages identified as of interest and record a logarithm transformation of the number of social media messages of interest (e.g., the social media messages that indicate exposure to a media asset) as the “SM Count” corresponding to the media asset of interest in the example translateddata database 145. - The
second example row 855 of the data table 800 ofFIG. 8 indicates that the examplesocial media handler 415 stores a value related to the number of unique authors who posted social media messages of interest as a floating data type in the example translateddata database 145. Thesecond example row 855 of the data table 800 ofFIG. 8 indicates thesocial media handler 415 ofFIG. 4 stores a “SM UAuthors” variable as a floating data type in the example translateddata database 145. In the illustrated example, thesocial media handler 415 determines a “SM UAuthors” value associated with a media asset of interest based on a number of unique authors who posted social media messages of interest. For example, thesocial media handler 415 may inspect the social media messages returned by theraw data database 135 for social media messages that indicate exposure to a media asset. In the illustrated example, thesocial media handler 415 may count the number of unique authors who posted the social media messages identified as of interest and record a logarithm transformation of the number of unique authors as the “SM UAuthors” corresponding to the media asset of interest in the example translateddata database 145. - The
third example row 860 of the data table 800 ofFIG. 8 indicates thesocial media handler 415 ofFIG. 4 stores a “SM Impressions” variable as a floating data type in the example translateddata database 145. In the illustrated example, thesocial media handler 415 determines a “SM Impressions” value associated with a media asset of interest based on impression information associated with social media messages of interest. For example, thesocial media handler 415 may count the number of times social media messages identified as of interest were viewed by users of the social media service and record a logarithm transformation of the number of impressions of social media messages of interest as the “SM Impressions” corresponding to the media asset of interest in the example translateddata database 145. - In the illustrated example of
FIG. 8 , the examplesocial media handler 415 applies a logarithm transformation to the “SM Count” variable (row 850), the “SM UAuthors” variable (row 855) and the example “SM Impressions” variable (row 860). However, thesocial media handler 415 may additionally or alternatively apply different transformations, including no transformations, to the variables. - In the illustrated example, the example
social media handler 415 inspects social media messages and/or social media messages-related information retrieved from theraw data database 135 to translate into a form meaningfully handled by theexample model builder 150. In some examples, the rawaudience measurement data 110 may be provided as aggregated data. For example, rather than providing social media messages and/or social media messages-related information, the example audience measurement system(s) 105 ofFIG. 1 may count the number of posted social media messages related to media assets of interest, may count the number of unique authors who posted social media messages related to media assets of interest and may count the number of impressions associated with posted social media messages related to media assets of interest, and provide the respective counts to the examplecentral facility 125. In some such instances, the examplesocial media handler 415 may retrieve the respective counts and store the logarithm transformation of the corresponding numbers as the respective social media-related variables. However, any other technique may be used to determine the number of posted social media messages related to media assets of interest, the number of unique authors who posted social media messages related to media assets of interest and the number of impressions associated with posted social media messages related to media assets of interest. - An
example schema 900 of the illustrated example ofFIG. 9 illustrates example ratings lift models based on season-episode groupings that may be used by theexample model builder 150 when building lift prediction models and/or used by the exampleprogram ratings estimator 160 when applying data to a lift prediction model to predict a ratings list for a media asset of interest. Theexample schema 900 of the illustrated example ofFIG. 9 includes aseason identifier column 905 to identify a season number of a media asset, an episodenumber identifier column 910 to identify an episode number of a media asset and a lift predictionmodel identifier column 915 to identify a lift prediction model applicable to the corresponding season-episode grouping. - The
example schema 900 ofFIG. 9 indicates that, in the illustrated example, during the first season of a media asset (correspondingsection 930 of the schema 900), three different lift prediction models may be used. For example, the first three episodes are associated with a first lift prediction model (Model 1). Theexample schema 900 also indicates that the next three episodes (e.g., episodes four through six of season one) are associated with a second lift prediction model (Model 2). Theexample schema 900 also indicates that episode seven and subsequent episodes of season one are associated with a third lift prediction model (Model 3). - In the illustrated example of
FIG. 9 , theexample schema 900 indicates that during the second and subsequent seasons (corresponding tosection 935 of schema 900), two different lift prediction models may be used. For example, the first six episodes of the second season are associated with the second lift prediction model (Model 2) while episodes seven and later are associated with the third lift prediction model (Model 3). While three example lift prediction models are represented in theexample schema 900 ofFIG. 9 , more or fewer lift prediction models may be represented in theexample schema 900 based on different season-episode groupings. - An example data table 1000 of the illustrated example of
FIG. 10 illustrates example sets of translated data variables that are used when generating (e.g., training) lift prediction models and/or that are applied to a lift prediction model when estimating ratings lift for media assets of interest. The example data table 1000 of the illustrated example ofFIG. 10 includes avariable identifier column 1005, a first lift predictionmodel identifier column 1010, a second lift predictionmodel identifier column 1015 and a third lift predictionmodel identifier column 1020. In the illustrated example, the three example lift prediction models ofFIG. 10 correspond to the three example lift prediction models ofFIG. 9 . - The example data table 1000 of the illustrated example of
FIG. 10 includes example rows corresponding to example translated ratings data variables (e.g., features) that are applied to the respective lift prediction models. In the illustrated example, thefirst example row 1050 corresponds to different demographic groupings (e.g., households, persons age two and up, persons between the ages of 25 and 54 and persons between the ages of 19 and 49). In some instances, it may be beneficial to develop lift prediction models for different demographic groupings since members of the respective groupings may influence ratings lift predictions differently. For example, social media indicators may not be a predictive variable for media assets whose audience(s) tends to not use social media services. Although the example data table 1000 indicates that twelve lift prediction models are generated and/or applied (e.g., four demographic groupings for each of the three lift prediction models), any other number of lift prediction models may additionally or alternatively be used. For example, the number of demographic groupings for one or more of the example lift prediction models vary based on, for example, client preference. - The example data table 1000 of the illustrated example of
FIG. 10 indicates that current TV ratings 1055 (e.g., “live+same day” ratings and “live” ratings), program lead-in 1060 (e.g., program lead-in ratings), program characteristics 1065 (e.g., day-of-week, genre, originator and half-hour block broadcast time) andsocial media indicators 1070 are used when training each of the lift prediction models and/or when applying each of lift prediction models. As described above, thecurrent TV ratings 1055 correspond to the exampleaudience measurement data 110 provided from the audience measurement system(s) 105 and used when building and/or training the lift prediction models. When applying the lift prediction models to estimate ratings lift for a media asset of interest, thecurrent TV ratings 1055 correspond to the estimated current TV ratings determined by the exampleprogram ratings estimator 160 ofFIG. 1 . - In the illustrated example, historical
TV ratings data 1075 is not used when generating and/or applying the first example lift predictor model, but is used with respect to the second and third example lift predictor models. Excluding the historical TV ratings data may be beneficial in connection with the first example lift predictor model because, as described above, the historical TV ratings data includes determining an average of previous TV ratings of the media asset. In some such instances, because the media asset is a new program (e.g., one of the first three episodes of the program), previous TV ratings may not be available (e.g., when the media asset of interest is the pilot) and/or may not be a reliable predictor of ratings lift. For example, consumers may switch between different pilots and/or episodes as they evaluate whether the program is worth their time, resulting in skewed TV ratings for the first and/or second episodes. - In the illustrated example, program loyalty scores 1080 are excluded from the first and second example lift prediction models, but are included with respect to the third example lift prediction model. In the illustrated example, excluding program loyalty scores may be beneficial in connection with the first and second example lift prediction models because, as described above, the program loyalty scores are determined based on five previous episodes and, in some examples, may also include a two-week lag. In some such instances, because seven episodes-worth of audience measurement data is needed to develop the program loyalty scores, including such scores in the first and/or second example lift prediction models would not be useful in estimating ratings lift for the media asset.
- While an example manner of implementing the
central facility 125 ofFIG. 1 is illustrated inFIG. 1 , one or more of the elements, processes and/or devices illustrated inFIG. 1 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, theexample data interface 130, the exampleraw data database 135, theexample data translator 140, the example translateddata database 145, theexample model builder 150, theexample models database 155, the exampleprogram ratings estimator 160 and/or, more generally, the examplecentral facility 125 ofFIG. 1 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of theexample data interface 130, the exampleraw data database 135, theexample data translator 140, the example translateddata database 145, theexample model builder 150, theexample models database 155, the exampleprogram ratings estimator 160 and/or, more generally, the examplecentral facility 125 ofFIG. 1 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of theexample data interface 130, the exampleraw data database 135, theexample data translator 140, the example translateddata database 145, theexample model builder 150, theexample models database 155, the exampleprogram ratings estimator 160 and/or, more generally, the examplecentral facility 125 ofFIG. 1 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware. Further still, the examplecentral facility 125 ofFIG. 1 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated inFIG. 1 , and/or may include more than one of any or all of the illustrated elements, processes and devices. - While an example manner of implementing the
data translator 140 ofFIG. 1 is illustrated inFIG. 4 , one or more of the elements, processes and/or devices illustrated inFIG. 4 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, theexample ratings handler 405, the example attributeshandler 410, the examplesocial media handler 415 and/or, more generally, theexample data translator 140 ofFIG. 4 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of theexample ratings handler 405, the example attributeshandler 410, the examplesocial media handler 415 and/or, more generally, theexample data translator 140 ofFIG. 4 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of theexample ratings handler 405, the example attributeshandler 410, the examplesocial media handler 415 and/or, more generally, theexample data translator 140 ofFIG. 4 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware. Further still, theexample data translator 140 ofFIG. 1 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated inFIG. 4 , and/or may include more than one of any or all of the illustrated elements, processes and devices. - Flowcharts representative of example machine readable instructions for implementing the example central facility of
FIG. 1 are shown inFIGS. 11-13 and/or 14 . In this example, the machine readable instructions comprise a program for execution by a processor such as theprocessor 1512 shown in theexample processor platform 1500 discussed below in connection withFIG. 15 . The program may be embodied in software stored on a tangible computer readable storage medium such as a CD-ROM, a floppy disk, a hard drive, a digital versatile disk (DVD), a Blu-ray disk, or a memory associated with theprocessor 1512, but the entire program and/or parts thereof could alternatively be executed by a device other than theprocessor 1512 and/or embodied in firmware or dedicated hardware. Further, although the example program is described with reference to the flowcharts illustrated inFIGS. 11-13 and/or 14 , many other methods of implementing the examplecentral facility 125 may alternatively be used. For example, the order of execution of the blocks may be changed, and/or some of the blocks described may be changed, eliminated, or combined. - As mentioned above, the example processes of
FIGS. 11-13 and/or 14 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a tangible computer readable storage medium such as a hard disk drive, a flash memory, a read-only memory (ROM), a compact disk (CD), a digital versatile disk (DVD), a cache, a random-access memory (RAM) and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term tangible computer readable storage medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media. As used herein, “tangible computer readable storage medium” and “tangible machine readable storage medium” are used interchangeably. Additionally or alternatively, the example processes ofFIGS. 11-13 and/or 14 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a non-transitory computer and/or machine readable medium such as a hard disk drive, a flash memory, a read-only memory, a compact disk, a digital versatile disk, a cache, a random-access memory and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term non-transitory computer readable medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media. As used herein, when the phrase “at least” is used as the transition term in a preamble of a claim, it is open-ended in the same manner as the term “comprising” is open ended. “Comprising” and all other variants of “comprise” are expressly defined to be open-ended terms. “Including” and all other variants of “include” are also defined to be open-ended terms. In contrast, the term “consisting” and/or other forms of “consist” are defined to be close-ended terms. -
FIG. 11 is a flowchart representative of example machine-readable instructions 1100 that may be executed by the examplecentral facility 125 ofFIG. 1 to predict time-shifted exposure to media. Theexample instructions 1100 ofFIG. 11 begin atblock 1102 when the examplecentral facility 125 receivesaudience measurement data 110 from the example audience measurement system(s) ofFIG. 1 . For example, the example data interface 130 (FIG. 1 ) may periodically obtain and/or retrieve example panelistmedia measurement data 110A and/or example socialmedia activity data 110B. In some examples, thedata interface 130 may obtain and/or retrieve the exampleaudience measurement data 110 aperiodically and/or as a one-time event. Theexample data interface 130 stores theaudience measurement data 110 in the example raw data database 135 (FIG. 1 ). - At
block 1104, the examplecentral facility 125 normalizes theaudience measurement data 110. For example, the example data translator 140 (FIG. 1 ) may manipulate and/or modify features of theaudience measurement data 110 from their raw form to be more meaningfully handled when building the prediction models and estimating the ratings lift. Theexample data translator 140 stores the translated data variables in the example translated data database 145 (FIG. 1 ). An example approach to normalizeaudience measurement data 110 is described below in connection withFIG. 12 . - At
block 1106, the examplecentral facility 125 builds a lift prediction model. For example, the example model builder 150 (FIG. 1 ) determines a relationship between translated data variables stored in the example translateddata database 145 and ratings lifts. Theexample model builder 150 stores the generated model(s) in the example models data store 155 (FIG. 1 ). An example approach to build a lift prediction model is described below in connection withFIG. 13 . - At
block 1108, the examplecentral facility 125 determines an estimated ratings lift for a media asset of interest. For example, the example program ratings estimator 160 (FIG. 1 ) may apply data related to the media asset of interest to a lift prediction model to estimate a ratings lift for the media asset. An example approach to determine an estimated ratings lift is described below in connection withFIG. 14 . Theexample process 1100 ofFIG. 11 ends. - While in the illustrated example, the
example instructions 1100 ofFIG. 11 represent a single iteration of predicting time-shifted exposure to media, in practice, theexample instructions 1100 of the illustrated example ofFIG. 11 may be executed in parallel (e.g., in separate threads) to allow thecentral facility 125 to handle multiple requests for ratings lift estimations at a time. -
FIG. 12 is a flowchart representative of example machine-readable instructions 1200 that may be executed by theexample data translator 140 ofFIGS. 1 and/or 4 to normalize raw audience measurement data. Theexample process 1200 of the illustrated example ofFIG. 12 begins atblock 1202 when theexample data translator 140 obtains ratings-related information associated with media assets. For example, thedata translator 140 may retrieve and/or query “live+same day” ratings, “live” ratings, “live+7” ratings and/or information representative of whether a panelist viewed a particular episode of a media asset from the exampleraw data database 135. Atblock 1204, theexample data translator 140 translates the ratings-related information to ratings data variables for use by theexample model builder 150 and/or the exampleprogram ratings estimator 160. In the illustrated example, the data translator translates the ratings-related information in accordance with the example translated ratings data variables table 500 ofFIG. 5 . Atblock 1206, theexample data translator 140 determines whether there is additional ratings-related information to translate. If, atblock 1206, thedata translator 140 determined that there is additional ratings-related information to translate, control returns to block 1202. - If, at
block 1206, thedata translator 140 determined that there is not additional ratings-related information to translate, then, atblock 1208, theexample data translator 140 obtains program attributes information associated with media assets. For example, thedata translator 140 may retrieve and/or query the exampleraw data database 135 for day-of-week information, genre information, originator information and/or broadcast time information. Atblock 1210, theexample data translator 140 translates the program attributes information to program attributes data variables for use by theexample model builder 150 and/or the exampleprogram ratings estimator 160. In the illustrated example, the data translator translates the program attributes information in accordance with the example translated program attributes data variables table 700 ofFIG. 7 . Atblock 1212, theexample data translator 140 determines whether there is additional program attributes information to translate. If, atblock 1212, thedata translator 140 determined that there is additional program attributes information to translate, control returns to block 1208. - If, at
block 1212, thedata translator 140 determined that there is not additional program attributes information to translate, then, atblock 1214, theexample data translator 140 obtains social media messages-related information associated with media assets. For example, thedata translator 140 may retrieve and/or query the exampleraw data database 135 for a number of posted social media messages of interest, a number of unique authors who posted social media messages of interest and/or a number of impressions of social media messages of interest. Atblock 1216, theexample data translator 140 translates the social media messages-related information to social media data variables for use by theexample model builder 150 and/or the exampleprogram ratings estimator 160. In the illustrated example, the data translator translates the social media messages-related information in accordance with the example translated social media data variables table 800 ofFIG. 8 . Atblock 1218, theexample data translator 140 determines whether there is additional social media messages-related information to translate. If, atblock 1218, thedata translator 140 determined that there is additional social media messages-related information to translate, control returns to block 1214. - If, at
block 1218, thedata translator 140 determined that there is not additional social media messages-related information to translate, then, atblock 1220, theexample data translator 140 determines whether to continue normalizing audience measurement data. If, atblock 1220, theexample data translator 140 determined to continue normalizing audience measurement data, control returns to block 1202 to wait to obtain ratings-related information for translating. - If, at
block 1220, theexample data translator 140 determined not to continue normalizing audience measurement data, theexample process 1200 ofFIG. 12 ends. - While in the illustrated example, the
example instructions 1200 ofFIG. 12 represent a single iteration of normalizing audience measurement data, in practice, theexample instructions 1200 of the illustrated example ofFIG. 12 may be executed in parallel (e.g., in separate threads) to allow thecentral facility 125 to handle multiple requests for normalizing audience measurement data at a time. -
FIG. 13 is a flowchart representative of example machine-readable instructions 1300 that may be executed by theexample model builder 150 ofFIG. 1 to build a lift prediction model used to estimate ratings lift for media assets of interest. Theexample instructions 1300 ofFIG. 13 begin atblock 1302 when theexample model builder 150 selects a lift prediction model to build based on the translated data variables stored in the example translateddata database 145 ofFIG. 1 . For example, themodel builder 150 may select a lift prediction model based on season-episode groupings of a particular media asset of interest for which ratings list is to be predicted. Atblock 1304, theexample model builder 150 selects a demographic grouping associated with the lift prediction model. For example, themodel builder 150 may generate a plurality of lift prediction models corresponding to different demographic segments. - At
block 1306, theexample model builder 150 obtains translated data variables based on the selected lift prediction model and the selected demographic grouping. For example, depending on the selected lift prediction model, themodel builder 150 may obtain program characteristics, social media indicators, current ratings information, historical ratings information and/or program loyalty scores for different media assets. In some examples, themodel builder 150 may consult the example data table 1000 of the illustrated example ofFIG. 10 to determine the translated data variables associated with the selected lift prediction model. - At
block 1308, theexample model builder 150 determines a relationship between the obtained translated data variables and rating lifts. For example, themodel builder 150 may represent the lift prediction model via an equation (e.g., theexample Equation 1 described above) and by applying logistic regression to the translated data variables, themodel builder 150 may solve for coefficients of the equation. - At
block 1310, theexample model builder 150 records the generated lift prediction model. For example, themodel builder 150 may store the determined coefficients in the examplemodels data store 155 ofFIG. 1 . Atblock 1312, theexample model builder 150 determines whether there is another demographic grouping to process for the selected lift prediction model. If, at 1312, themodel builder 150 determined that there is another demographic grouping to process, then control returns to block 1304 to select a demographic grouping to process. - If, at
block 1312, themodel builder 150 determined that there is not another demographic grouping to process, then, atblock 1314, theexample model builder 150 determines whether there is another lift prediction model to build. For example, themodel builder 150 may determine whether to build lift prediction models for a different season-episode grouping of a different media asset for which ratings lift is to be predicted. If, atblock 1314, themodel builder 150 determined that there is another lift prediction model to build, then control returns to block 1302 to select a lift prediction model. - If, at
block 1314, themodel builder 150 determined that there is not another lift prediction model to build, theexample process 1300 ofFIG. 13 ends. -
FIG. 14 is a flowchart representative of example machine-readable instructions 1400 that may be executed by the exampleprogram ratings estimator 160 ofFIG. 1 to predict time-shifted exposure to media. Theexample instructions 1400 ofFIG. 14 begin atblock 1402 when the exampleprogram ratings estimator 160 selects a lift prediction model to use to estimate ratings lift for a media asset of interest. For example, the exampleprogram ratings estimator 160 may select a lift prediction model based on season and episode number information associated with the media asset of interest. In some examples, theprogram ratings estimator 160 may consult theexample schema 900 of the illustrated example ofFIG. 9 to identify a lift prediction model based on season-episode groupings. - At
block 1404, the exampleprogram ratings estimator 160 obtains translated data variables based on the selected lift prediction model. For example, depending on the selected lift prediction model, theprogram ratings estimator 160 may obtain, for the media asset of interest, program characteristics, social media indicators, historical ratings information and/or program loyalty scores. In some examples, theprogram ratings estimator 160 may consult the example data table 1000 of the illustrated example ofFIG. 10 to determine the translated data variables associated with the selected lift prediction model. - At
block 1406, the exampleprogram ratings estimator 160 determines estimated current ratings information for the media asset of interest. For example, theprogram ratings estimator 160 may process time-period ratings (e.g., overnight ratings provided via a fast affiliates report) and actual broadcast information to estimate current ratings (e.g., “live” ratings and “live+same day” ratings) associated with the media asset of interest to determine estimated current ratings for the media asset. In some examples, theprogram ratings estimator 160 may further process such information to estimate program lead-in ratings associated with the program that precedes the media asset of interest. - At
block 1408, the exampleprogram ratings estimator 160 applies the translated data variables and the estimated current ratings to the selected lift prediction model to determine the estimated ratings lift for the media asset of interest. Atblock 1410, the exampleprogram ratings estimator 160 determines whether there is another media asset of interest to process. If, atblock 1410, the exampleprogram ratings estimator 160 determined that there is another media asset of interest to process, then control returns to block 1402 to select a lift prediction model. - If, at
block 1410, the exampleprogram ratings estimator 160 determined that there is not another media asset of interest to process, theexample process 1400 ofFIG. 14 ends. -
FIG. 15 is a block diagram of anexample processor platform 1500 capable of executing the instructions ofFIGS. 11-13 and/or 14 to implement thecentral facility 125 ofFIG. 1 and/or thedata translator 140 ofFIGS. 1 and/or 4 . Theprocessor platform 1500 can be, for example, a server, a personal computer, or any other type of computing device. - The
processor platform 1500 of the illustrated example includes aprocessor 1512. Theprocessor 1512 of the illustrated example is hardware. For example, theprocessor 1512 can be implemented by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired family or manufacturer. - The
processor 1512 of the illustrated example includes a local memory 1513 (e.g., a cache). Theprocessor 1512 of the illustrated example executes the instructions to implement theexample data interface 130, the exampleraw data database 135, theexample data translator 140, the example translateddata database 145, theexample model builder 150, theexample models database 155, the exampleprogram ratings estimator 160, theexample ratings handler 405, the example attributeshandler 410 and the examplesocial media handler 415. Theprocessor 1512 of the illustrated example is in communication with a main memory including avolatile memory 1514 and anon-volatile memory 1516 via abus 1518. Thevolatile memory 1514 may be implemented by Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM) and/or any other type of random access memory device. Thenon-volatile memory 1516 may be implemented by flash memory and/or any other desired type of memory device. Access to themain memory - The
processor platform 1500 of the illustrated example also includes aninterface circuit 1520. Theinterface circuit 1520 may be implemented by any type of interface standard, such as an Ethernet interface, a universal serial bus (USB), and/or a PCI express interface. - In the illustrated example, one or
more input devices 1522 are connected to theinterface circuit 1520. The input device(s) 1522 permit(s) a user to enter data and commands into theprocessor 1512. The input device(s) can be implemented by, for example, an audio sensor, a microphone, a camera (still or video), a keyboard, a button, a mouse, a touchscreen, a track-pad, a trackball, isopoint and/or a voice recognition system. - One or
more output devices 1524 are also connected to theinterface circuit 1520 of the illustrated example. Theoutput devices 1524 can be implemented, for example, by display devices (e.g., a light emitting diode (LED), an organic light emitting diode (OLED), a liquid crystal display, a cathode ray tube display (CRT), a touchscreen, a tactile output device, a printer and/or speakers). Theinterface circuit 1520 of the illustrated example, thus, typically includes a graphics driver card, a graphics driver chip or a graphics driver processor. - The
interface circuit 1520 of the illustrated example also includes a communication device such as a transmitter, a receiver, a transceiver, a modem and/or network interface card to facilitate exchange of data with external machines (e.g., computing devices of any kind) via a network 1526 (e.g., an Ethernet connection, a digital subscriber line (DSL), a telephone line, coaxial cable, a cellular telephone system, etc.). - The
processor platform 1500 of the illustrated example also includes one or moremass storage devices 1528 for storing software and/or data. Examples of suchmass storage devices 1528 include floppy disk drives, hard drive disks, compact disk drives, Blu-ray disk drives, RAID systems, and digital versatile disk (DVD) drives. Theexample mass storage 1528 implements the exampleraw data database 135, the example translateddata database 145 and the examplemodels data store 155. - The coded
instructions 1532 ofFIGS. 11-13 and/or 14 may be stored in themass storage device 1528, in thevolatile memory 1514, in thenon-volatile memory 1516, and/or on a removable tangible computer readable storage medium such as a CD or DVD. - From the foregoing, it will appreciate that the above disclosed methods, apparatus and articles of manufacture facilitate predicting time-shifted viewing of media. For example, disclosed examples include building a lift prediction model based on historical audience measurement data. Examples disclosed herein may then apply data related to the media to the lift prediction model to predict time-shifted viewing of the media. In some examples, real-time ratings information (e.g., overnight ratings) is also applied to the lift prediction model to predict the time-shifted viewing of the media.
- Although certain example methods, apparatus and articles of manufacture have been disclosed herein, the scope of coverage of this patent is not limited thereto. On the contrary, this patent covers all methods, apparatus and articles of manufacture fairly falling within the scope of the claims of this patent.
Claims (19)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/951,454 US20160148228A1 (en) | 2014-11-24 | 2015-11-24 | Methods and apparatus to predict time-shifted exposure to media |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201462083716P | 2014-11-24 | 2014-11-24 | |
US14/951,454 US20160148228A1 (en) | 2014-11-24 | 2015-11-24 | Methods and apparatus to predict time-shifted exposure to media |
Publications (1)
Publication Number | Publication Date |
---|---|
US20160148228A1 true US20160148228A1 (en) | 2016-05-26 |
Family
ID=56010639
Family Applications (5)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/951,465 Abandoned US20160150280A1 (en) | 2014-11-24 | 2015-11-24 | Methods and apparatus to project ratings for future broadcasts of media |
US14/951,454 Abandoned US20160148228A1 (en) | 2014-11-24 | 2015-11-24 | Methods and apparatus to predict time-shifted exposure to media |
US16/036,614 Active US10867308B2 (en) | 2014-11-24 | 2018-07-16 | Methods and apparatus to project ratings for future broadcasts of media |
US17/121,323 Active US11657413B2 (en) | 2014-11-24 | 2020-12-14 | Methods and apparatus to project ratings for future broadcasts of media |
US18/301,183 Active US11989746B2 (en) | 2014-11-24 | 2023-04-14 | Methods and apparatus to project ratings for future broadcasts of media |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/951,465 Abandoned US20160150280A1 (en) | 2014-11-24 | 2015-11-24 | Methods and apparatus to project ratings for future broadcasts of media |
Family Applications After (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/036,614 Active US10867308B2 (en) | 2014-11-24 | 2018-07-16 | Methods and apparatus to project ratings for future broadcasts of media |
US17/121,323 Active US11657413B2 (en) | 2014-11-24 | 2020-12-14 | Methods and apparatus to project ratings for future broadcasts of media |
US18/301,183 Active US11989746B2 (en) | 2014-11-24 | 2023-04-14 | Methods and apparatus to project ratings for future broadcasts of media |
Country Status (2)
Country | Link |
---|---|
US (5) | US20160150280A1 (en) |
WO (2) | WO2016086075A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10867308B2 (en) | 2014-11-24 | 2020-12-15 | The Nielsen Company (Us), Llc | Methods and apparatus to project ratings for future broadcasts of media |
CN112154668A (en) * | 2019-04-24 | 2020-12-29 | 海信视像科技股份有限公司 | Repeated watching device analysis method and analysis system for searching advertisement time period |
US20230085186A1 (en) * | 2020-04-07 | 2023-03-16 | Dentsu Inc. | Information processing apparatus, plan revision assist method and plan revision assist program |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130346154A1 (en) * | 2012-06-22 | 2013-12-26 | Josephine Holz | Systems and methods for audience measurement analysis |
US11443332B2 (en) * | 2014-12-22 | 2022-09-13 | Superior Integrated Solutions Llc | System, method, and software for predicting the likelihood of selling automotive commodities |
US10674214B2 (en) * | 2015-08-28 | 2020-06-02 | DISH Technologies L.L.C. | Systems, methods and apparatus for presenting relevant programming information |
US20170161772A1 (en) * | 2015-12-03 | 2017-06-08 | Rovi Guides, Inc. | Methods and Systems for Targeted Advertising Using Machine Learning Techniques |
CN106095903A (en) * | 2016-06-08 | 2016-11-09 | 成都三零凯天通信实业有限公司 | A kind of radio and television the analysis of public opinion method and system based on degree of depth learning art |
US10430239B2 (en) * | 2016-08-24 | 2019-10-01 | Clari Inc. | Method and system for predicting task completion of a time period based on task completion rates of prior time periods using machine learning |
US20180096028A1 (en) * | 2016-09-30 | 2018-04-05 | Salesforce.Com, Inc. | Framework for management of models based on tenant business criteria in an on-demand environment |
US10165315B2 (en) * | 2016-10-17 | 2018-12-25 | Viacom International Inc. | Systems and methods for predicting audience measurements of a television program |
WO2018131576A1 (en) * | 2017-01-10 | 2018-07-19 | 株式会社電通 | Advertisement slot optimization system and advertisement slot optimization method in broadcast media such as television |
US10778599B2 (en) * | 2017-03-30 | 2020-09-15 | Home Box Office, Inc. | Predictive scaling of computing resources |
US11367049B2 (en) | 2017-05-02 | 2022-06-21 | Clari Inc. | Method and system for identifying emails and calendar events associated with projects of an enterprise entity |
US20190057339A1 (en) | 2017-08-16 | 2019-02-21 | Clari Inc. | Method and system for determining states of tasks based on activities associated with the tasks over a predetermined period of time |
US11416799B2 (en) | 2017-08-28 | 2022-08-16 | Clari Inc. | Method and system for summarizing user activities of tasks into a single activity score using machine learning to predict probabilities of completeness of the tasks |
WO2019070879A1 (en) | 2017-10-04 | 2019-04-11 | AMC Network Entertainment LLC | Graphical user interface for graphically displaying television viewership data |
US11922440B2 (en) * | 2017-10-31 | 2024-03-05 | Oracle International Corporation | Demand forecasting using weighted mixed machine learning models |
US11250357B2 (en) | 2018-01-29 | 2022-02-15 | Clari Inc. | Method for estimating amount of task objects required to reach target completed tasks |
US11451875B2 (en) * | 2018-06-04 | 2022-09-20 | Samsung Electronics Co., Ltd. | Machine learning-based approach to demographic attribute inference using time-sensitive features |
US10785538B2 (en) | 2018-10-03 | 2020-09-22 | Comcast Cable Communications, Llc | Prioritized content selection and delivery |
US11663493B2 (en) * | 2019-01-30 | 2023-05-30 | Intuit Inc. | Method and system of dynamic model selection for time series forecasting |
US11568215B2 (en) | 2019-07-15 | 2023-01-31 | The Nielsen Company (Us), Llc | Probabilistic modeling for anonymized data integration and bayesian survey measurement of sparse and weakly-labeled datasets |
US11657302B2 (en) | 2019-11-19 | 2023-05-23 | Intuit Inc. | Model selection in a forecasting pipeline to optimize tradeoff between forecast accuracy and computational cost |
US11423250B2 (en) | 2019-11-19 | 2022-08-23 | Intuit Inc. | Hierarchical deep neural network forecasting of cashflows with linear algebraic constraints |
US20210350459A1 (en) * | 2020-05-07 | 2021-11-11 | Fine Art Bourse Australia Pty Ltd | Diamond Asset Systems and Methods Facilitating Transactions, Valuation, and Securitization |
US11902622B2 (en) * | 2020-05-28 | 2024-02-13 | Comcast Cable Communications, Llc | Methods, systems, and apparatuses for determining viewership |
CN112598447B (en) * | 2020-12-28 | 2023-10-10 | 加和(北京)信息科技有限公司 | Order information processing method and device, electronic equipment and processor |
US11961611B2 (en) | 2021-05-03 | 2024-04-16 | Evernorth Strategic Development, Inc. | Automated bias correction for database systems |
CN113379447B (en) * | 2021-05-28 | 2024-05-31 | 西安影视数据评估中心有限公司 | Prediction method for single-day audience rating of television |
US11973576B2 (en) * | 2021-12-29 | 2024-04-30 | The Nielsen Company (Us), Llc | Methods, systems and apparatus to determine panel attrition |
US20240129569A1 (en) * | 2022-09-29 | 2024-04-18 | Gracenote, Inc. | Predictive Measurement of End-User Activities at Specified Times |
US11743524B1 (en) | 2023-04-12 | 2023-08-29 | Recentive Analytics, Inc. | Artificial intelligence techniques for projecting viewership using partial prior data sources |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010020236A1 (en) * | 1998-03-11 | 2001-09-06 | Cannon Mark E. | Method and apparatus for analyzing data and advertising optimization |
US20080249832A1 (en) * | 2007-04-04 | 2008-10-09 | Microsoft Corporation | Estimating expected performance of advertisements |
US20110040612A1 (en) * | 2009-08-14 | 2011-02-17 | Simmons Willard L | Machine learning for computing and targeting bids for the placement of advertisements |
US20110119126A1 (en) * | 2009-11-19 | 2011-05-19 | Google Inc. | Online Monitoring Systems to Determine Offline Advertising Effectiveness |
US20110196733A1 (en) * | 2010-02-05 | 2011-08-11 | Wei Li | Optimizing Advertisement Selection in Contextual Advertising Systems |
US20120004983A1 (en) * | 2010-06-30 | 2012-01-05 | Cbs Interactive Inc. | Systems and methods for determining the efficacy of advertising |
US20120084141A1 (en) * | 2009-03-30 | 2012-04-05 | Acquisio | System and Method to Predict the Performance of Keywords for Advertising Campaigns Managed on the Internet |
US8265989B2 (en) * | 2009-05-05 | 2012-09-11 | The Nielsen Company, LLC | Methods and apparatus to determine effects of promotional activity on sales |
US20120254911A1 (en) * | 2011-04-01 | 2012-10-04 | Peter Campbell Doe | Methods, apparatus and articles of manufacture to estimate local market audiences of media content |
US20120259919A1 (en) * | 2011-04-07 | 2012-10-11 | Rong Yan | Using Polling Results as Discrete Metrics for Content Quality Prediction Model |
US20120323675A1 (en) * | 2010-12-15 | 2012-12-20 | Ari Paparo | Methods and apparatus to measure comparative performance of internet and television ad campaigns |
US8364516B2 (en) * | 2008-09-05 | 2013-01-29 | The Nielsen Company (Us), Llc | Methods and apparatus to determine the effects of trade promotions on subsequent sales |
US20130311408A1 (en) * | 2012-05-15 | 2013-11-21 | Comcast Cable Communications, Llc | Determining and Predicting Popularity of Content |
US20130346154A1 (en) * | 2012-06-22 | 2013-12-26 | Josephine Holz | Systems and methods for audience measurement analysis |
Family Cites Families (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7080026B2 (en) * | 2000-10-27 | 2006-07-18 | Manugistics, Inc. | Supply chain demand forecasting and planning |
US20020143669A1 (en) * | 2001-01-22 | 2002-10-03 | Scheer Robert H. | Method for managing inventory within an integrated supply chain |
WO2003075524A1 (en) * | 2002-03-04 | 2003-09-12 | Fujitsu Limited | Hierarchical encoded data distributor and distributing method |
CN100591116C (en) * | 2002-03-28 | 2010-02-17 | 诺基亚公司 | Method and system for announcing a transport stream in a digital broadcast network |
GB0420814D0 (en) * | 2004-09-18 | 2004-10-20 | Koninkl Philips Electronics Nv | Managing stored service information |
US8613024B2 (en) * | 2005-12-13 | 2013-12-17 | United Video Properties, Inc. | Cross-platform predictive popularity ratings for use in interactive television applications |
US20070147409A1 (en) * | 2005-12-22 | 2007-06-28 | Nokia Corporation | Optimized method for multiplexing digital data |
JP4049799B2 (en) * | 2006-04-26 | 2008-02-20 | 三菱電機株式会社 | Digital broadcast receiving apparatus and receiving method thereof |
US7702337B2 (en) * | 2006-05-16 | 2010-04-20 | Nokia Corporation | Method and system for providing quick service access |
US20080155587A1 (en) * | 2006-12-20 | 2008-06-26 | General Instrument Corporation | Video Content Targeting System and Method |
KR101405967B1 (en) * | 2007-06-28 | 2014-06-12 | 엘지전자 주식회사 | Digital broadcasting system and method of processing data in digital broadcasting system |
KR101486357B1 (en) * | 2007-07-12 | 2015-01-26 | 엘지전자 주식회사 | method of transmitting and receiving a broadcasting signal and apparatus for receiving a broadcasting signal |
KR101486372B1 (en) * | 2007-07-25 | 2015-01-26 | 엘지전자 주식회사 | Digital broadcasting system and method of processing data in digital broadcasting system |
US8413194B2 (en) * | 2007-08-24 | 2013-04-02 | Lg Electronics Inc. | Digital broadcasting system and method of processing data in digital broadcasting system |
US8059210B2 (en) * | 2007-08-24 | 2011-11-15 | Lg Electronics, Inc. | Digital broadcasting system and method of processing data in the digital broadcasting system |
US8776143B2 (en) * | 2007-08-24 | 2014-07-08 | Lg Electronics Inc. | Digital broadcasting system and method of processing data in digital broadcasting system |
KR101556134B1 (en) * | 2007-08-24 | 2015-09-30 | 엘지전자 주식회사 | Digital broadcasting receiver and method for controlling the same |
US8051451B2 (en) * | 2007-08-24 | 2011-11-01 | Lg Electronics, Inc. | Digital broadcasting system and method of processing data in digital broadcasting system |
US7936786B2 (en) * | 2007-09-20 | 2011-05-03 | Lg Electronics, Inc. | Digital broadcasting system and method of processing data in digital broadcasting system |
WO2009038437A2 (en) * | 2007-09-21 | 2009-03-26 | Lg Electronics Inc. | Digital broadcasting receiver and method for controlling the same |
US20090083779A1 (en) * | 2007-09-24 | 2009-03-26 | Yevgeniy Eugene Shteyn | Digital content promotion |
US20090106297A1 (en) | 2007-10-18 | 2009-04-23 | David Howell Wright | Methods and apparatus to create a media measurement reference database from a plurality of distributed sources |
KR100889988B1 (en) * | 2007-11-30 | 2009-03-25 | 엔에이치엔(주) | System for ranking broadcast program and method thereof |
US20090158309A1 (en) * | 2007-12-12 | 2009-06-18 | Hankyu Moon | Method and system for media audience measurement and spatial extrapolation based on site, display, crowd, and viewership characterization |
KR20100016774A (en) * | 2008-08-05 | 2010-02-16 | 삼성전자주식회사 | Apparatus and method for braodcasting information |
US20100106561A1 (en) | 2008-10-28 | 2010-04-29 | Sergiy Peredriy | Forecasting Using Share Models And Hierarchies |
JP2010130585A (en) * | 2008-11-28 | 2010-06-10 | Video Research:Kk | Viewer rating prediction apparatus and program |
US8046468B2 (en) * | 2009-01-26 | 2011-10-25 | Vmware, Inc. | Process demand prediction for distributed power and resource management |
CA2750700C (en) * | 2009-01-30 | 2018-11-27 | Invidi Technologies Corporation | System and method for auctioning avails |
US8774225B2 (en) * | 2009-02-04 | 2014-07-08 | Nokia Corporation | Mapping service components in a broadcast environment |
US7882054B2 (en) * | 2009-03-19 | 2011-02-01 | Gutman Levitan | System for estimating audience size in a digital broadcast environment using control packets and predictions |
WO2010120156A2 (en) * | 2009-04-17 | 2010-10-21 | 엘지전자 주식회사 | Transmitting/receiving system and broadcast signal processing method |
KR20110053160A (en) * | 2009-11-13 | 2011-05-19 | 삼성전자주식회사 | Method and apparatus for generating multimedia stream for 3-dimensional display of additional video display information, method and apparatus for receiving the same |
CA2818107C (en) * | 2010-02-12 | 2017-06-27 | Lg Electronics Inc. | Broadcasting signal transmitter/receiver and broadcasting signal transmission/reception method |
CA2845224A1 (en) * | 2010-04-04 | 2011-10-13 | Lg Electronics Inc. | Method and apparatus for processing non-real-time broadcast service and content transmitted by broadcast signal |
GB2480882B (en) * | 2010-06-04 | 2016-08-31 | Samsung Electronics Co Ltd | Method and apparatus for multiplexing different efficiency modes in digital radio systems |
US9092797B2 (en) | 2010-09-22 | 2015-07-28 | The Nielsen Company (Us), Llc | Methods and apparatus to analyze and adjust demographic information |
US20140130109A1 (en) * | 2011-04-20 | 2014-05-08 | Shenzhen Skyworth Digital Technology Co., Ltd. | System and method for playing digital television program, and digital television reception terminal |
WO2012173387A2 (en) * | 2011-06-16 | 2012-12-20 | Samsung Electronics Co., Ltd. | Method and apparatus for transmitting and receiving signaling information for reception of broadcast services in a digital broadcasting system |
US8959554B2 (en) * | 2012-04-25 | 2015-02-17 | Samsung Electronics Co., Ltd | Apparatus and method for transmitting and receiving signaling information in a digital broadcasting system |
KR101501344B1 (en) * | 2012-05-02 | 2015-03-10 | 삼성전자주식회사 | Method and apparatus for transmitting and receiving multimedia service |
US20130297706A1 (en) * | 2012-05-03 | 2013-11-07 | United Video Properties, Inc. | Systems and methods for processing input from a plurality of users to identify a type of media asset segment |
US20140019208A1 (en) | 2012-07-11 | 2014-01-16 | Nathan W. Brixius | Methods and apparatus to evaluate model stability and fit |
US20140075018A1 (en) * | 2012-09-11 | 2014-03-13 | Umbel Corporation | Systems and Methods of Audience Measurement |
US20140096169A1 (en) * | 2012-09-28 | 2014-04-03 | Joseph Dodson | Playback synchronization in a group viewing a media title |
US9002942B2 (en) * | 2012-10-08 | 2015-04-07 | Google Inc. | Processing content spoilers |
US20140344861A1 (en) * | 2013-05-14 | 2014-11-20 | Tivo Inc. | Method and system for trending media programs for a user |
CA2921921C (en) * | 2013-08-22 | 2022-06-07 | Thomson Licensing | System physical layer pipe for a digital television system |
WO2015160221A1 (en) * | 2014-04-18 | 2015-10-22 | Samsung Electronics Co., Ltd. | Method and apparatus for providing information related to content supporting broadcast service |
US9785719B2 (en) * | 2014-07-15 | 2017-10-10 | Adobe Systems Incorporated | Generating synthetic data |
US10185971B2 (en) * | 2014-10-27 | 2019-01-22 | Adobe Systems Incorporated | Systems and methods for planning and executing an advertising campaign targeting TV viewers and digital media viewers across formats and screen types |
WO2016086075A1 (en) * | 2014-11-24 | 2016-06-02 | The Nielsen Company (Us), Llc | Methods and apparatus to predict time-shifted exposure to media |
-
2015
- 2015-11-24 WO PCT/US2015/062551 patent/WO2016086075A1/en active Application Filing
- 2015-11-24 WO PCT/US2015/062554 patent/WO2016086076A1/en active Application Filing
- 2015-11-24 US US14/951,465 patent/US20160150280A1/en not_active Abandoned
- 2015-11-24 US US14/951,454 patent/US20160148228A1/en not_active Abandoned
-
2018
- 2018-07-16 US US16/036,614 patent/US10867308B2/en active Active
-
2020
- 2020-12-14 US US17/121,323 patent/US11657413B2/en active Active
-
2023
- 2023-04-14 US US18/301,183 patent/US11989746B2/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010020236A1 (en) * | 1998-03-11 | 2001-09-06 | Cannon Mark E. | Method and apparatus for analyzing data and advertising optimization |
US20080249832A1 (en) * | 2007-04-04 | 2008-10-09 | Microsoft Corporation | Estimating expected performance of advertisements |
US8364516B2 (en) * | 2008-09-05 | 2013-01-29 | The Nielsen Company (Us), Llc | Methods and apparatus to determine the effects of trade promotions on subsequent sales |
US20120084141A1 (en) * | 2009-03-30 | 2012-04-05 | Acquisio | System and Method to Predict the Performance of Keywords for Advertising Campaigns Managed on the Internet |
US8265989B2 (en) * | 2009-05-05 | 2012-09-11 | The Nielsen Company, LLC | Methods and apparatus to determine effects of promotional activity on sales |
US20110040612A1 (en) * | 2009-08-14 | 2011-02-17 | Simmons Willard L | Machine learning for computing and targeting bids for the placement of advertisements |
US20110119126A1 (en) * | 2009-11-19 | 2011-05-19 | Google Inc. | Online Monitoring Systems to Determine Offline Advertising Effectiveness |
US20110196733A1 (en) * | 2010-02-05 | 2011-08-11 | Wei Li | Optimizing Advertisement Selection in Contextual Advertising Systems |
US20120004983A1 (en) * | 2010-06-30 | 2012-01-05 | Cbs Interactive Inc. | Systems and methods for determining the efficacy of advertising |
US20120323675A1 (en) * | 2010-12-15 | 2012-12-20 | Ari Paparo | Methods and apparatus to measure comparative performance of internet and television ad campaigns |
US20120254911A1 (en) * | 2011-04-01 | 2012-10-04 | Peter Campbell Doe | Methods, apparatus and articles of manufacture to estimate local market audiences of media content |
US20120259919A1 (en) * | 2011-04-07 | 2012-10-11 | Rong Yan | Using Polling Results as Discrete Metrics for Content Quality Prediction Model |
US20130311408A1 (en) * | 2012-05-15 | 2013-11-21 | Comcast Cable Communications, Llc | Determining and Predicting Popularity of Content |
US20130346154A1 (en) * | 2012-06-22 | 2013-12-26 | Josephine Holz | Systems and methods for audience measurement analysis |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10867308B2 (en) | 2014-11-24 | 2020-12-15 | The Nielsen Company (Us), Llc | Methods and apparatus to project ratings for future broadcasts of media |
US11657413B2 (en) | 2014-11-24 | 2023-05-23 | The Nielsen Company (Us), Llc | Methods and apparatus to project ratings for future broadcasts of media |
CN112154668A (en) * | 2019-04-24 | 2020-12-29 | 海信视像科技股份有限公司 | Repeated watching device analysis method and analysis system for searching advertisement time period |
US20230085186A1 (en) * | 2020-04-07 | 2023-03-16 | Dentsu Inc. | Information processing apparatus, plan revision assist method and plan revision assist program |
Also Published As
Publication number | Publication date |
---|---|
US11657413B2 (en) | 2023-05-23 |
US20160150280A1 (en) | 2016-05-26 |
US11989746B2 (en) | 2024-05-21 |
WO2016086075A1 (en) | 2016-06-02 |
US20230325858A1 (en) | 2023-10-12 |
WO2016086076A1 (en) | 2016-06-02 |
US10867308B2 (en) | 2020-12-15 |
US20190012684A1 (en) | 2019-01-10 |
US20210174381A1 (en) | 2021-06-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20160148228A1 (en) | Methods and apparatus to predict time-shifted exposure to media | |
US12015826B2 (en) | Methods and apparatus to correct errors in audience measurements for media accessed using over-the-top devices | |
JP6918884B2 (en) | Methods and devices to compensate for misjudgment of the attribution of impression data and / or uncovered by the database owner | |
US9912424B2 (en) | Methods and apparatus to estimate ratings for media assets using social media | |
WO2016109438A1 (en) | Methods and apparatus to estimate demographics of an audience of a media event using social media message sentiment | |
US9936255B2 (en) | Methods and apparatus to determine characteristics of media audiences | |
US11375274B2 (en) | Methods and apparatus to increase a match rate for media identification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: THE NIELSEN COMPANY (US), LLC, NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CUI, JINGSONG;DOE, PETER CAMPBELL;SIGNING DATES FROM 20151202 TO 20160127;REEL/FRAME:037734/0063 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
AS | Assignment |
Owner name: CITIBANK, N.A., NEW YORK Free format text: SUPPLEMENTAL SECURITY AGREEMENT;ASSIGNORS:A. C. NIELSEN COMPANY, LLC;ACN HOLDINGS INC.;ACNIELSEN CORPORATION;AND OTHERS;REEL/FRAME:053473/0001 Effective date: 20200604 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
AS | Assignment |
Owner name: CITIBANK, N.A, NEW YORK Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE PATENTS LISTED ON SCHEDULE 1 RECORDED ON 6-9-2020 PREVIOUSLY RECORDED ON REEL 053473 FRAME 0001. ASSIGNOR(S) HEREBY CONFIRMS THE SUPPLEMENTAL IP SECURITY AGREEMENT;ASSIGNORS:A.C. NIELSEN (ARGENTINA) S.A.;A.C. NIELSEN COMPANY, LLC;ACN HOLDINGS INC.;AND OTHERS;REEL/FRAME:054066/0064 Effective date: 20200604 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STCV | Information on status: appeal procedure |
Free format text: NOTICE OF APPEAL FILED |
|
STCV | Information on status: appeal procedure |
Free format text: APPEAL BRIEF (OR SUPPLEMENTAL BRIEF) ENTERED AND FORWARDED TO EXAMINER |
|
STCV | Information on status: appeal procedure |
Free format text: EXAMINER'S ANSWER TO APPEAL BRIEF MAILED |
|
STCV | Information on status: appeal procedure |
Free format text: APPEAL READY FOR REVIEW |
|
STCV | Information on status: appeal procedure |
Free format text: ON APPEAL -- AWAITING DECISION BY THE BOARD OF APPEALS |
|
STCV | Information on status: appeal procedure |
Free format text: BOARD OF APPEALS DECISION RENDERED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- AFTER EXAMINER'S ANSWER OR BOARD OF APPEALS DECISION |
|
AS | Assignment |
Owner name: BANK OF AMERICA, N.A., NEW YORK Free format text: SECURITY AGREEMENT;ASSIGNORS:GRACENOTE DIGITAL VENTURES, LLC;GRACENOTE MEDIA SERVICES, LLC;GRACENOTE, INC.;AND OTHERS;REEL/FRAME:063560/0547 Effective date: 20230123 |
|
AS | Assignment |
Owner name: CITIBANK, N.A., NEW YORK Free format text: SECURITY INTEREST;ASSIGNORS:GRACENOTE DIGITAL VENTURES, LLC;GRACENOTE MEDIA SERVICES, LLC;GRACENOTE, INC.;AND OTHERS;REEL/FRAME:063561/0381 Effective date: 20230427 |
|
AS | Assignment |
Owner name: ARES CAPITAL CORPORATION, NEW YORK Free format text: SECURITY INTEREST;ASSIGNORS:GRACENOTE DIGITAL VENTURES, LLC;GRACENOTE MEDIA SERVICES, LLC;GRACENOTE, INC.;AND OTHERS;REEL/FRAME:063574/0632 Effective date: 20230508 |
|
AS | Assignment |
Owner name: NETRATINGS, LLC, NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: THE NIELSEN COMPANY (US), LLC, NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: GRACENOTE MEDIA SERVICES, LLC, NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: GRACENOTE, INC., NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: EXELATE, INC., NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: A. C. NIELSEN COMPANY, LLC, NEW YORK Free format text: RELEASE (REEL 053473 / FRAME 0001);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063603/0001 Effective date: 20221011 Owner name: NETRATINGS, LLC, NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 Owner name: THE NIELSEN COMPANY (US), LLC, NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 Owner name: GRACENOTE MEDIA SERVICES, LLC, NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 Owner name: GRACENOTE, INC., NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 Owner name: EXELATE, INC., NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 Owner name: A. C. NIELSEN COMPANY, LLC, NEW YORK Free format text: RELEASE (REEL 054066 / FRAME 0064);ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:063605/0001 Effective date: 20221011 |