WO2016120775A1

WO2016120775A1 - Engagement optimization

Info

Publication number: WO2016120775A1
Application number: PCT/IB2016/050353
Authority: WO
Inventors: Guy Rom; Yossi Mizrahi
Original assignee: Grymco 2014 Ltd.
Priority date: 2015-01-27
Filing date: 2016-01-25
Publication date: 2016-08-04

Abstract

A method for optimizing engagement with active leads, comprising: deducing and scoring each user's intent to buy and points of interest according to the user's online behavior and assessing the user's availability for engagement.

Description

ENGAGEMENT OPTIMIZATION

FIELD OF THE INVENTION

The present invention relates to user-engagement enhancement in online commerce.

CROSS-REFERENCE TO RELATED PATENT APPLICATIONS

This patent application claims priority from and is related to U.S. Provisional Patent Application Serial Number 62/108,084, filed 27 January 2015, this U.S. Provisional Patent Application incorporated by reference in its entirety herein.

BACKGROUND

A business with effective marketing and lead generation strategies needs a topnotch sales team that can convert most, if not all, of the leads into sales. There are several ways how to drive prospective buyers to become quality leads for a business. Marketing strategies and campaigns, together with telemarketing agents, can help scout leads that can ultimately be converted into actual paying customers.

For every call center, training sales agents how to qualify sales calls as either potentially good leads or bogus business calls is an important aspect of quality assurance. Once qualified, lead conversion must also be done effectively to make sure the sales process benefits the company's bottom line.

But sales agents from a call center can also face the problem of being bombarded by sales calls, especially during peak seasons or promotional periods. How can they effectively manage this influx of inbound leads?

Call centers respond to these challenges by focusing on several areas: 1. Availability- Call centers have the ability to manage sales operations and other call center support services on a 24/7 basis. By studying and strategically plotting the schedule of the available sales agents, a business can make sure that its product inquiry or order processing lines are available, even after normal business hours. The call center can therefore help give real-time responses to prospective buyers and eliminate the chances of losing them to competing brands.

2. Promptness - It's a fact that the quicker you respond to a sales inquiry, the higher the chances of having that certain lead converted into a successful sale. Sales agents must be properly trained on how to give prompt yet comprehensive responses that can convince prospects to go further into the sales process. The interest of customers to purchase items can decrease if there's a slow or delayed response from the support team.

3. Personalization - Sales agents can be helped in having a smoother call flow and providing consistent responses by developing lead conversion templates or guidelines on how to execute the sales talk.

4. Follow-up - By checking on your leads through follow-up emails or calls, a business can make sure that all its sales efforts have reached them successfully. They may have questions or concerns they want to raise. The agents' ability to convince them that the product is valuable to them can significantly increase sales.

A business with effective marketing and lead generation strategies needs a topnotch sales team that can convert most, if not all, of the acquired leads into actual sales. By ensuring that these areas are monitored and given attention, it can significantly improve the ability of its call center sales agents to increase the bottom line.

However, today's technological advancement in the field of communication and big-data analysis may even further improve the process of user engagement optimization. SUMMARY

According to a first aspect of the present invention there is provided a method for optimizing engagement with active leads, comprising: deducing and scoring each user's intent to buy and points of interest according to the user's online behavior; and assessing the user's availability for engagement.

The method may further comprise: receiving ID of a user requesting to be contacted by an advertiser; receiving IDs of current visitors to a plurality of publisher websites; correlating said current visitors' IDs with said user ID; analyzing said publisher websites' content; and scoring the advertiser's engagement with said user according to content relevance and time criteria.

Receiving user ID may comprise communicating said user ID by a code embedded in the advertiser's website to a system database.

Receiving user ID may comprise communicating said user ID by a code embedded in the advertiser's ad on the publisher's website to a system database.

Receiving IDs of current visitors may comprise communicating said visitors' user IDs by a code embedded in the publisher's website to a system database.

Each one of said user I D and said visitor ID may comprise a device I D and the method may further comprise identifying users and website visitors according to said device ID.

The device may be one of a plurality of devices and the method may further comprise identifying users and website visitors according to any one ID of said plurality of device. Analyzing may comprise intent to buy analysis and points of interest analysis.

According to a second aspect of the present invention there is provided a system for optimizing advertisers' engagement comprising: a system server storing advertisers' and website visitors' databases; a plurality of advertisers' websites comprising advertiser's embedded code configured to communicate to the system server I Ds of users to be contacted by the advertiser by call, email, sms, push etc.; a plurality of publisher's websites comprising publisher's embedded code configured to communicate to the system server IDs of website visitors; and a plurality of publisher's websites hosting advertisers' banners comprising advertiser's embedded code configured to communicate to the system server IDs of website visitors to be contacted by the advertiser; wherein said system server is configured to analyze said communicated data and optimize engagement with users/customers, by manual or automatic operations. Analyzing may comprise analyzing online activities and devices information.

The websites and apps analysis may comprise using own generated data or 3^rd party data .

The websites analysis may comprise analyzing surfed websites using machine learning, statistical and contextual algorithms. The device information may comprise at least one of device type and device location.

The analyzing may comprise intent to buy and points of interest.

The intent to buy analysis may comprise correlating said websites and apps analysis with advertiser's content world.

BRIEF DESCRIPTION OF THE DRAWINGS

For better understanding of the invention and to show how the same may be carried into effect, reference will now be made, purely by way of example, to the accompanying drawings.

With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of the preferred embodiments of the present invention only, and are presented in the cause of providing what is believed to be the most useful and readily understood description of the principles and conceptual aspects of the invention. In this regard, no attempt is made to show structural details of the invention in more detail than is necessary for a fundamental understanding of the invention, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice. In the accompanying drawings: Fig. 1 is a general block diagram showing the main parts of the system according to the invention; and

Figs. 2A through 2D are schematic flowcharts showing two processes supported by the system of the present invention.

DETAILED DESCRIPTION OF EMBODIMENTS

The method of the present invention provides a new paradigm for optimizing users engagement, by predicting the potential customer's interest and availability to be engaged by an advertiser, as opposed to prevailing methods where the advertiser proactively profiles internet users, mainly by analyzing their social networks profiles, connections and content, to create target groups for his campaigns.

Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of the components and/or methods set forth in the following description and/or illustrated in the drawings and/or the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.

Users of the system of the present invention may be producers/sellers/service providers that base their operation on generating leads (potential customers) online (websites, emails, apps etc.), contact the leads (phone, SMS, email, app notification etc.) and turn them into actual customers or call for action (go to website, call, open mobile app, download etc.).

Thus, the present invention provides a system and method for optimizing engagement with active users, based on collecting data related to online activities (websites, mobile apps, internet services etc.) and dynamic and real- time management of the user priority. The priorities are dynamically determined by:

1. Deducing and scoring each user's (potential or existing customer)

intent to buy and points of interest according to its online behavior, and

2. Assessing the user's availability for engagement (call, sms, email, app/browser push notification etc.).

The service enables firms to improve their conversion rate (leads to customers), to reduce the number of missed engagements (unanswered calls, unread emails etc.) and to improve the customer experience by engaging him at a time convenient to him with a targeted message.

The method uses two supervised learning data mining regression models that take discretized feature sets as independent variable inputs and produce a probability score:

Topics of interest categories→ probability of conversion User availability feature-set→ probability of engagement

Upon receiving a new user's registration, data is gathered from Events such as:

- Pre-reg Events - events prior to registration→ General Interest, topics and online actions that led to user's registration.

- Post-reg Events

The data collected indicates:

- General Interest research & comparison on topics related to user

- Regarding potential user engagement, Current State

features collected (evaluate appropriateness of

engagement timing and method).

The feature set is composed of discretely categorized bins of:

(1) General Interest identified Topics

(2) Current State identified Features (3) Engagement Result (the dependent variable)

The model is trained to predict the probability of Engagement Result (3) based upon features in General Interest identified Topics (1) and Current State identified Features (2). This allows the method to make predictions such as: LET

"Users with profile characteristics {A,B,C} be classified as User Type {Q}" GIVEN

"Users of type {Q} that showed a browsing pattern of add-relevant topics {l,J,K} have a X% probability of purchase intent" AND

"Users of type {Q} that showed a browsing pattern of add-relevant topics {l,J,M} have a Y% probability of purchase intent"

IT CAN BE IMPLIED THAT

"for User type Q, topic K placed users have a conversion rate of Z (where Z is the ratio X:Y) relative to topic M"

Data items collected may include (but are not limited to):

- User ID

- User actions - clicks, hover durations, scrolls

- Content keyword relevance score to advertisement topic

- A sequential series of page view requests - can yield web content, web structure and web usage mining

- Click-stream - Data features: time, I P address, page request URL , referrer - identify session

- Sequences of page types (e.g. shopping cart,

landing page etc.)

- Sequences of page categories

- Sessions - sort by session start time The data may yield at least some (but not exclusively) of the following extractable features:

- Identify user navigation patterns in the visited page sequences

- Statistics - number of page views, duration, number of sites, number of registrations etc.

- Content - Keyword/Topic relation score to the lead subject

- Geographic - country, city, location, language

- Time - how much time since user was registered, time of the day

(creation and/or engagement), day of the week etc. Demographic - male/female, age etc. based on content patterns.

Fig. 1 is a general block diagram showing the system 100 main parts:

- Advertisers 110: Firms that operate online sales operation 116. These are the system users. Advertisers make large investments in online campaigns and affiliates programs in order to persuade potential customers to register for contact (e.g. by providing their contact details using a form, chat, email etc.).

An advertiser's code 1 15 is embedded where users are generated, e.g. in the "Contact Us" page of the advertiser's website, which

communicates the user to the system server 130 where it is registered for the purpose of monitoring, analyzing and notifications regarding engagement recommendations.

- Publishers 120, 121 : Internet sites which, by embedding a publisher's code 125 in the website or by hosting an advertiser's banner in which the advertiser's code is embedded 126, provide data regarding website visitors to the system server 130.

- System server 130: Cloud-based platform comprising databases 135, which receives data from publishers regarding visitors to the various websites, analyses the data and cross-references it with users registered by advertisers. When relevant data is found, the server triggers manual or automatic action for engaging the user, e.g. sends a notification to the appropriate advertiser's call center to contact the potential customer or automatically sends email or SMS. Figs. 2A through 2D are schematic flowcharts showing two processes supported by the system of the present invention. The following steps, depicted in Fig. 2A, are common to both processes:

- In both processes a code is embedded where users are generated- step 201.

- Both processes begin when a user is generated (e.g. submitting a "Contact" form on advertiser's website) - step 202.

- In both processes an I D is created for the user (e.g. using Fingerprint JS, cookie, Ad ID or any other identifier or combination of identifiers) and stored on the server - step 203.

- In both processes another ID i.e. advertiser CRM user ID is created to enable cross-referencing with the system ID - step 204.

The flowchart 209 of Fig. 2B describes the initial actions performed on the system server following a website visitor leaving a lead on an advertiser's website.

In step 210 the advertiser code communicates to the server the system user ID created for the lead.

In step 215, if the user is new to the system, the system creates an initial system profile for the user, which may later be updated with data created while monitoring the website visitor. If the user already exists in the system the information is added/updated.

In step 220 the system saves the created profile in its databases and in step 225 the user ID is tagged as monitored by the advertiser. Figs 2C and 2D are flowcharts showing the continued monitoring of users surfing to establish intent to buy.

Process 1 : Code embedded in publisher's website

The code embedded in the publisher's website reports continuously to the system server information regarding visitors to the website (240) by creating and sending an I D (245) for each website visitor, IP address, URL, device type, language and other parameters.

The server receives the ID (255) and checks whether the same ID is being monitored (260) following a request by an advertiser. If the ID is found to be a monitored ID, the server checks if the current report is relevant for the advertiser's request (265). The relevance is determined by analyzing the current page content and checking whether it is relevant to the advertiser, e.g. a hotel review page is relevant to tourism firms.

Process 2: Code embedded in advertiser's banner

This process uses media (Ads, banners etc.) published by the advertiser on the internet in various channels (e.g. direct media buying, AdExchange, Affiliation, PPC etc.). The advertiser's code embedded in the banner reports to the system server information related to the websites visitors in a similar way to that described in process 1. Returning to Fig. 2C, in step 235 the advertiser's banner is hosted in the publisher's website.

The next steps are the same as in Process 1.

The embedded code in the publishers and advertisers sites/banners send information to the system server such as user identification, browser information, browsing information and behavior, device information.

The system server communicates to the advertiser's systems the user details such as user IDs, classification, time and location.

Website visitor identification and monitoring algorithm

In order to improve the function of tracking users' behavior, the system may use enhanced identification algorithms.

The first algorithm is designed to differentiate between various devices such as desktop computers, laptop computers, tablets and smart phones and to identify a specific website visitor by the device he uses. The device is identified by its Fingerprint, namely, by analyzing a plurality of parameters using JavaScript, such as browser type, operating system' language, fonts, time etc. and combining them to a unique fingerprint of the device.

A second algorithm using machine learning techniques (e.g. neural networking, back-propagation, statistics) enables identification of a user who uses a plurality of devices (cross-device). This algorithm is based on collecting large amounts of information from various databases (created by the system or accessible to the system), analysis, cross-referencing, fusion and retrieval of information. The system's own data sources are the codes embedded in many websites (publishers and advertisers) which gather data related to website visitors and devices.

When a user visits a web site, the pages they visit, the amount of time they view each page, the links they click on, the things that they interact with, allow us to collect that data and other factors to create a 'profile' that links to that visitor's web browser.

Returning to Fig. 2D, the data collected from the various sources (i.e. the system's internal sources and external sources such as free public databases, paid databases, business partners etc.) and in different formats is identified by the system (using tags, structures, formats etc.) and normalized to an internal format. Each data item is classified (265), assigned to an appropriate "bucket" and stored in the appropriate tables in the system's database (270).

The data in the buckets is then fused and cross-referenced with data in other buckets, correlations are calculated and the data is stored in smaller buckets. Overtime this process enables small buckets that give unique identification of website visitors.

Example:

1. Creating buckets containing information regarding website visitors in a certain website, at a certain location (using location aware browsing, e.g. Firefox), using a certain network (cellular provider, ISP, Wi-Fi etc.), language etc.

2. Cross-referencing the buckets to create fused lists of website visitors who fulfill a number of criteria.

3. Over time more criteria will be added thus creating more focused lists of website visitors, which may be cross-referenced in real time with information received from the system in real time regarding a specific website visitor, to establish whether the website visitor is "known" to the system or "new".

4. When a website visitor is identified, the device he is currently using is mapped to the same user and added to the other devices (if any) so that the website visitor may be identified each time he uses any one of these devices.

Website visitor's intent to buy algorithm

This algorithm aims to grade the correlation between the website visitor's surfing actions and the category of the product or service of the advertiser in which the website visitor had previously shown interest. The correlation is tested in two aspects: content correlation and website visitor's behavior correlation.

Content correlation refers to the extent to which the content of the page which the website visitor is presently visiting is correlated to the advertiser's content world. For example: a website visitor currently visits a hotel booking website which is relevant to a lead he had left at a travel agency where he was interested in flights abroad. This is a simple and clear example, but the system also needs to determine in less straight forward cases, such as: is the website visitor currently visiting a news site that is relevant to his travel agency lead (an article related to the weather or to a festival may be relevant while an article related to real estate may not). The algorithm grades (275) the content correlation by extracting keywords from the web page currently visited and correlating them with categories, sub- categories, keywords and more, which are relevant to the advertiser's content world (as will be explained in detail below).

Correlating the website visitor's surfing behavior means monitoring the website visitor's actions and identifying events and action which may indicate intent to buy. This is a statistical and contextual algorithm that measures various parameters such as: number of visits to the website, time spent in the website, number of relevant websites visited by the website visitor, total time spent in relevant websites, surfing in price comparison websites, reading recommendations, etc. By measuring the various parameters the system determines a grade (280) indicating a level of intent to buy.

The two grades reflecting content correlation and intent to buy are combined into a single grade which indicated the website visitor's intent to buy and enables the system to grade the advertiser's leads accordingly (285). The priority is communicated to the advertiser (290). Website analysis

One of the parameters for determining if this is a suitable time to contact a potential user is the content of the user's currently surfed webpage and its relevance to the product or service offered by the advertiser.

This requires analyzing the current webpage, categorizing and sub- categorizing it, extracting keywords and "understanding" the text.

A website analysis may be performed on different levels:

- Categorizing by URL and keywords: Most websites enable

categorization by URL, since the URLs are arranged a-priori by category - for example, economic articles will appear under finance.yahoo.com, sports articles will appear under sports.yahoo.com etc. Moreover, many website have sub-categories, so that stock indices will appear under investing.com/charts/stock-charts and the gold index will appear under investing.com/commodities/gold. Also, it is possible to check correlation with keywords the platform assigns to each user, by using the webpage's metadata (keywords, description). Example of metadata in the gold index page referred to above:

< meta name- 'description" content="Get detailed information about Gold including Price, Charts, Technical Analysis, Historical data, Reports and more.">

- Categorizing by machine learning: Statistical machine learning and NLP (natural language processing) algorithms are used to perform automatic content analysis of webpages, followed by automatic categorization and sub-categorization.

Retention According to some embodiments, the present invention serves as a retention facilitator for the system clients, to retain and re-attract their users.

The client (advertiser) may request the system to locate any number of tracked users at a given time. These may be current users or past users which the system continues to track. The client may query the system for information regarding these tracked users, such as which of them are currently online, their geographic and/or linguistic distribution, top areas of interest, etc.

Integration

The described system may have interfaces with other users' engagement systems such as CRM, email marketing systems, app servers etc.

The engagement triggers produced by the system can be manually or automatically be transferred to any integrated system for delivering the engagement, e.g. send an email to the user.

The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.

The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g. , light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.

Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some

embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions. These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a

programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks. The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

1. A method for optimizing engagement with active leads, comprising: deducing and scoring each user's intent to buy and points of interest according to the user's online behavior; and assessing the user's availability for engagement.

2. The method of claim 1 , comprising:

receiving ID of a user requesting to be contacted by an advertiser; receiving IDs of current visitors to a plurality of publisher websites; correlating said current visitors' IDs with said user ID;

analyzing said publisher websites' content; and

scoring the advertiser's engagement with said user according to content relevance and time criteria.

3. The method of claim 2, wherein said receiving user ID comprises

communicating said user ID by a code embedded in the advertiser's website to a system database.

4. The method of claim 2, wherein said receiving user ID comprises

communicating said user ID by a code embedded in the advertiser's ad on the publisher's website to a system database.

5. The method of claim 2, wherein said receiving IDs of current visitors comprises communicating said visitors' user I Ds by a code embedded in the publisher's website to a system database.

6. The method of claim 2, wherein each one of said user ID and said visitor ID comprise a device ID and wherein the method further comprises identifying users and website visitors according to said device ID.

7. The method claim 6, wherein said device is one of a plurality of

devices and wherein the method further comprises identifying users and website visitors according to any one ID of said plurality of device.

8. The method of claim 2, wherein said analyzing comprises intent to buy analysis and points of interest analysis.

9. A system for optimizing advertisers' engagement comprising: a system server storing advertisers' and website visitors' databases; a plurality of advertisers' websites comprising advertiser's embedded code configured to communicate to the system server IDs of users to be contacted by the advertiser by call, email, sms, push etc.; a plurality of publisher's websites comprising publisher's embedded code configured to communicate to the system server IDs of website visitors; and

a plurality of publisher's websites hosting advertisers' banners comprising advertiser's embedded code configured to communicate to the system server IDs of website visitors to be contacted by the advertiser;

wherein said system server is configured to analyze said

communicated data and optimize engagement with users/customers, by manual or automatic operations.

10. The system of claim 9, wherein said analyzing comprises analyzing online activities and devices information.

11. The system of claim 10, wherein said websites and apps analysis

comprises using own generated data or 3^rd party data .

12. The system of claim 9, wherein said websites analysis comprises

analyzing surfed websites using machine learning, statistical and contextual algorithms.

13. The system of claim 10, wherein said device information comprises at least one of device type and device location.

14. The system of claim 10, wherein said analyzing comprises intent to buy and points of interest.

15. The system of claim 14, wherein said intent to buy analysis comprises correlating said websites and apps analysis with advertiser's content world.