JP2024001534A - Information processing apparatus, information processing method, and information processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To forecast prospective customers after a pre-set optional reference timing.

SOLUTION: An information processing apparatus according to the present invention has setting means for setting a reference timing and a target service, acquiring means for acquiring a user feature including factual feature including a user attribute of a user before the reference timing and a service use history of the target service after the reference timing, and prediction means for, based on the user feature and the service use history, predicting whether or not an optional target user different from the user can be a prominent customer who is expected to use the target service.

SELECTED DRAWING: Figure 2

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present invention relates to an information processing device, an information processing method, and an information processing program, and particularly relates to a technique for predicting prospective customers who are expected to use a service.

In order to maximize advertising effectiveness, it is important to appropriately extract prospective customers (target customers) who are expected to use the advertised service as a user group to which the advertisement is distributed. Patent Document 1 discloses a technique for predicting future purchasing trends of any user using machine learning. According to this document, it is possible to extract prospective customers based on the prediction result.

JP 2021-189983 Publication

In the above literature, the future purchasing trends of any user are predicted using past user behavior data. Specifically, the present time is set as a reference timing, and purchasing behavior after the reference timing is predicted. However, with the technique according to Document 1, it was not possible to predict purchasing behavior after an arbitrary reference timing in time, such as a future timing, and it was not possible to predict potential customers after the reference timing.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a technique for predicting potential customers after an arbitrary set reference timing.

In order to solve the above problems, one aspect of the information processing apparatus according to the present invention includes a setting means for setting a reference timing and a target service, a user characteristic including a factual characteristic including a user attribute of a user before the reference timing, an acquisition means for acquiring a service usage history of the target service after the reference timing; A prediction means for predicting whether or not a prospective customer is expected to use the target service.

In order to solve the above problems, one aspect of the information processing method according to the present invention includes a setting step of setting a reference timing and a target service, user characteristics including factual characteristics including user attributes of the user before the reference timing, and an acquisition step of acquiring the usage history of the target service after the reference timing, and based on the user characteristics and service usage history, an arbitrary target user different from the user becomes the target service after the reference timing. and a prediction step of predicting whether or not the customer is a prospective customer who is expected to use the service.

In order to solve the above problems, one aspect of a program according to the present invention is an information processing program for causing a computer to perform information processing, the information processing program setting a reference timing and a target service in the computer. a setting process to obtain user characteristics including factual features including user attributes of the user before the reference timing, an acquisition process to obtain a usage history of the target service after the reference timing, and the user characteristics and the service. a prediction process for predicting whether or not an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on usage history; It is something.

According to the present invention, it is possible to predict potential customers after a set arbitrary reference timing.
The objects, aspects, and effects of the present invention described above as well as the objects, aspects, and effects of the present invention not described above can be understood by those skilled in the art by referring to the accompanying drawings and claims. It can be understood from the form of

FIG. 1 shows an example of the configuration of an information processing system. FIG. 2 shows an example of the functional configuration of the information processing device 10 according to the embodiment. FIG. 3 shows an example of the hardware configuration of the information processing device 10 and the user device 11. FIG. 4A shows a conceptual diagram of the learning process of the purchase prediction model 112. FIG. 4B shows a conceptual diagram of purchase probability prediction processing by the purchase prediction model 112. FIG. 5A shows a schematic flow of purchase probability prediction processing by the prospective customer prediction unit 105. FIG. 5B shows a schematic flow of purchase probability prediction processing by the prospective customer prediction unit 105 when the configuration file 121 is used. FIG. 6 shows a flowchart of processing executed by the information processing device 10.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the accompanying drawings. Among the constituent elements disclosed below, those having the same functions are given the same reference numerals, and their explanations will be omitted. The embodiments disclosed below are examples of means for realizing the present invention, and should be modified or changed as appropriate depending on the configuration of the device to which the present invention is applied and various conditions. The present invention is not limited to this embodiment. Furthermore, not all combinations of features described in this embodiment are essential to the solution of the present invention.

[Configuration example of information processing system]
FIG. 1 shows a configuration example of an information processing system according to this embodiment. For example, as shown in FIG. 1, this information processing system includes an information processing device 10 and a plurality of user devices 11-1 to 11-N (N>1) used by arbitrary plurality of users 1 to N. ). Note that in the following description, the user devices 11-1 to 11-N may be collectively referred to as the user devices 11 unless otherwise specified. Furthermore, in the following description, the terms user device and user may be used interchangeably.

The user device 11 is, for example, a device such as a smartphone or a tablet, and is capable of communicating with the information processing device 10 via a public network such as LTE (Long Term Evolution) or a wireless communication network such as a wireless LAN (Local Area Network). It is composed of The user device 11 has a display unit (display surface) such as a liquid crystal display, and each user can perform various operations using a GUI (Graphic User Interface) provided on the liquid crystal display. The operation includes various operations on content such as an image displayed on the screen, such as a tap operation, a slide operation, and a scroll operation using a finger, a stylus, or the like.
Note that the user device 11 is not limited to the device shown in FIG. 1, but may be a device such as a tablet terminal or a notebook PC. Further, the user device 11 may be provided with a separate display screen.

The user device 11 can use a web service (Internet-related service) provided from the information processing device 10 or from another device (not shown) via the information processing device 10. The web services may include online malls, online supermarkets, communications, finance, real estate, sports, and travel reservation services provided via the Internet. In order to use the web service, the user device 11 collects the user's address, name, credit card number held by the user, and demographic information (such as gender, age, area of residence, occupation, family structure, etc.). Information such as demographic user attributes) can be registered.

[Functional configuration of information processing device 10]
The information processing device 10 according to the present embodiment sets a target service (target service) for predicting prospective customers. The information processing device 10 also determines a timing that is a standard for predicting potential customers (hereinafter referred to as a standard timing), a certain period (first period) before (past) the standard timing, and a period after the standard timing. Set a certain period (second period) in the (future). The information processing device 10 uses user data in the first period acquired from any user (target user) among the plurality of users 1 to N to calculate the purchase probability of the target user for the target service in the second period. Predict. The information processing device 10 further predicts whether the target user is a prospective customer based on the predicted purchase probability. In this embodiment, a prospective customer is a user who is expected to use a target service, and the target service is any web service or any item available to the user, and can be read as a target item. In this embodiment, "use" means "purchase", but may include any form of use such as registration and membership.

In this embodiment, the items available to the user may be tangible or intangible things that can be provided for various services. For example, regarding financial (FinTech) services, there are items such as bank accounts, financial products such as stocks, investment trusts, and insurance products, cryptocurrencies, and smartphone app payments. Regarding digital content services, there are items such as video content such as movies and anime, and still image content such as photographs, illustrations, and text. Furthermore, regarding e-commerce services, there are items such as intangible or tangible products that are handled through online shopping. Regarding travel services, there are items such as information and reservations regarding hotels, package tours, and transportation facilities. Furthermore, regarding mobile services, there are items such as mobile devices, public network/Internet connections, and communication charges. Regarding advertising and media services, there are items such as off-line and off-line advertising products, direct mail, and advertising via broadcasting and the Internet. Regarding card services, there are items such as credit card payments and point transactions. Regarding sports and cultural services, there are events such as sporting events and concerts, and items such as products sold at events.

FIG. 2 is a block diagram showing an example of the functional configuration of the information processing device 10 according to this embodiment.
The information processing device 10 shown in FIG. 2 includes a user data acquisition unit 101, a time information setting unit 102, a service setting unit 103, a user data selection unit 104, a potential customer prediction unit 105, an output unit 106, a learning model storage unit 110, and A file storage unit 120 is provided. The learning model storage unit 110 is configured to be able to store a user feature prediction model 111 and a purchase prediction model 112. Further, the file storage unit 120 is configured to be able to store the configuration file 121.

The user data acquisition unit 101 acquires data (user data) indicating characteristics (user characteristics) about the user device or user from each of the user devices 11-1 to 11-N. In this embodiment, the user data includes factual characteristics of the user and estimated characteristics of the user estimated based on the factual characteristics of the user.

Factual characteristics of a user are characteristics obtained from factual information about the user device and the user. For example, the user data acquisition unit 101 can directly acquire factual characteristics of the user from the user device 11. Further, the user data acquisition unit 101 can acquire factual characteristics of the user of the user device 11 as information registered in the web service. The factual characteristics of the user include factual attributes about the user device and the user (hereinafter referred to as user attributes). Further, the factual characteristics of the user may include tracking data (tracking log) and usage history data.

User attributes include the IP address of the user device, the user's address and name, the credit card number held by the user, and the user's demographic information (demographic information such as gender, age, area of residence, occupation, family structure, etc.) These are attributes related to the user himself, including attributes such as Further, the user attributes may include a registration number and a registered name when using a predetermined web service.

Tracking data is data obtained by tracking users' actions on a website for providing services (for example, multiple services including the target service) (data indicating actions on the website). be. Tracking data includes, for example, actions on the website, such as the number of clicks, the route taken to visit the site, the number of clicks on items on the site, or the viewing time of the site.

The usage history data includes service usage history (usage status, search history, item purchase history (including purchase results)) when a user uses a service (for example, a plurality of services including the target service). Usage history data may also include data such as the amount spent on services used, the number of items purchased, or the number of items registered. The usage history data may also include information regarding points that can be earned by using the web service.

The estimated features of the user are estimated (derived) from the factual features of the user. In this embodiment, the user data acquisition unit 101 can apply the factual features of the user to the trained user feature prediction model 111 to obtain the estimated features. The user feature prediction model 111 is configured to receive factual features of a target user as input, and to estimate and output the probability that each of a plurality of user features corresponds to (suits) the target user (probability of relevance). The user data acquisition unit 101 determines the estimated characteristics of the target user based on the applicable probability.

For example, the user data acquisition unit 101 inputs factual features of the target user into the user feature prediction model 111. The user characteristic prediction model 111 outputs, as corresponding probabilities, probabilities for each of a plurality of items that are estimated to be purchased by the target user and a plurality of preferences that the target user may have. Then, the user data acquisition unit 101 can acquire the estimated user attributes that correspond to items and preferences that have a probability of a predetermined value or higher, as the estimated characteristics of the target user.

Note that the estimated features of the user are not limited to features estimated for the future (ie, the future). A reference for feature estimation may be set before the present (that is, in the past), and the estimated features of the user after the reference may be estimated.

The time information setting unit 102 includes, as time information, a reference timing for predicting potential customers, a certain period (first period) after (the past) by the reference timing, and a certain period (in the future) before the reference timing. Set the period (second period). The time information may be set by the operator through an input operation using the input unit (input unit 35 in FIG. 3), may be set in advance in the system, or may be set in the storage unit (ROM 32 or RAM 33 in FIG. 3). It may be set by any program stored in .

The service setting unit 103 sets a service (target service) that is a target of prospective customer prediction. The target service may be set by the operator through an input operation using the input unit (input unit 35 in FIG. 3), may be set in advance in the system, or may be set in the storage unit (ROM 32 or RAM 33 in FIG. 3). It may be set by any program stored in .

The user data selection unit 104 is an optional function, and selects user data to be used for prediction processing by the prospective customer prediction unit 105 from the user data acquired by the user data acquisition unit 101. In this embodiment, the user data selection unit 104 can select user data based on the configuration file 121 stored in the file storage unit 120. The configuration file 121 will be described later.

The prospective customer prediction unit 105 uses the learned purchase prediction model 112 to predict and extract prospective customers. Specifically, the prospective customer prediction unit 105 uses user data in the first period acquired from any user (target user) among the plurality of users 1 to N to predict the target service in the second period. Predict the purchase probability of the target user. Then, the prospective customer prediction unit 105 predicts whether the target user is a prospective customer based on the purchase probability. Further, the prospective customer prediction unit 105 can generate a group (user segment) of prospective customers among the users 1 to N by predicting whether each of the users 1 to N is a prospective customer.

The output unit 106 outputs information on prospective customers predicted by the prospective customer prediction unit 105. The output unit 106 may generate and output information regarding the prospective customer. Further, the output unit 106 can generate and output (provide) an advertisement regarding the target service to the user segment. The output may be any output process, and may be output to an external device via a communication I/F (communication I/F 37 in FIG. 3), or may be output to a display unit (display unit 36 in FIG. 3). may be displayed.

The learning model storage unit 110 stores the trained user feature prediction model 111 described above. Furthermore, the learning model storage unit 110 stores a purchase prediction model 112. The purchase prediction model 112 will be described later.

The file storage unit 120 stores a configuration file 121. The configuration file 121 has setting information for each of a plurality of services for predicting potential customers. In the present embodiment, the configuration file 121 includes information indicating data necessary for predicting prospective customers for each service among the user data that can be acquired by the user data acquisition unit 101. The user data selection unit 104 can select user data necessary for predicting prospective customers for the target service from the user data acquired by the user data acquisition unit 101 according to the configuration file 121. As a result, only the user data necessary for predicting potential customers for the target service can be selected from the huge amount of data acquired by the user data acquisition unit 101, thereby saving data selection processing by the prospective customer prediction unit 105. This reduces the processing load.

The configuration file 121 according to this embodiment also includes settings for the purchase prediction model 112 for each service. For example, the configuration file 121 includes parameters to be used for the target service, a model to be used (such as CatBoost as described later), a structure of user data to be used, and the like. Thereby, the prospective customer prediction unit 105 can perform prospective customer prediction processing using the purchase prediction model 112 that is more suitable for the target service.

[Hardware configuration of information processing device 10]
FIG. 3 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to this embodiment.
The information processing apparatus 10 according to this embodiment can be implemented on any single or multiple computers, mobile devices, or any other processing platform.
Referring to FIG. 3, an example is shown in which the information processing device 10 is implemented in a single computer, but the information processing device 10 according to the present embodiment is implemented in a computer system including a plurality of computers. good. A plurality of computers may be connected to each other through a wired or wireless network so that they can communicate with each other.

As shown in FIG. 3, the information processing device 10 may include a CPU 31, a ROM 32, a RAM 33, an HDD 34, an input section 35, a display section 36, a communication I/F 37, and a system bus 38. The information processing device 10 may also include an external memory.
A CPU (Central Processing Unit) 31 centrally controls operations in the information processing device 10, and controls each component (32 to 37) via a system bus 38, which is a data transmission path.

The ROM (Read Only Memory) 32 is a nonvolatile memory that stores control programs and the like necessary for the CPU 31 to execute processing. Note that the program may be stored in a nonvolatile memory such as an HDD (Hard Disk Drive) 34 or an SSD (Solid State Drive), or an external memory such as a removable storage medium (not shown).
A RAM (Random Access Memory) 33 is a volatile memory and functions as a main memory, work area, etc. of the CPU 31. That is, the CPU 31 loads necessary programs and the like from the ROM 32 into the RAM 33 when executing processing, and implements various functional operations by executing the programs and the like. In this embodiment, the learning model storage unit 110 and the file storage unit 120 may be configured with the RAM 33.

The HDD 34 stores, for example, various data and information necessary when the CPU 31 performs processing using a program. Further, the HDD 34 stores various data, various information, etc. obtained by the CPU 31 performing processing using programs and the like.
The input unit 35 is composed of a pointing device such as a keyboard and a mouse.
The display unit 36 is composed of a monitor such as a liquid crystal display (LCD). The display section 46 may function as a GUI (Graphical User Interface) by being configured in combination with the input section 35.

The communication I/F 37 is an interface that controls communication between the information processing device 10 and external devices.
The communication I/F 37 provides an interface with a network and executes communication with an external device via the network. Via the communication I/F 37, various data, various parameters, etc. are transmitted and received with external devices. In this embodiment, the communication I/F 37 may perform communication via a wired LAN (Local Area Network) or a dedicated line that complies with communication standards such as Ethernet (registered trademark). However, the network that can be used in this embodiment is not limited to this, and may be configured as a wireless network. This wireless network includes a wireless PAN (Personal Area Network) such as Bluetooth (registered trademark), ZigBee (registered trademark), and UWB (Ultra Wide Band). It also includes wireless LAN (Local Area Network) such as Wi-Fi (Wireless Fidelity) (registered trademark) and wireless MAN (Metropolitan Area Network) such as WiMAX (registered trademark). Furthermore, it includes wireless WAN (Wide Area Network) such as LTE/3G, 4G, and 5G. Note that the network only needs to connect each device so that they can communicate with each other, and the communication standard, scale, and configuration are not limited to the above.

At least some of the functions of each element of the information processing device 10 shown in FIG. 2 can be realized by the CPU 31 executing a program. However, at least some of the functions of each element of the information processing device 10 shown in FIG. 2 may operate as dedicated hardware. In this case, the dedicated hardware operates under the control of the CPU 31.

[Hardware configuration of user device 11]
The hardware configuration of the user device 11 shown in FIG. 1 may be the same as that in FIG. 3. That is, the user device 11 can include a CPU 31 , a ROM 32 , a RAM 33 , an HDD 34 , an input section 35 , a display section 36 , a communication I/F 37 , and a system bus 38 . The user device 11 displays various information provided by the information processing device 10 on the display unit 36, and performs processing corresponding to input operations received from the user via the GUI (configured by the input unit 35 and the display unit 36). be able to.

[Procedure for predicting potential customers]
In this embodiment, the prospective customer prediction unit 105 applies the user data of the target user acquired by the user data acquisition unit 101 to the learned purchase prediction model 112 to predict the purchase probability. Then, the prospective customer prediction unit 105 predicts whether the target user is a prospective customer for the target service based on the purchase probability. Regarding the prospective customer prediction procedure, first, the purchase prediction model 112 will be explained, and then the purchase probability prediction process and the prospective customer prediction (extraction) process using the purchase prediction model 112 will be explained.

The purchase prediction model 112 is a learning model for machine learning (machine learning model), and is, for example, a learning model based on CatBoost. Alternatively, the purchase prediction model 112 may be another boosting-based learning model such as XGBoost or LightGBM.

The purchase prediction model 112 has been trained using learning data based on past user data (user data obtained in the past) acquired by the user data acquisition unit 101. The learning process of the purchase prediction model 112 will be explained with reference to FIG. 4A. FIG. 4A shows a conceptual diagram of the learning process of the purchase prediction model 112. A first period 41 before (past) the reference timing T1 and a second period 42 after (future) the reference timing T1 are set. For example, the first period 41 is one year, and the second period 42 is one month. The learning data includes usage history data (part of past user data) for user characteristics corresponding to past user data for any service (user data acquired in the first period 41) in the first period 41. Learning data obtained by labeling purchase results (for example, 0: not purchased, 1: purchased) corresponding to the service usage history (usage history, purchase history) obtained from the service is prepared. Then, the purchase prediction model 112 is trained using the learning data. Note that the reference timing T1, the first period 41, and the second period 42 are arbitrarily set in the learning stage. Note that the reference timing T1 (reference timing T1 in the learning data) that is set when making a purchase prediction includes, for example, not only temporal information such as the year, month, and day, but also information indicating events such as seasons and holidays. It may further include.

The purchase results reflected in the learning data through labeling refer to purchase results that can be confirmed from usage history data at least in the second period 42. Furthermore, the purchase results reflected in the learning data through labeling may refer to purchase results that can be confirmed from usage history data in a continuous period including at least the reference timing T1. Furthermore, the purchase results reflected in the learning data through labeling are the differences between the purchase results that can be confirmed from the usage history data in the first period 41 and the purchase results that can be confirmed from the usage history data in the second period 42 ( It may also refer to changes in purchasing status over time. Specifically, the purchase results reflected in the learning data through labeling are purchases based on the reference timing T1 based on the presence or absence of purchases in the first period 41 and the presence or absence of purchases in the second period 42. It may also refer to the presence or absence of positive changes in the situation over time. Here, if there is no purchase in the first period 41 and there is a purchase in the second period 42, the learning data is labeled positively, for example. Further, here, if there is no purchase in the first period 41 and there is a purchase in the second period 42, the learning data is negatively labeled, for example.

The learning data of the purchase prediction model 112 is based on the user characteristics in the first period 41, and the presence or absence of time-series changes (time changes) in the user characteristics from the first period 41 to the second period 42 with reference to the reference timing T1. may be labeled. For example, when the reference timing T1 is the user's birthday, the learning data considers that the age change of the user occurs based on the reference timing T1, and the user characteristics are set for the user characteristics in the first period 41. It may be labeled if there is a time-series change. The learning data may be labeled to indicate whether or not there is a time-series change in user characteristics for each attribute.

The learned purchase prediction model 112 inputs user data in the first period before an arbitrary reference timing and calculates the purchase probability (purchase score) for the set target service in the second period after the reference timing. is configured to output. The purchase probability is expressed as 0 to 1, and in this embodiment, when the purchase probability is 1, it means that there is a 100% possibility that the user will make a purchase in the target service, and when the purchase probability is 0, the user indicates that the probability of making a purchase in the target service is 0%. The learned purchase prediction model 112 is stored in the learning model storage unit 110.

Next, the process of predicting the purchase probability 55 using the purchase prediction model 112 will be described with reference to FIGS. 4B and 5A. FIG. 4B shows a conceptual diagram of the purchase probability prediction process by the purchase prediction model 112, and FIG. 5A shows a schematic flow of the purchase probability prediction process by the prospective customer prediction unit 105.

First, the prospective customer prediction unit 105 acquires the time information 52 set by the time information setting unit 102 and the target service 53 for prospective customer prediction set by the service setting unit 103. The time information 52 includes information on a reference timing T2, a first period 43, and a second period 44 shown in FIG. 4B. Further, the prospective customer prediction unit 105 acquires user data 51 in the first period 43 from among the user data acquired by the user data acquisition unit 101.

Subsequently, the prospective customer prediction unit 105 inputs the user data 51 into the purchase prediction model 112 and predicts the purchase probability 55 for the target service 53 in the second period 44 . Here, the purchase prediction model 112 used is a model learned based on the reference timing T2, the first period 43, and the second period 44. Alternatively, the purchase prediction model 112 to be used is a model selected based on the reference timing T2, the first period 43, and the second period 44. When the reference timing T2 is set before the current time (in the past), the purchase prediction model 112 that has already been learned based on the reference timing T2, the first period 43, and the second period 44 may be used. On the other hand, if the reference timing T2 is set after the present (in the future), there is substantially no learning data (that is, purchase results). In this case, for example, it is possible to select and use the purchase prediction model 112 that has already been learned based on the reference timing T2, the first period 43, and the second period 44 corresponding to the same date and time one year ago. can.

Note that the prospective customer prediction unit 105 predicts a plurality of purchase probabilities 55 of the target user based on the purchase prediction model 112 corresponding to each of the plurality of combinations of the reference timing T2, the first period 43, and the second period 44. , the final purchase probability 55 may be determined based on the plurality of purchase probabilities 55 predicted in each purchase prediction model 112. Here, the prospective customer prediction unit 105 predicts a plurality of purchase probabilities 55 with certain constraints imposed on the combination of the reference timing, the first period, and the second period. The constraints are based on predetermined timing such as advertisement provision timing, reference timing, first period, and second period. In addition, the constraints include, for example, a combination in which the second period includes timing that is the same as the advertisement provision timing.

In this way, by inputting the user data up to the reference timing T2, specifically, the user characteristics in the first period 43 into the purchase prediction model 112, it is possible to predict the user's purchase probability 55 in the second period 44. can.

By performing such purchase probability prediction processing on the users 1 to N, the prospective customer prediction unit 105 can predict the purchase probability 55 of the users 1 to N for the target service 53 in the second period 44. can.

When using the configuration file 121, purchase probability prediction processing can be performed more efficiently. FIG. 5B shows a schematic flow of purchase probability prediction processing by the prospective customer prediction unit 105 when using the configuration file 121. As described above, the configuration file 121 includes information indicating data necessary to predict potential customers for each service, and settings for the purchase prediction model 112 for each service. The prospective customer prediction unit 105 acquires user data 51 in the first period 43 and selects data necessary for predicting prospective customers for the target service 53 from the user data 51 according to the configuration file 121 (selection User data 54). Further, the prospective customer prediction unit 105 sets the purchase prediction model 112 for the target service 53 according to the configuration file 121.

If the target service 53 is, for example, a travel reservation service, the user data 54 selected according to the configuration file 121 includes the number of travel packages and hotel reservations, travel destinations, and travel costs in the first period 43. As described above, the user data 51 is a huge amount of data, but by using the configuration file 121, the user data 54 selected corresponding to the target service 53 can be input into the purchase prediction model 112.

When the purchase probability 55 is predicted, the prospective customer prediction unit 105 predicts the prospective customer based on the purchase probability 55. Specifically, the prospective customer prediction unit 105 predicts one or more users whose purchase probability 55 is equal to or higher than a predetermined threshold value as prospective customers (users who are expected to use the target service 53 (with a high probability of use)). can do. The threshold value is, for example, 0.5.

Further, the potential customer prediction unit 105 generates a user group consisting of one or more users predicted as potential customers as a user segment. Users included in the user segment have a high possibility of using the target service 53. Therefore, the prospective customer prediction unit 105 can determine the user segment as a user group suitable for the advertisement distribution target of the target service 53.

[Processing flow]
FIG. 6 shows a flowchart of processing executed by the information processing device 10 according to this embodiment. The process shown in FIG. 6 can be realized by the CPU 31 of the information processing device 10 loading a program stored in the ROM 32 or the like into the RAM 33 and executing it. For explanation of FIG. 6, reference will be made to the information processing system shown in FIG. It is assumed that the learned user feature prediction model 111 and purchase prediction model 112 are stored in the learning model storage unit 110. Further, the order of the processing in FIG. 6 is not limited to the illustrated order.

In S61, the time information setting unit 102 sets a reference timing for predicting potential customers, a (first period) after (the past) by the reference timing, and a certain period (the first period) before (the future) than the reference timing. 2 periods). The reference timing is not limited to the current timing, but can be set to any timing in the past or future.

In S62, the service setting unit 103 sets a service (target service 53) that is a target of prospective customer prediction. In this embodiment, a service is a web service or an item available to a user.

In S63, the user data acquisition unit 101 acquires user data from a user who is a target of potential customer prediction (target user). In this embodiment, as described above, the user data (user characteristics) includes factual characteristics of the user and estimated characteristics of the user estimated based on the factual characteristics of the user.

In S64, the prospective customer prediction unit 105 inputs the user data acquired in S63 to the purchase prediction model 112, and predicts the purchase probability 55 of the target user for the target service 53 set in S62. The purchase probability prediction process is as described above with reference to FIGS. 4B, 5A, and 5B.

In S65, the prospective customer prediction unit 105 determines whether the target user is a prospective customer (a user who is expected to use the target service 53) based on the purchase probability 55 of the target user predicted in S64. For example, if the purchase probability 55 is greater than or equal to a predetermined threshold, the prospective customer prediction unit 105 determines that the target user is a prospective customer.

The information processing device 10 performs the processes of S63 to S65 for users 1 to N. That is, the information processing device 10 performs the processes of S63 to S65 using each of the users 1 to N as target users. Next, in S66, the prospective customer prediction unit 105 generates a user group consisting of one or more of users 1 to N predicted as prospective customers as a user segment.

S67 is an optional process, and the output unit 106 provides the user segment generated in S66 with an advertisement regarding the target service 53 set in S62. for example. If the reference timing set in S61 is one month from now, the output unit 106 provides advertisements regarding the target service 53 to the user segment during a certain period before the reference timing. Providing the advertisement can effectively affect the purchasing behavior of the user segment after the reference timing.

As described above, according to the present embodiment, by considering time-series changes in user characteristics based on an arbitrarily set reference timing, it is possible to predict whether a user is a potential customer with higher accuracy. It can be carried out. In particular, user characteristics are likely to change through life events (marriage, childbirth, etc.), but in this embodiment, by considering chronological changes in user characteristics during a certain period before the reference timing, It becomes possible to effectively predict whether a user will become a potential customer (in the future).

In addition, in this embodiment, an example is shown in which "use" corresponds to "purchase", and the purchase prediction model 112 is used to predict the purchase probability 55, but the present embodiment can be applied to all types of usage. It is. That is, a usage prediction model corresponding to any type of usage may be used, and potential customers may be predicted according to the usage probability predicted by the usage prediction model.

Below, multiple use cases will be explained depending on the reference timing settings. For this explanation, reference will be made to the information processing system shown in FIG. 1, the conceptual diagram of the purchase probability prediction process shown in FIG. 4B, and the schematic flow of the purchase probability prediction process shown in FIG. 5A.

[First use case]
The first use case is a case where the reference timing T2 is set before the current time. In this use case, the reference timing T2 is set to the date of a past customer-attracting event, and the target service 53 is set to a service related to the area where the customer-attracting event was held. The prospective customer prediction unit 105 uses the learned purchase prediction model 112 to predict prospective customers for services related to the area in the second period 44 after the reference timing T2 among the plurality of users 1 to N. I can do it. The predicted prospective customer information can be utilized when a customer attraction event is held again in the area. For example, if an event to attract customers is held in the area in the future, it becomes possible to effectively plan the level of service availability for the area.

[Second use case]
The second use case is a case where multiple reference timings are set from the past to the future. In this use case, the reference timing T2 is set to the end of the epidemic of a plurality of infectious diseases, and the target service 53 is set to an Internet mall. The prospective customer prediction unit 105 uses the learned purchase prediction model 112 to predict prospective customers for the Internet mall among the plurality of users 1 to N in the second period 44 after each reference timing T2. I can do it. Information on predicted potential customers can be used to plan listings in accordance with the time when the infectious disease epidemic subsides. In other words, users' purchasing trends according to different convergence periods are quantified, making it possible to effectively plan listings on the Internet mall.

[Third use case]
The third use case is a case where the reference timing T2 is set after the current time. In this use case, the reference timing T2 is set to December 1 of this year (after the reference timing T2), and the target service 53 is set to the restaurant reservation service. The prospective customer prediction unit 105 uses the learned purchase prediction model 112 to predict potential customers for the restaurant reservation service in the second period 44 including Christmas, which is after the reference timing T2, among the plurality of users 1 to N. Can be predicted. That is, it is possible to predict whether or not the plurality of users 1 to N will become prospective customers for the restaurant reservation service in the future.

Note that although specific embodiments have been described above, these embodiments are merely illustrative and are not intended to limit the scope of the present invention. The apparatus and methods described herein may be embodied in forms other than those described above. In addition, appropriate omissions, substitutions, and changes may be made to the embodiments described above without departing from the scope of the present invention. Such omissions, substitutions, and modifications are included within the scope of the claims and their equivalents, and fall within the technical scope of the present invention.

The disclosure of this embodiment includes the following configurations.
[1] Setting means for setting a reference timing and a target service, user characteristics including factual characteristics including user attributes of the user before the reference timing, and service usage history of the target service after the reference timing. Prediction for predicting whether or not an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on the acquisition means to acquire, the user characteristics, and the service usage history. An information processing device comprising: means.

[2] The information processing device according to [1], wherein the user characteristics include estimated characteristics including the user attributes estimated based on the factual characteristics.

[3] According to [2], the user characteristics further include data indicating actions by the user on a website for providing a plurality of services including the target service, as factual characteristics. The information processing device described.

[4] From [1], the prediction means predicts whether or not the target user is the prospective customer by inputting the user characteristics and service usage history into a trained machine learning model. The information processing device according to any one of [3].

[5] Further comprising a generation means for generating a group of the prospective customers, the acquisition means acquires the user characteristics for each of the plurality of target users, and the prediction means further comprises a generation means for generating a group of the prospective customers, and the prediction means acquires the user characteristics for each of the plurality of target users. Predicting whether or not they are prospective customers, the generating means selects a group consisting of one or more target users among the plurality of target users predicted to be the prospective customers by the predicting means as the prospective customers. The information processing device according to [4], wherein the information processing device generates the information as a group.

[6] The information processing device according to [5], further comprising providing means for providing an advertisement regarding the target service to the group of prospective customers.

[7] Setting step of setting a reference timing and target service, user characteristics including factual characteristics including user attributes of the user before the reference timing, and service usage history of the target service after the reference timing. Prediction of predicting whether or not an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on the acquisition step and the user characteristics and service usage history. An information processing method comprising the steps of:

[8] An information processing program for causing a computer to execute information processing, the information processing program including a setting process for setting a reference timing and a target service in the computer, and a user's user information processing before the reference timing. Acquisition processing that acquires user characteristics including factual characteristics including attributes and service usage history of the target service after the reference timing; An information processing program for executing a process including a prediction process of predicting whether or not a target user is a prospective customer who is expected to use the target service after the reference timing.

1 to N: User, 10: Information processing device, 11-1 to 11-N: User device, 101: User data acquisition unit, 102: Time information setting unit, 103: Service setting unit, 104: User data selection unit, 105: Potential customer prediction unit, 106: Output unit, 110: Learning model storage unit, 111: User feature prediction model, 112: Purchase prediction model, 120: File storage unit, 121: Configuration file

Claims (8)

a setting means for setting a reference timing and a target service;
acquisition means for acquiring user characteristics including factual characteristics including user attributes of the user before the reference timing, and service usage history of the target service after the reference timing;
Prediction means for predicting whether or not an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on the user characteristics and service usage history;
An information processing device comprising: The information processing apparatus according to claim 1, wherein the user characteristics include estimated characteristics including the user attributes estimated based on the factual characteristics. The information according to claim 2, wherein the user characteristics further include data indicating actions by the user on a website for providing a plurality of services including the target service, as factual characteristics. Processing equipment. The information according to claim 1, wherein the prediction means predicts whether the target user is the prospective customer by inputting the user characteristics and service usage history into a trained machine learning model. Processing equipment. further comprising generating means for generating the group of prospective customers,
The acquisition means acquires the user characteristics for each of the plurality of target users,
The prediction means predicts whether each of the plurality of target users is the potential customer,
The generating means generates, as the prospective customer group, a group consisting of one or more of the target users among the plurality of target users predicted to be the prospective customers by the prediction means. The information processing device according to claim 1. The information processing apparatus according to claim 5, further comprising providing means for providing an advertisement regarding the target service to the group of potential customers. a setting process for setting reference timing and target services;
an acquisition step of acquiring user characteristics including factual features including user attributes of the user before the reference timing, and service usage history of the target service after the reference timing;
a prediction step of predicting whether an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on the user characteristics and service usage history;
An information processing method characterized by having the following. An information processing program for causing a computer to perform information processing, the information processing program causing the computer to:
Setting process for setting reference timing and target service;
acquisition processing for acquiring user characteristics including factual features including user attributes of the user before the reference timing, and service usage history of the target service after the reference timing;
Prediction processing for predicting whether or not an arbitrary target user different from the user is a prospective customer who is expected to use the target service after the reference timing, based on the user characteristics and service usage history. It is intended to carry out
Information processing program.

Images