JP7620596B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program, and in particular to technology for advertising planning.

A technology called user segmentation is known that extracts one or more users with similar characteristics as potential customers (target customers) to form a user segment. By using user segmentation, it is expected that the effectiveness of advertising can be maximized. Various technologies have been developed regarding the relationship between user segmentation and advertising.

For example, Patent Document 1 describes a technology for optimizing budget allocation for advertising placements. The document describes calculating a predicted conversion number for an advertisement based on a budget amount allocated to a group of users (user segment) that have common characteristics, and a predicted number of clicks and predicted CV (conversion) rate for the advertisement predicted based on the characteristics. Because the predicted conversion number is calculated for each group, it is possible to efficiently optimize budget allocation.

JP 2020-187697 A

The technology described in the above literature is effective in terms of optimizing advertising plans that take into account budgets, which are considered important in marketing. However, various marketing indicators, including budgets, are used in marketing strategies. Up until now, no method has been proposed for advertising plans that take into account all marketing indicators, not just the marketing indicator of budget.

The present invention was made in consideration of the above problems, and aims to provide technology for advertising planning according to the target setting of various marketing indicators.

In order to solve the above problem, one aspect of the information processing device according to the present invention includes a feature acquisition means for acquiring user features representing the characteristics of each of a plurality of users, a feature setting means for setting marketing features related to the provision of a predetermined advertisement, an estimation means for inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the predetermined advertisement for each of the plurality of users, a generation means for generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score, a goal setting means for setting a target value of a marketing indicator for the predetermined advertisement, and a determination means for determining one or more user groups to which the predetermined advertisement is to be provided from the plurality of user groups based on the target value of the marketing indicator.

In order to solve the above problem, one aspect of the information processing method according to the present invention includes a feature acquisition step of acquiring user features representing the characteristics of each of a plurality of users, a feature setting step of setting marketing features related to the provision of a predetermined advertisement, an estimation step of inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the predetermined advertisement for each of the plurality of users, a generation step of generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score, a goal setting step of setting a target value of a marketing indicator for the predetermined advertisement, and a determination step of determining one or more user groups to which the predetermined advertisement is to be provided from the plurality of user groups based on the target value of the marketing indicator.

In order to solve the above problem, one aspect of the program according to the present invention is an information processing program for causing a computer to execute information processing, the program causing the computer to execute processes including a feature acquisition process for acquiring user features representing the features of each of a plurality of users, a feature setting process for setting marketing features related to the provision of a predetermined advertisement, an estimation process for inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the predetermined advertisement for each of the plurality of users, a generation process for generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score, a goal setting process for setting a target value of a marketing indicator for the predetermined advertisement, and a determination process for determining one or more user groups to which the predetermined advertisement is to be provided from the plurality of user groups based on the target value of the marketing indicator.

According to the present invention, it becomes possible to carry out advertising planning in accordance with the target setting of various marketing indicators.
The above-mentioned objects, aspects, and advantages of the present invention, as well as objects, aspects, and advantages of the present invention not described above, will be understood by those skilled in the art from the following detailed description of the invention by referring to the accompanying drawings and the claims.

FIG. 1 shows an example of the configuration of an information processing system. FIG. 2 shows an example of a 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. As shown in FIG. FIG. 4 shows an example of a procedure for estimating an effectiveness score. FIG. 5 shows an example of a score table including effect scores. FIG. 6 shows an example of a procedure for determining a target segment. FIG. 7 shows a flowchart of the process executed by the information processing device.

Below, an embodiment for carrying out the present invention will be described in detail with reference to the attached drawings. Among the components disclosed below, those having the same functions are given the same reference numerals, and their description will be omitted. Note that the embodiment disclosed below is one example of a means for realizing the present invention, and should be appropriately modified or changed depending on the configuration of the device to which the present invention is applied and various conditions, and the present invention is not limited to the following embodiment. Furthermore, not all of the combinations of features described in this embodiment are necessarily essential to the solution of the present invention.

[Example of configuration of information processing system]
1 shows an example of the configuration of an information processing system according to the present embodiment. As an example, as shown in FIG. 1, this information processing system includes an information processing device 10 and multiple user devices 11-1 to 11-N (N>1) used by multiple arbitrary users 1 to N. In the following description, unless otherwise specified, the user devices 11-1 to 11-N may be collectively referred to as user device 11. In the following description, the terms user device and user are used synonymously, and the numbers 1 to N may be used as identification numbers (IDs) of users (user devices).

The user device 11 is, for example, a device such as a smartphone or a tablet, and is configured to be able to communicate 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). 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) equipped on the liquid crystal display. The operations include various operations on content such as images displayed on the screen, such as tapping, sliding, and scrolling using a finger or a stylus.
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. The user device 11 may also be provided with a separate display screen.

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

[Functional configuration of information processing device 10]
The information processing device 10 according to this embodiment predicts an effectiveness score indicating an advertising effectiveness for a plurality of users, using the user features and marketing features of the plurality of users acquired from the plurality of user devices 11-1 to 11-N, and the trained score prediction model 112. Then, the information processing device 10 determines a target segment, which is a group of users to which the advertisement is provided, based on the effectiveness scores for the plurality of users and the target values of the set marketing indicators.

FIG. 2 is a block diagram showing an example of a functional configuration of the information processing device 10 according to the present embodiment.
2 includes a user feature acquisition unit 101, a marketing feature acquisition unit 102, a marketing feature setting unit 103, a score estimation unit 104, a marketing index setting unit 105, a target segment determination unit 106, an output unit 107, a learning model storage unit 110, and a selection rule storage unit 120. The learning model storage unit 110 is configured to be capable of storing a user feature prediction model 111 and a score prediction model 112. Furthermore, the selection rule storage unit 120 is configured to be capable of storing a selection rule 121.

The user feature acquisition unit 101 acquires factual features (factual information, factual attributes) (hereinafter, user features) about each of the user devices 11-1 to 11-N regarding the user device or user. User features are factual features (information) that are actually or objectively obtained from the user device or user. The user feature acquisition unit 101 can acquire user features directly from the user device 11, for example. The user feature acquisition unit 101 can also acquire user features as information registered in a web service by the user of the user device 11.

User characteristics 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 user attributes such as gender, age, residential area, occupation, and family structure). User characteristics may also include a registration number and registered name when using a specified web service. User characteristics may also include call history, a delivery address other than the user's address for products when using a specified web service, usage status when using a specified web service, usage history, search history, item purchase history (including purchase results), and information regarding points that can be accumulated by using a service. In this way, user characteristics can include any information, including information related to the user device or the user himself/herself, and information regarding the use of a specified service via communication.

In this embodiment, the available items, such as purchases, can be tangible or intangible things (Things) that can be provided for various services. For example, for financial (fintech) services, there are items such as bank accounts, financial products such as stocks, investment trusts, and insurance products, cryptocurrency, and smartphone app payments. For digital content services, there are items such as video content such as movies and animations, and still image content such as photos, illustrations, and text. For e-commerce services, there are items such as intangible or tangible products handled in online shopping. For travel services, there are items such as information and reservations on hotels, package tours, and transportation. For mobile services, there are items such as mobile devices, public network/Internet connections, and communication usage fees. For advertising and media services, there are items such as offline and offline advertising products, direct mail, and advertising via broadcasting and the Internet. For card services, there are items such as credit card payments and point transactions. For sports and cultural services, there are items such as events such as sporting events and concerts, and products sold at events.

The user feature acquisition unit 101 is also configured to apply the acquired user features to the trained user feature prediction model 111 to acquire user features (estimated user features (attributes)) estimated for the user features. The user feature prediction model 111 is configured to receive the user features (i.e., fact features) of a target user as input, and output the probability (correspondence probability) that each of the multiple user features corresponds (matches) to the target user. The user feature acquisition unit 101 ultimately determines the estimated user features of the target user from the correlation probability.

For example, the user feature acquisition unit 101 inputs the target user's demographic information and data indicating past purchase history and preferences in web services into the user feature prediction model 111 as the user features of the target user. The user feature prediction model 111 outputs the probability for each of multiple items that the target user is estimated to purchase and multiple preferences that the target user may have as the relevant probability. The user feature acquisition unit 101 can then acquire items and preferences that have a probability equal to or greater than a predetermined value as the estimated user features of the target user.

The marketing feature acquisition unit 102 acquires marketing features related to the provision of advertisements as marketing features. The marketing feature acquisition unit 102 acquires marketing features associated with past user features acquired by the user feature acquisition unit 101. In this embodiment, the marketing features include channels used for the provision of advertisements and incentive data. The marketing features also include information (cost data) related to costs (expenses) corresponding to the channels used for the provision of advertisements.
for example,

A channel is a means for providing an advertisement. The channel includes, for example, at least one of electronic mail (E-mail), direct mail (DM), display advertisement, web banner advertisement (banner advertisement), and push notification. Display advertisement is advertisement on a display in general and includes text advertisement, responsive advertisement, dynamic display advertisement, and video advertisement, and banner advertisement is a type of display advertisement.
The incentive data is promotional material (incentives, bonus information) for encouraging actions (purchases and registrations) that the advertising provider expects in the advertisement. The incentives include at least one of coupons, points, and discount information (discount rates) that are granted (given) depending on the user's actions. The coupons may correspond to a predetermined amount of money. The points correspond to a number of points that can be accumulated according to predetermined rules on the web service. Accumulated points may be exchangeable for items or money depending on the number.
As mentioned above, the cost data is information regarding the cost corresponding to the channel used to provide the advertisement, and for example, if the channel is email, it is 0 yen, and if the channel is direct mail by mail, it is equivalent to postal charges.

The marketing feature setting unit 103 sets the marketing features to be estimated by the score estimation unit 104. The marketing features may be set by an 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 by any program stored in the storage unit (ROM 32 or RAM 33 in FIG. 3).

The score estimation unit 104 applies the user features acquired by the user feature acquisition unit 101 and the marketing features set by the marketing feature setting unit 103 to the trained score prediction model 112 to estimate an advertising effectiveness score (effectiveness score). The procedure for estimating the effectiveness score will be described later.

The marketing index setting unit 105 sets a target (target value) for one or more marketing indexes. The marketing index is, for example, at least one of a total budget, a return on investment (ROI), and a conversion rate (CVR). The ROI is a ratio (index) of the effect or profit achieved for the invested cost. The CVR is a ratio (index) of the number of accesses to the set advertisement site that led to a conversion such as registration, purchase, or application. The ROI and CVR can also be set for a target period.
The target value for the marketing index may be set by an 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 by any program stored in the storage unit (ROM 32 or RAM 33 in FIG. 3). Note that in this embodiment, the target for the marketing index is set as a target value, but the target is not limited to numerical information as long as it is information indicating the target.

The target segment determination unit 106 determines the final target segment based on the effect score estimated by the score estimation unit 104 and the target values for one or more marketing indicators set by the marketing indicator setting unit 105. In this embodiment, the target segment determination unit 106 performs a target segment determination process based on the selection rules 121 stored in the selection rule storage unit 120. The target segment determination procedure will be described later.

The output unit 107 outputs information on the target segment determined by the target segment determination unit 106. The output unit 107 may generate and output information on the target 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 displayed on a display unit (display unit 46 in FIG. 3).

[Hardware configuration of information processing device 10]
FIG. 3 is a block diagram showing an example of a hardware configuration of the information processing device 10 according to the present embodiment.
The information processing apparatus 10 according to the present embodiment can be implemented on any single or multiple computers, mobile devices, or any other processing platform.
3, the information processing device 10 is illustrated as being implemented in a single computer, but the information processing device 10 according to the present embodiment may be implemented in a computer system including multiple computers. The multiple computers may be connected to each other via a wired or wireless network so as to be able to communicate with each other.

3, the information processing device 10 may include a CPU 31, a ROM 32, a RAM 33, a HDD 34, an input unit 35, a display unit 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 generally controls the operations of the information processing device 10, and controls each of the components (32 to 37) via a system bus 38, which is a data transmission path.

The ROM (Read Only Memory) 32 is a non-volatile memory that stores control programs and the like necessary for the CPU 31 to execute processing. Note that the programs may be stored in a non-volatile memory such as a HDD (Hard Disk Drive) 34 or an SSD (Solid State Drive) or in an external memory such as a removable storage medium (not shown).
The RAM (Random Access Memory) 33 is a volatile memory and functions as a main memory, a work area, etc. of the CPU 31. That is, when executing a process, the CPU 31 loads necessary programs, etc. from the ROM 32 into the RAM 33 and executes the programs, etc. to realize various functional operations.

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

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. Various data, various parameters, etc. are transmitted and received between the external device and the communication I/F 37. In this embodiment, the communication I/F 37 may execute communication via a wired LAN (Local Area Network) or a dedicated line that complies with a communication standard 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 wireless PANs (Personal Area Networks) such as Bluetooth (registered trademark), ZigBee (registered trademark), and UWB (Ultra Wide Band). It also includes wireless LANs (Local Area Networks) such as Wi-Fi (Wireless Fidelity) (registered trademark) and wireless MANs (Metropolitan Area Networks) such as WiMAX (registered trademark). It also includes wireless WANs (Wide Area Networks) such as LTE/3G, 4G, and 5G. Note that the network only needs to be able to connect devices to each other and communicate with each other, and the communication standard, scale, and configuration are not limited to those described 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 be operated 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 of Fig. 3. That is, the user device 11 may include a CPU 31, a ROM 32, a RAM 33, a HDD 34, an input unit 35, a display unit 36, a communication I/F 37, and a system bus 38. The user device 11 can display various information provided by the information processing device 10 on the display unit 36 and perform processing corresponding to an input operation received from a user via a GUI (configured by the input unit 35 and the display unit 36).

[Effect score estimation procedure]
Next, a procedure for estimating the effectiveness score will be described. In this embodiment, the score estimation unit 104 estimates the effectiveness score by applying the user features acquired by the user feature acquisition unit 101 and the marketing features acquired by the marketing feature acquisition unit 102 to the trained score prediction model 112. The score prediction model 112 is a learning model for machine learning, and is, for example, a learning model based on CatBoost. Alternatively, the score prediction model 112 may be another boosting-based learning model such as XGBoost or LightGBM.

The score prediction model 112 has been trained using training data based on past user features acquired by the user feature acquisition unit 101 and past marketing features acquired by the marketing feature acquisition unit 102. To explain a specific example of the training process, information on the web service used and past advertising results (corresponding to purchase results) for the web service are prepared as past user features. In addition, the channel (such as direct mail) used in the purchase and incentive data (such as the presence or absence of a coupon) are prepared as past marketing features. Then, training data is prepared in which past purchase results (for example, 0: did not purchase, 1: purchased) are labeled for the set of the web service usage history and the past marketing features, and the score prediction model 112 is trained using the training data.

The trained score prediction model 112 is configured to take user features and marketing features including the target web service as input, and output an advertising effectiveness score (effectiveness score) indicating the likelihood that the user will make a purchase in the target web service. The effectiveness score is expressed as a value between 0 and 1, and in this embodiment, an effectiveness score of 1 indicates that the likelihood that the user will make a purchase in the web service is 100% (highest advertising effectiveness), and an effectiveness score of 0 indicates that the likelihood that the user will make a purchase in the web service is 0% (lowest advertising effectiveness). The trained score prediction model 112 is stored in the learning model storage unit 110.

If the web service is a shopping service such as an Internet mall, the advertising results correspond to purchase results, but the advertising results will differ depending on the web service. For example, the advertising results correspond to the results that the advertising provider intends as the final result, such as the result of registering for a specific service.

The score estimation unit 104 applies the user features and marketing features for each of the target users to the score prediction model 112 stored in the learning model storage unit 110, and estimates an effectiveness score for each of the users. In this embodiment, the score estimation unit 104 estimates effectiveness scores for users 1 to N. Figure 4 shows an example of the procedure for estimating an effectiveness score.

Figure 4 shows an example where the user ID is user 1. The user features 41 acquired by the user feature acquisition unit 101 include demographic information of user 1 (demographic user attributes such as gender, age, residential area, occupation, family structure, etc.), the service used by user 1 (= Internet mall), user 1's purchase history in that service, and estimated user features of user 1. As described above, the estimated user features of user 1 are user features estimated using the user feature prediction model 111 based on past user features acquired by the user feature acquisition unit 101.

The marketing feature setting unit 103 also sets the marketing feature 42. The set marketing features include the channel to be estimated, incentive data, and target web service. In the example of FIG. 4, the marketing feature 42 includes that the channel is direct mail, that there is no incentive, and that the target web service is an internet mall. Note that in the example of FIG. 4, the service used included in the user feature 41 and the target service included in the marketing feature 42 are both internet malls, but a web service different from the service used included in the user feature 41 may be set in the marketing feature 42.

The score estimation unit 104 inputs the user characteristics 41 and marketing characteristics 42 into the score prediction model 112, and estimates an effectiveness score 43 indicating the advertising effectiveness for the service used that is included in the user characteristics 41, i.e., the Internet mall.

Figure 5 shows an example of a score table 50 including the effect scores estimated by the score estimation unit 104 for users 1 to 3 out of users 1 to N. In the score table 50, the user ID 51 is obtained from the user feature (user feature 41 in the example of Figure 4) acquired by the user feature acquisition unit 101. The channel 52, incentive 53, and service 54 are obtained from the marketing feature set by the marketing feature setting unit 103 (marketing feature 42 in the example of Figure 4). Specifically, the user ID 51 indicates one of users 1 to 3. The channel 52, incentive 53, and service 54 are the channel, incentive, and target web service set to estimate the effect score 43, respectively. The effect score 55 is the effect score estimated by the score estimation unit 104 for each of users 1 to 3, and is indicated by a value between 0 and 1.

In the example of FIG. 5, in the case of user 2, if an advertisement for the Internet mall is provided by email and the incentive for purchase is set to a 500 yen coupon, the probability that user 2 will make a purchase from the Internet mall is 83% (0.83). On the other hand, even for the same user 2, if an advertisement for the Internet mall is provided by direct mail and the incentive for purchase is set to a 500 yen coupon, the probability that user 2 will make a purchase from the Internet mall is 20% (0.2). Note that the advertisement for the Internet mall may be an advertisement for the entire Internet mall, or an advertisement for a specific item handled by the Internet mall. In the case of an advertisement for a specific item, it may be specified based on user characteristics (including estimated user characteristics).

[Procedure for determining target segment]
When the score estimation unit 104 estimates the effect scores for users 1 to N, the target segment determination unit 106 performs a target segment determination process using the effect scores. The target segment determination procedure will be described with reference to Fig. 6. Fig. 6 shows an example of the target segment determination procedure. A score table 60 shows an example of a score table 60 including effect scores estimated for users 1 to N. The content included in the score table 60 is the same as that in Fig. 5.

To determine the target segment, the marketing indicator setting unit 105 first sets the target web service 61 and one or more marketing indicators 62. In this embodiment, the marketing indicators 62 are the total budget, ROI, and CVR. In the example of FIG. 6, the marketing indicator setting unit 105 sets the target web service 61 to be an Internet mall, with the total budget set to 1 million yen, ROI (%) set to 60, and CVR (%) set to 0.5. The marketing indicator setting unit 105 may appropriately set the priority of each marketing indicator, which indicates a marketing indicator that is particularly prioritized when determining the target segment among the marketing indicators. Here, the marketing indicator setting unit 105 may set the priority of the marketing indicators based on the type and content of the target web service.

Next, the target segment determination unit 106 generates multiple user segments based on the target web service, channel 52, and incentive 53 set by the marketing indicator setting unit 105. A user segment is a user group formed by grouping multiple users (prospective users) having an effectiveness score equal to or greater than a predetermined value (predetermined threshold) based on a common marketing feature (i.e., channel 52 and incentive 53). In the example of FIG. 6, user segments 63 to 65 are generated that have a common channel 52 and incentive 53. For example, user segment 63 is a group of users who have the common marketing feature of channel 52 = e-mail and incentive 53 = 500 yen coupon, and whose estimated effectiveness score 43 is 0.5 or more.

After generating the user segments, the target segment determination unit 106 applies the target values of the marketing indicators (total budget, ROI, and CVR) set by the marketing indicator setting unit 105 to the selection rules 121 to determine a combination of one or more user segments that satisfies the target values. In the example of FIG. 6, the total group of user segments 63 to 65 is determined as the final user segment, i.e., the target segment. The target segment determination unit 106 may determine the target segment based on the priority of each marketing indicator set by the marketing indicator setting unit 105. Specifically, if the target segment determination unit 106 cannot determine a target segment that satisfies all of the target values of the set marketing indicators, it may determine a target segment that satisfies the target value of the marketing indicator with the highest priority.

Here, we will explain a specific example of determining a target segment to meet the target values for the total budget, ROI, and each of the marketing indicators according to this embodiment.

In the case of a total budget, first, the target segment determination unit 106 calculates the incurred costs based on the costs of the marketing features (cost data) and incentives (incentive data) of each of any one or more user segments. Then, the target segment determination unit 106 may determine a combination of user segments (target segment) from the any one or more user segments such that the incurred costs are less than (equal to or less than) the target value of the set total budget.

In the case of ROI, the target segment determination unit 106 first calculates profit statistics such as the expected profit value obtained by applying the effectiveness score 43 of each user as a coefficient to the gross profit (profit) that each user of any one or more user segments can obtain by using the target web service, etc. The target segment determination unit 106 also calculates incurred costs based on the cost (cost data) and incentives (incentive data) of the marketing features of each of any one or more user segments. The target segment determination unit 106 may then determine a target segment from any one or more user segments such that the ratio of the profit statistics to the incurred costs exceeds (is equal to or exceeds) the set target value of ROI.

In the case of CVR, the target segment determination unit 106 may determine a target segment from any one or more user segments such that a statistical value based on the effectiveness score 43 of each user in each of the one or more user segments exceeds (is equal to or exceeds) the set target CVR value. The statistical value based on the effectiveness score 43 may be the value of the effectiveness score 43 itself or a numerical value derived from the effectiveness score 43.

In addition, when determining the target segment, the target segment determination unit 106 may apply a predetermined coefficient to various statistical values depending on the time when marketing is performed based on the assumption that various statistical values are dependent on the time, etc. In addition, the target segment determination unit 106 may determine or correct the statistical values of the profits of the user segment based on at least the factual characteristics of each user constituting the user segment.

Below we explain two specific examples of different scenarios for determining target segments.

(Example 1: Prioritizing low budgets)
The scenario of the first specific example is "when developing a web service for managing health of seniors, it is desirable to acquire new users with a low budget." In this case, for example, the marketing index setting unit 105 performs the following setting.
Target web service: Health management service for seniors Total budget: 0 yen ROI (%): Not set CVR (%): 0.5

Based on the setting, the target segment determination unit 106 selects a number of user segments to generate a target segment.
Based on the setting, the target segment determiner 106 can select marketing features (channels and incentives) and multiple user segments according to the selection rules 121 to determine the target segment.
First user segment: 30,000 users (channel: banner ads, incentive: none)
Second user segment: 30,000 users (channel: push notification, incentive: none)
Third User Segment: 40,000 users (Channel: Email, Incentive: None)
In this manner, since the set total budget is 0 yen, one or more user segments having a marketing characteristic with "no incentive" are selected.
The number of users in the first user segment to the third user segment and the total number of users can be determined by the target segment determination unit 106 so as to achieve a target CVR (=0.5%).

(Second concrete example: Achieving high CVR is the goal)
The scenario of the second specific example is "expecting a high CVR in an Internet mall, which is a web service." In this case, for example, the marketing index setting unit 105 performs the following setting.
Target web service: Internet mall Total budget: 50 million yen ROI (%): 30
CVR(%):15

Based on the setting, the target segment determination unit 106 can select multiple user segments and determine the target segment according to the selection rules 121 .
First user segment: 150,000 users (channel: DM, incentive: 1,000 coupons)
Second user segment: 200,000 users (channel: push notification, incentive: 500 coupon)
Third user segment: 50,000 users (Channel: Email, Incentive: 1,500 coupons)
The number of users in the first user segment to the third user segment and the total number of users can be determined by the target segment determination unit 106 so as to achieve the total budget (less than 50 million yen), the target ROI (= 35%), and the target CVR (= 15%).

[Process flow]
FIG. 7 shows a flowchart of the process executed by the information processing device 10 according to this embodiment. The process shown in FIG. 7 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 the explanation of FIG. 7, the information processing system shown in FIG. 1 will be referred to. It is assumed that the trained user feature prediction model 111 and score prediction model 112 are stored in the learning model storage unit 110. It is also assumed in this example that the target web service for determining the target segment is set in advance. It is also assumed that the order of the process shown in FIG. 7 is not limited to the order shown in FIG. 7.

In S71, the user feature acquisition unit 101 acquires user features of users 1 to N from the user devices 11-1 to 11-N. The user feature acquisition unit 101 may also acquire user features (estimated user features (attributes)) estimated for users 1 to N based on the user features using the user feature prediction model 111.

In S72, the marketing feature setting unit 103 sets the marketing features to be estimated by the score estimation unit 104. The marketing features according to this embodiment include a means (channel) for providing an advertisement and promotional materials (incentives) for promoting the behavior expected by the advertisement provider on the advertisement.

In S73, the marketing indicator setting unit 105 sets target values for one or more marketing indicators. In this embodiment, the marketing indicators include at least one of the total budget, ROI, and CVR.

In S74, the score estimation unit 104 estimates the effectiveness scores of users 1 to N for the set target web service. The score estimation unit 104 inputs the user characteristics and marketing characteristics acquired in S71 and S72 into the score prediction model 112, and estimates the effectiveness score for the target web service for each of users 1 to N. The effectiveness score estimation procedure is as described above with reference to FIG. 4.

In S75, the target segment determination unit 106 generates a user group as a user segment by grouping users (prospective users) whose effectiveness scores estimated in S74 are equal to or greater than a predetermined value (e.g., 0.5) by common marketing features (channels and incentives). Next, in S76, the target segment determination unit 106 determines one or more user segments as a target segment from the generated user segments in accordance with the selection rules 121 based on the target value of the marketing index set in S73. Here, as described above, the target segment determination unit 106 also determines the marketing features (channels and incentives) to be used in addition to the target segment.

Finally, in S77, the output unit 107 provides the advertisement to the target segment determined in S76. That is, the output unit 107 provides the advertisement to the target segment according to the marketing characteristics determined in S75.

In this way, according to this embodiment, by utilizing the advertising effectiveness scores predicted according to all combinations of advertising channel types and user characteristics, it is possible to optimize channels and user segments according to the target settings of various marketing indicators. Furthermore, according to this embodiment, it is possible to consider many advertising measures, including not only digital advertising but also analog advertising, as options, and it is possible to support decision-making for more flexible marketing measures.

Although specific embodiments have been described above, these embodiments are merely examples and are not intended to limit the scope of the present invention. The devices and methods described herein may be embodied in forms other than those described above. Furthermore, the above-described embodiments may be omitted, substituted, or modified as appropriate without departing from the scope of the present invention. Forms in which such omissions, substitutions, or modifications have been made are included within the scope of the claims and their equivalents, and belong to the technical scope of the present invention.

The disclosure of this embodiment includes the following configuration.
[1] An information processing device comprising: a feature acquisition means for acquiring user features representing user characteristics from each of a plurality of users; a feature setting means for setting marketing features related to the provision of a specified advertisement; an estimation means for inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the specified advertisement for each of the plurality of users; a generation means for generating a plurality of user groups from the plurality of users for each of the marketing features based on the effectiveness score; a goal setting means for setting a target value of a marketing indicator for the specified advertisement; and a determination means for determining one or more user groups to which the specified advertisement will be provided from the plurality of user groups based on the target value of the marketing indicator.

[2] The information processing device described in [1], characterized in that the user features include factual features about the user and estimated user features estimated based on the factual features.

[3] The information processing device described in [1] or [2], characterized in that the marketing features include a means for providing the specified advertisement and promotional materials for encouraging the behavior expected by the advertisement provider on the specified advertisement.

[4] The information processing device described in [3], characterized in that the means for providing the specified advertisement includes at least one of email, direct mail, display advertisement, web banner advertisement, and push notification.

[5] The information processing device described in [3] or [4], characterized in that the promotional material includes at least one of coupons, points, and discount information.

[6] The information processing device according to any one of [1] to [5], characterized in that the learning model is configured to output the effectiveness score such that the effectiveness score is 1 when the advertising effectiveness is the highest and the effectiveness score is 0 when the advertising effectiveness is the lowest.

[7] The information processing device described in any one of [1] to [6], characterized in that the generating means extracts one or more users whose effectiveness score is equal to or greater than a predetermined value from the plurality of users, and generates the plurality of user groups from the one or more users for each of the marketing features.

[8] The information processing device according to any one of [1] to [7], characterized in that the marketing index includes at least one of budget information for providing the advertisement, ROI (return on investment) expected from the advertisement, and CVR (conversion rate).

[9] The information processing device described in any one of [1] to [8], characterized in that the determination means determines the one or more user groups by applying a target value of the marketing index to a predetermined rule.

[10] The information processing device according to any one of [1] to [9], further comprising a providing means for providing the predetermined advertisement to the one or more user groups determined by the determining means.

[11] An information processing method comprising: a feature acquisition step of acquiring user features representing user characteristics from each of a plurality of users; a feature setting step of setting marketing features related to the provision of a predetermined advertisement; an estimation step of inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the predetermined advertisement for each of the plurality of users; a generation step of generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score; a goal setting step of setting a target value of a marketing indicator for the predetermined advertisement; and a determination step of determining, from the plurality of user groups, one or more user groups to which the predetermined advertisement is to be provided based on the target value of the marketing indicator.

[12] An information processing program for causing a computer to execute information processing, the program causing the computer to execute processes including a feature acquisition process for acquiring user features representing user features from each of a plurality of users, a feature setting process for setting marketing features related to the provision of a predetermined advertisement, an estimation process for inputting the user features and the marketing features into a trained learning model and estimating an effectiveness score indicating the advertising effectiveness of the predetermined advertisement for each of the plurality of users, a generation process for generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score, a goal setting process for setting a target value of a marketing indicator for the predetermined advertisement, and a determination process for determining one or more user groups to which the predetermined advertisement is to be provided from the plurality of user groups based on the target value of the marketing indicator.

1 to N: User, 10: Information processing device, 11-1 to 11-N: User device, 101: User feature acquisition unit, 102: Marketing feature acquisition unit, 103: Marketing feature setting unit, 104: Score estimation unit, 105: Marketing index setting unit, 106: Target segment determination unit, 107: Output unit, 110: Learning model storage unit, 111: User feature prediction model, 112: Score prediction model, 120: Selection rule storage unit, 121: Selection rule

Claims (13)

A feature acquiring means for acquiring user features representing characteristics of each of a plurality of users;
A feature setting means for setting marketing features related to the provision of a predetermined advertisement;
an estimation means for inputting the user characteristics and the marketing characteristics into a trained learning model and estimating an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generation means for generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score;
a target setting means for setting a target value of a marketing index for the predetermined advertisement;
a determining means for determining, from the plurality of user groups, one or more user groups to which the predetermined advertisement is to be provided based on a target value of the marketing index;
having
The target value of the marketing index includes a target value of a budget for providing an advertisement, a target value of a return on investment (ROI) for the advertisement, and a target value of a conversion rate (CVR) for the advertisement;
The information processing device is characterized in that the determination means calculates, for each of the multiple user groups, a budget for providing advertisements using the marketing features, a statistical value corresponding to ROI, and a statistical value corresponding to CVR, and determines one or more user groups among the multiple user groups for which the calculated budget is equal to or less than a target value of the budget, and the statistical value corresponding to the ROI and the statistical value corresponding to the CVR are equal to or greater than the target value of the ROI and the target value of the CVR . A feature acquiring means for acquiring user features representing characteristics of each of a plurality of users;
A feature setting means for setting marketing features related to the provision of a predetermined advertisement;
an estimation means for inputting the user characteristics and the marketing characteristics into a trained learning model and estimating an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generation means for generating a plurality of user groups by grouping users having an effectiveness score equal to or greater than a predetermined value for each marketing feature from the plurality of users;
a target setting means for setting a target value of a marketing index for the predetermined advertisement;
a determination means for calculating a value for the marketing index for each of the plurality of user groups, and determining, among the plurality of user groups, one or more user groups whose value for the marketing index is equal to or greater than a target value of the marketing index as one or more user groups to which the predetermined advertisement is to be provided;
having
The information processing device, wherein the target value of the marketing index includes at least one of a target value of ROI (Return on Investment) for an advertisement and a target value of CVR (Conversion Rate) for the advertisement. 3 . The information processing apparatus according to claim 1 , wherein the user features include factual features of the user and estimated user features estimated based on the factual features. 4 . 3. The information processing device according to claim 1, wherein the marketing features include a means for providing the predetermined advertisement and promotional materials for promoting a behavior expected by an advertisement provider on the predetermined advertisement. The information processing device according to claim 4 , wherein the means for providing the predetermined advertisement includes at least one of email, direct mail, display advertisement, web banner advertisement, and push notification. 5. The information processing apparatus according to claim 4 , wherein the promotional material includes at least one of a coupon, points, and discount information. The information processing device according to claim 1 or 2, characterized in that the learning model is configured to output the effectiveness score so that the effectiveness score is 1 when the advertising effectiveness is the highest and the effectiveness score is 0 when the advertising effectiveness is the lowest . The information processing device according to claim 1, characterized in that the generating means extracts one or more users whose effectiveness score is equal to or greater than a predetermined value from the plurality of users, and generates the plurality of user groups from the one or more users for each of the marketing features. 3. The information processing apparatus according to claim 1, further comprising a providing unit that provides the predetermined advertisement to the one or more user groups determined by the determining unit. An information processing method executed by an information processing device,
a feature acquisition step of acquiring user features representing features of each of the plurality of users;
a feature setting step for setting marketing features for a given advertisement presentation;
an estimation step of inputting the user characteristics and the marketing characteristics into a trained learning model to estimate an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generation step of generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score;
a target setting step of setting a target value of a marketing index for the predetermined advertisement;
a determination step of determining, from the plurality of user groups, one or more user groups to which the predetermined advertisement is to be provided based on a target value of the marketing index;
having
The target value of the marketing index includes a target value of a budget for providing an advertisement, a target value of a return on investment (ROI) for the advertisement, and a target value of a conversion rate (CVR) for the advertisement;
The information processing method is characterized in that, in the determination process, a budget for providing advertisements using the marketing features, a statistical value corresponding to ROI, and a statistical value corresponding to CVR are calculated for each of the multiple user groups, and one or more user groups are determined from among the multiple user groups for which the calculated budget is equal to or less than a target value of the budget, and the statistical value corresponding to the ROI and the statistical value corresponding to the CVR are equal to or greater than the target value of the ROI and the target value of the CVR . An information processing method executed by an information processing device,
A feature acquiring means for acquiring user features representing characteristics of each of a plurality of users;
a feature setting step for setting marketing features for a given advertisement presentation;
an estimation step of inputting the user characteristics and the marketing characteristics into a trained learning model to estimate an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generating step of grouping users having the effectiveness score equal to or greater than a predetermined value for each of the marketing features from the plurality of users to generate a plurality of user groups;
a target setting step of setting a target value of a marketing index for the predetermined advertisement;
a determination step of calculating a value for the marketing index for each of the plurality of user groups, and determining, among the plurality of user groups, one or more user groups whose value for the marketing index is equal to or greater than a target value of the marketing index as one or more user groups to which the predetermined advertisement is to be provided;
having
The information processing method, wherein the target value of the marketing index includes at least one of a target value of ROI (Return on Investment) for an advertisement and a target value of CVR (Conversion Rate) for the advertisement. An information processing program for causing a computer to execute information processing, the information processing program comprising:
A feature acquisition process for acquiring user features representing characteristics of each of a plurality of users;
a feature setting process for setting marketing features for a given advertisement offering;
an estimation process of inputting the user features and the marketing features into a trained learning model to estimate an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generation process for generating a plurality of user groups for each of the marketing features from the plurality of users based on the effectiveness score;
a target setting process for setting a target value of a marketing index for the predetermined advertisement;
a determination process for determining, from the plurality of user groups, one or more user groups to which the predetermined advertisement is to be provided, based on a target value of the marketing index ;
The target value of the marketing index includes a target value of a budget for providing an advertisement, a target value of a return on investment (ROI) for the advertisement, and a target value of a conversion rate (CVR) for the advertisement;
the determination process includes calculating, for each of the plurality of user groups, a budget for providing an advertisement using the marketing feature, a statistical value corresponding to an ROI, and a statistical value corresponding to a CVR, and determining, from among the plurality of user groups, one or more user groups for which the calculated budget is equal to or less than a target value of the budget, and the statistical value corresponding to the ROI and the statistical value corresponding to the CVR are equal to or greater than the target value of the ROI and the target value of the CVR.
Information processing program. An information processing program for causing a computer to execute information processing, the information processing program comprising:
A feature acquiring means for acquiring user features representing characteristics of each of a plurality of users;
a feature setting process for setting marketing features for a given advertisement offering;
an estimation process of inputting the user features and the marketing features into a trained learning model to estimate an effectiveness score indicating an advertising effectiveness of the predetermined advertisement for each of the plurality of users;
a generation process of grouping users having the effectiveness score equal to or greater than a predetermined value for each marketing feature from the plurality of users to generate a plurality of user groups;
a target setting process for setting a target value of a marketing index for the predetermined advertisement;
a determination process of calculating a value for the marketing index for each of the plurality of user groups, and determining, among the plurality of user groups, one or more user groups whose value for the marketing index is equal to or greater than a target value of the marketing index, as one or more user groups to which the predetermined advertisement is to be provided,
The target value of the marketing index includes at least one of a target value of ROI (Return on Investment) for the advertisement and a target value of CVR (Conversion Rate) for the advertisement;
Information processing program.

Images