JP7544916B1 - Discounted item setting device, discounted item setting method, and program - Google Patents

Abstract

The present invention provides a discount product setting device that can design discount products suitable for new users and improve the expected profits of subscription service providers.
[Solution] In the setting system 100, an acquisition unit of the setting device 1 acquires user information based on identification information of the terminal 2, a first extraction unit extracts two or more candidate discounted product information from the user information and purchasing probability information, a second extraction unit extracts candidate discounted product information that matches the user's needs from the candidate discounted product information based on the candidate service contract period and candidate service contract price of each candidate discounted product information as selected discounted product information, a calculation unit calculates the expected profit to be earned from the user's contract to cancellation for each selected discounted product information based on the selected discounted product information and past user cancellation information, and a third extraction unit extracts recommended discounted product information to be presented to the user from the selected discounted product information based on the expected profit.
[Selected Figure] Figure 1

Description

The present invention relates to a device for setting discounted items, a method for setting discounted items, and a program.

In various services such as subscription services, various methods are used for sales promotion, such as the presentation of time-limited coupons, in order to acquire new users. Patent Document 1 describes how a rebate value is set according to the user's reaction when a rebate value according to user information is presented.

JP 2021-163046 A

However, when the rebate value is corrected using the reaction to the rebate value, the process of checking the user's reaction is required multiple times. This makes it difficult to use this method to acquire new users. In addition, when the rebate value is set based on the reaction of the user, there is a problem that the expected profit for the subscription service provider tends to be low.

The present disclosure therefore aims to provide a device for setting discounted products in a subscription service that can design discounted products suited to users, even for new users, and can improve the expected profits of subscription service providers.

In order to achieve the above object, the present disclosure provides a device for setting discounted items in a subscription service, comprising:
The apparatus includes an acquisition unit, a first extraction unit, a second extraction unit, a calculation unit, and a third extraction unit,
The acquisition unit acquires user information,
The first extraction unit extracts two or more pieces of candidate discount product information from the user information and the purchase probability information,
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction unit extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
the calculation unit calculates an expected profit to be obtained from the user's contract to cancellation for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
The third extraction unit extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit.

The disclosed method includes a computer-implemented method for setting discounted items in a subscription service, the method comprising:
The method includes an acquisition step, a first extraction step, a second extraction step, a calculation step, and a third extraction step,
In the acquiring step, user information is acquired,
In the first extraction step, two or more pieces of candidate discounted product information are extracted from the user information and purchase probability information;
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction step extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information as selected discount product information;
In the calculation step, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction step, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit.

A program according to the present disclosure is a program for causing a computer to execute an acquisition process, a first extraction process, a second extraction process, a calculation process, and a third extraction process,
In the acquisition process, user information is acquired,
In the first extraction process, two or more pieces of candidate discounted product information are extracted from the user information and the purchase probability information;
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction process extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
In the calculation process, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction process, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit.

This disclosure makes it possible to design discounted products that are suitable for new users and improve the expected profits of subscription service providers.

FIG. 1 is a block diagram showing an example of a design system including a design apparatus according to the first embodiment. FIG. 2 is a block diagram illustrating an example of a hardware configuration of the design apparatus according to the first embodiment. FIG. 3 is a flowchart showing an example of a design method and program according to the first embodiment. FIG. 4 is a block diagram showing an example of a design system including a design apparatus according to the second embodiment. FIG. 5 is a flowchart showing an example of a design method and program according to the second embodiment.

Hereinafter, the present disclosure will be described in detail with reference to the drawings, giving examples. However, the present disclosure is not limited by the following description. In addition, in the following Figures 1 to 5, the same parts may be given the same reference numerals, and their description may be omitted. In addition, in the drawings, for the convenience of explanation, the structure of each part may be appropriately simplified, and the dimensional ratio of each part may be shown diagrammatically, different from the actual one. In addition, each embodiment and description may refer to each other, unless otherwise specified. In addition, when the expression "~" is used in this specification, it is used to mean including the numerical value or physical value before and after it. In addition, in this specification, the expression "A and/or B" includes "A only", "B only", and "both A and B".

(Embodiment 1)
This embodiment is an example of a setting system including a setting device of the present disclosure. As shown in FIG. 1, a setting system 100 of this embodiment includes a setting device 1. The setting device 1 includes an acquisition unit 11, a first extraction unit 12, a second extraction unit 13, a calculation unit 14, and a third extraction unit 15. As shown in FIG. 1, in the setting system 100, the setting device 1 can be connected (communicated) in one or both directions with a user's terminal 2 via an authentication server (not shown, a server of a newspaper publication site described later) outside the system and a communication line network 3. The number of terminals 2 that can be connected to the setting device 1 may be one, or may be multiple as shown in FIG. 1. In the first embodiment, the setting device 1 is configured as a server.

The setting device 1 of this embodiment may be incorporated into a personal computer (PC) in which the program disclosed herein is installed, or into a server or the like as a system. The setting device 1 of this embodiment may also be a system consisting of one or more computers or servers capable of executing the program disclosed herein, i.e., a cloud computing system. The personal computers may form a computer cluster. Although not shown, the setting device 1 may be configured to be connectable to an external terminal of a system administrator via the authentication server and communication line network 3, so that the system administrator can manage the setting device 1 from the external terminal. In this embodiment, the setting system 100 includes one setting device 1, but may include multiple setting devices.

Examples of terminal 2 include PCs; mobile terminals such as mobile phones, smartphones, and tablet terminals; smart watches, smart glasses, and wearable terminals; etc.

The communication network 3 is not particularly limited and may be a publicly known network, for example, wired or wireless. Examples of the communication network 3 include the Internet line, the World Wide Web (WWW), a telephone line, a Local Area Network (LAN), and Wi-Fi (Wireless Fidelity).

Figure 2 shows an example block diagram of the hardware configuration of the setting device 1. The setting device 1 has, for example, a CPU (Central Processing Unit) 101, which is a computing element, a memory 102, a bus 103, a storage device 104, an input device 109, a display 110, a communication device (communication unit) 111, and the like. Each part of the setting device 1 is connected via the bus 103 by its respective interface (I/F).

The CPU 101 cooperates with other components through a controller (system controller, I/O controller, etc.) and controls the entire setting device 1. In the setting device 1, the CPU 101 executes the program 105 of the present disclosure and other programs, and also reads or writes various information. Specifically, in this embodiment, the CPU 101 functions as an acquisition unit 11, a first extraction unit 12, a second extraction unit 13, a calculation unit 14, and a third extraction unit 15. The setting device 1 includes the CPU 101 as a calculation device (calculation element), but may also include other calculation devices such as a GPU (Graphics Processing Unit) or an APU (Accelerated Processing Unit), or may include a combination of the CPU and these. Note that the CPU 101 functions as each unit other than the storage unit in other embodiments, for example.

The memory 102 includes a main memory. The main memory is also called a primary storage device. When the CPU 101 performs processing, the memory 102 reads various operating programs, such as the program 105 of the present disclosure, stored in the storage device 104 (auxiliary storage device) described below. The CPU 101 then reads data from the memory 102, decodes it, and executes the program. The main memory is a RAM (random access memory). The memory 102 may further include a ROM (read only memory).

The bus 103 can also be connected to external devices. Examples of the external devices include an external storage device (external database, etc.) and a printer. The setting device 1 can be connected to a communication network 3, for example, by a communication device 111 connected to the bus 103, and can also be connected to external devices such as a terminal 2 via the communication network 3.

The storage device 104 is also referred to as an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operating program including the program 105 of the present disclosure, and data including user information 106, purchase probability information 107, and cancellation information 108. The storage device 104 includes, for example, a storage medium and a drive for reading and writing data from and to the storage medium. The storage medium is not particularly limited, and may be either built-in or external, and examples of the storage medium include HD (hard disk), FD (floppy disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc., and the drive is not particularly limited. The storage device 104 may be, for example, a hard disk drive (HDD) in which the storage medium and the drive are integrated.

The setting device 1 further includes an input device 109 and a display 110 which is an output device. Examples of the input device 109 include pointing devices such as a touch panel, a track pad, and a mouse; a keyboard; an imaging means such as a camera or a scanner; a card reader such as an IC card reader or a magnetic card reader; and a voice input means such as a microphone. Examples of the display 110 include display devices such as an LED (light emitting diode) display and a liquid crystal display. In this embodiment, the input device 109 and the display 110 are configured separately, but the input device 109 and the display 110 may be configured as an integrated device, such as a touch panel display. In addition, the input device 109 and the display 110 in the setting device 1 may be configured as desired, and may be absent or may include one or more of them.

Next, an example of processing in the setting system 100 of this embodiment will be described with reference to the flowchart in FIG. 3, taking as an example a case where a user uses a terminal 2 to access a site that lists online newspapers that can be purchased as subscription services, and sets discounted items for the subscription service for the user. As shown in FIG. 3, the setting method and program of embodiment 1 performs the processes of S1 (acquisition), S2 (first extraction), S3 (second extraction), S4 (calculation), and S5 (third extraction) in this order.

Prior to processing by the setting device 1, first, the user uses terminal 2 to access the newspaper site. The server (not shown) of the newspaper site receives identification information or authorization information of terminal 2, such as a cookie of terminal 2, from terminal 2. The server of the newspaper site transmits the identification information of terminal 2 to the setting device 1.

Next, the process in the setting device 1 is started. After receiving the identification information of the terminal 2, the acquisition unit 11 acquires user information based on the identification information of the terminal 2 (S1). Specifically, the acquisition unit 11 compares the user information 106 stored in the storage device 104 with the identification information of the terminal 2. The user information 106 is linked to the identification information of the user who accessed the newspaper publication site. The user information 106 includes the user's contract type (e.g., the presence or absence of a subscription contract, the type of contract (monthly contract, annual contract, etc.), the period since the start of the contract, whether or not the user is a trial member, etc.), the user's attributes, and the user's behavior history (e.g., the browsing history of articles on the newspaper publication site, the number of articles viewed, the frequency of visits, the number of articles saved, etc.). If there is user information 106 linked to the identification number of the terminal 2, the acquisition unit 11 acquires the user information 106 linked to the identification number of the terminal 2 as the user information of the terminal 2.

Next, the first extraction unit 12 extracts two or more candidate discounted product information from the user information 106 and the purchase probability information 107 (S2). That is, in step S2, multiple candidates of discounted products of the subscription service that can be presented to the user of the terminal 2 are extracted (generated) from the user information 106 and the purchase probability information 107 based on the past subscription service contract. The purchase probability information 107 is linked to past user information, the service contract period, the service contract price, and the purchase probability distribution. The purchase probability information 107 is generated (constructed) from information of users (past users) who have previously signed a subscription service contract, the service contract period of the past users, and the service contract price of the past users, and a purchase probability distribution generated based on the service contract period of the past users and the service contract price of the past users. Therefore, by using the purchase probability information 107, the first extraction unit 12 can extract the service contract period, service contract price, and purchase probability for the service contract period and service contract price of a past user who is the same as or similar to the user of the terminal 2. The first extraction unit 12 can then use these to generate (extract) candidate discounted product information that includes multiple pieces of information that link candidate service contract periods with candidate service contract prices and purchase probabilities for each candidate service contract period. Note that the purchase probability information 107 can be updated based on the presence or absence of a new subscription contract for the user of the terminal 2 and the content of the new contract, as described below.

Specifically, in step S2, the first extraction unit 12 compares the user information 106 of the terminal 2 acquired in step S1 with past user information in the purchase probability information 107. If past user information matching the user information 106 exists, the first extraction unit 12 extracts purchase probability information linked to the past user information. On the other hand, if past user information matching the user information 106 does not exist, the first extraction unit 12 removes some of the conditions of the user information 106 and performs a similar comparison, extracting purchase probability information 107 linked to past user information corresponding to the user information 106.

The purchase probability distribution included in the extracted purchase probability information is linked to the subscription service contract period, the subscription contract price, and the purchase probability. Therefore, in step S2, the first extraction unit 12 refers to the extracted purchase probability information and calculates the user's purchase probability when the service contract period and the service contract price are set from the randomly determined service contract period and the service contract price in the service contract period. Then, the first extraction unit 12 sets the service contract period as a candidate service contract period and the service contract price as a candidate service contract price, and generates a set of data linked to the obtained purchase probability (for example, set 1 "1 month, 4000 yen/month, 30%", "6 months, 3000 yen/month, 50%", "12 months, 2150 yen/month, 70%", set 2 "1 month, 4000 yen/month, 30%", "6 months, 3500 yen/month, 35%", "12 months, 3050 yen/month, 60%", etc.). In step S2, the first extraction unit 12 repeatedly generates the data until the number of sets specified in advance is reached. The specified number of sets is, for example, a number that can be confirmed when presented to the user, for example, 1 to 10, and preferably 2 to 3. The first extraction unit 12 then extracts the obtained sets of data as candidate discounted product information. The first extraction unit 12 then repeats the same process to extract two or more pieces of candidate discounted product information. Note that in step S2, the candidate service contract period and the candidate service contract price are randomly determined, but the present disclosure is not limited to this, and multiple contract periods and contract prices specified in advance may be used as the candidate service contract period and the candidate service contract price. Also, in step S2, for example, multiple contract periods and contract prices may be set within the range of the contract period and contract price specified in advance, and the set contract period and contract price may be used as the candidate service contract period and the candidate service contract price.

Next, in step S3, the second extraction unit 13 extracts candidate discounted product information that matches the user's demand from the candidate discounted product information based on the candidate service contract price and purchase probability of each candidate discounted product information as selected discounted product information. In step S3, the candidate discounted product information is extracted based on the past user information. The candidate discounted product information includes a combination of a plurality of service contract periods and service contract periods, but a plurality of combinations may not necessarily match the user's demand. For example, when comparing a plurality of service contract prices and purchase probabilities, if the service contract price increases but the purchase probability of the higher service contract price is the same as or higher than the purchase probability of the lower service contract price, the user is unlikely to select such a candidate discounted product, and does not match the user's demand. Therefore, in step S3, candidate discounted product information that matches the user's demand is selected.

Specifically, in step S3, the second extraction unit 13 extracts, as selected discounted product information, candidate discounted product information having a combination of candidate service contract price and purchase probability in which the purchase probability becomes relatively low when the candidate service contract price becomes relatively high in each piece of candidate discounted product information. Note that the second extraction unit 13 can also extract, as selected discounted product information, candidate discounted product information having a combination of candidate service contract period and purchase probability in which the purchase probability becomes relatively high when the candidate service contract price becomes relatively low in each piece of candidate discounted product information.

Next, in step S4, the calculation unit 14 calculates the expected profits to be obtained from the user's contract to cancellation for each selected discounted product information from the selected discounted product information and the past user cancellation information 108. In step S3, the profits for the subscription service provider are not taken into consideration. On the other hand, the user cancellation information 108 used in step S4 is linked to the past user information, the service contract period, the service contract price, and the service cancellation rate. The user cancellation information 108 is generated (constructed) from the past user information, the user's service contract period, and the user's service contract price, and the service cancellation rate generated based on the past user's service contract period and the past user's service contract price. Therefore, in step S4, the user cancellation information 108 such as the past user's service cancellation rate is used to calculate the expected profits that the subscription service provider may be able to obtain for each candidate discounted product information selected as matching the user's demand. As a result, in step S5 described below, the subscription service provider can select recommended discounted product information that will have a relatively large expected profit based on the calculated expected profit.

Specifically, in step S4, the user information is compared with past user information in the user cancellation information 108. If past user information matching the user information exists, the calculation unit 14 extracts the cancellation information 108 of the user linked to the past user information. On the other hand, if past user information matching the user information does not exist, the calculation unit 14 performs the comparison in the same manner, excluding some conditions of the user, and extracts the cancellation information 108 of the user linked to the past user information corresponding to the user information. The cancellation information 108 includes the service contract period of the user and the service contract price of the user, and the service cancellation rate of the user linked to the service contract period of the user and the service contract price of the user. Therefore, the calculation unit 14 extracts the cancellation rate of the user corresponding to the selected discounted product information using the service contract period of the user and the service contract price of the user included in the selected discounted product information and the extracted cancellation information of the user. Then, the calculation unit 14 calculates the expected profit using the service cancellation rate corresponding to the selected discounted product information. The expected profit can be the profit (sales) expected in the future when the user enters into a contract, and can be calculated by a known financial engineering method for calculating future expected profits. As a specific example, the expected profit can be calculated by, for example, the following formula (1). The following formula (1) can also be the expected profit when the period (horizon) considered in the profit calculation is assumed to be infinite, the user cancellation rate is constant, and the discount rate for future cash flows is not considered. The discount rate means a value for calculating the present value (profit) when the profit to be received in the future is received in the present. The discount rate can also be, for example, a discount rate. The discount rate can be set according to, for example, the official discount rate, the interest rate of 10-year Japanese government bonds, the Tokyo Stock Price Index (TOPIX), the growth rate of the subscription service provider, etc.

(Expected revenue) = 1 / service cancellation rate × candidate service contract price × purchase probability / candidate service contract period ... (1)

The expected profit may be calculated, for example, by the following formula (2): The following formula (2) can also be regarded as the expected profit when it is assumed that the period (horizon) considered in the profit calculation is finite, the user churn rate is constant, and the discount rate for future cash flows is not taken into account.

(Expected revenue) = sum [t = 0 to Horizon] {(1 - service churn rate) x candidate service contract price x purchase probability / candidate service contract period} ... (2)
t: number of months passed

The expected profit may be calculated, for example, by the following formula (3): The following formula (3) can also be regarded as the expected profit when the period (horizon) considered in the profit calculation is infinite, the user churn rate is constant, and a discount rate for future cash flows is taken into account.

(Expected revenue) = 1 / (service cancellation rate + discount rate for future cash flows) × candidate service contract price × purchase probability / candidate service contract period ... (3)

The expected profit may be calculated, for example, by the following formula (4): The following formula (4) can also be regarded as the expected profit when the period (horizon) considered in the profit calculation is finite, the user churn rate is constant, and the discount rate for future cash flows is taken into account.

(Expected revenue) = sum [t = 0 to Horizon] {(1 - service cancellation rate - discount rate for future cash flows) x candidate service contract price x purchase probability / candidate service contract period} ... (4)
t: number of months passed

In step S4, an example was given in which the cancellation information 108 includes a service cancellation rate, but the cancellation information 108 may include a service continuation rate in addition to or instead of the service cancellation rate. In this case, the service cancellation rate used to calculate the expected profit can be calculated as 1 - service continuation rate.

Then, in step S5, the third extraction unit 15 extracts recommended discounted product information to be presented to the user from the selected discounted product information based on the expected profit. Specifically, in step S4, the expected profit is calculated for each recommended discounted product information using two or more candidate service contract periods, and the candidate service contract price and purchase probability for each candidate service contract period. Therefore, in step S5, the sum of two or more expected profits calculated from each recommended discounted product information is calculated as the expected profit for each recommended discounted product information. Then, the third extraction unit 15 extracts selected discounted product information having the maximum expected profit from the expected profits of each selected discounted product information as the recommended discounted product information. Then, the setting device 1 ends the processing. Note that the third extraction unit 15 extracts the recommended discounted product information using the sum of the expected profits of the selected discounted product information, but the present disclosure is not limited to this, and it is sufficient to extract selected discounted product information with a relatively high expected profit. The third extraction unit 15 may extract the recommended discounted product information, for example, by using the average expected profit of the selected discounted product information.

In the setting device 1 of the first embodiment, the first extraction unit 12 and the second extraction unit 13 use the past user information and purchase probability information of the subscription service to evaluate the purchasing behavior of a new user and extract candidate discounted product information to be presented to the new user, and further extract the candidate discounted product information that matches the user's needs as selected discounted product information. Therefore, the setting device 1 can design discounted products suitable for new users as well. On the other hand, in the setting device 1, the calculation unit 14 and the third extraction unit 15 use the cancellation information of past users to select selected discounted product information with high expected profits for the subscription service provider from the selected discounted product information as recommended discounted product information. Therefore, the setting device 1 can improve the expected profits of the subscription service provider.

In addition, when designing discounted products for the same contract period, if a discount rate that emphasizes the profitability of the subscription service provider, i.e., a higher service contract price, is set, the user's purchase probability decreases. On the other hand, when designing the discounted product, if a discount rate that increases the user's purchase probability, i.e., a lower service contract price, is set, the subscription service provider's profitability decreases. For this reason, there is a trade-off between the profitability and the user's purchase probability. On the other hand, in the setting device 1 of the first embodiment, in the extraction of candidate discounted product information by the first extraction unit 12, the candidate service contract period can be freely set, and the second extraction unit 13 extracts candidate discounted product information that matches the user's demand. Therefore, according to the setting device 1 of the first embodiment, the discount rate can be adjusted to match the user's demand, i.e., the service contract price can be adjusted to match the user's demand, depending on the candidate service contract period, so that the user's purchase probability can be improved while improving the profitability.

The setting device 1 of the first embodiment may further include an output unit, which outputs the recommended discounted product information to the user's terminal 2. In this case, the output unit outputs the recommended discounted product information to the user's terminal 2, for example, via the authentication server and the communication line network 3. This makes it possible to encourage the user of the terminal 2 to purchase a subscription service based on the recommended discounted product information set by the setting device 1. In addition, when the setting device 1 includes the output unit, the output unit may output the recommended discounted product information by linking it to the time for presenting the recommended discounted product information to the user terminal. By limiting the time for displaying the recommended discounted product information in the terminal 2, the setting device 1 can further encourage the user of the terminal 2 to purchase a subscription service. When the setting device 1 includes an output unit, the setting device 1 may also be called, for example, a suggestion device.

The setting device 1 of embodiment 1 has been described using a newspaper subscription service as an example, but the present disclosure is not limited to this and can be used for other subscription services as well.

(Embodiment 2)
This embodiment is another example of the setting device of the present disclosure. FIG. 4 is a block diagram showing a setting system 200 including a setting device 1A of this embodiment. As shown in FIG. 4, the setting device 1A of this embodiment includes an output unit 16, a collection unit 17, and an update unit 18 in addition to the configuration of the setting device 1 of the first embodiment. The hardware configuration of the setting device 1A is the same as that of the setting device 1 of FIG. 2, except that the CPU 101 includes the configuration of the setting device 1A of FIG. 4 instead of the configuration of the setting device 1 of FIG. 2. Except for these points, the configuration of the setting device 1A of the second embodiment is the same as that of the setting device 1 of the first embodiment, and the description thereof can be used.

Next, an example of the processing of the setting system 200 including the setting device 1A of this embodiment will be described with reference to the flowchart of FIG. 5. As shown in FIG. 5, the setting method of the second embodiment includes steps S6 (output), S7 (collection), and S8 (update) in addition to steps S1 to S5 of the setting method of the first embodiment.

First, the setting system 200 of this embodiment performs steps S1 to S5 in the same manner as the setting system 100 of embodiment 1.

Next, in step S6, the output unit 16 outputs the recommended discounted product information obtained in step S5 to the user's terminal 2. Specifically, the output unit 16 outputs the recommended discounted product information to the user's terminal 2 via the authentication server and the communication line network 3. This allows the setting system 200 to encourage the user of the terminal 2 to purchase a subscription. When outputting the recommended discounted product information, the output unit 16 may provide information limiting the display time for which the recommended discounted product information is displayed (presented) on the user's terminal 2. In this case, the output unit 16 links the recommended discounted product information to the time for which the recommended discounted product information is presented on the user's terminal 2 and outputs it. Then, on the user's terminal 2, multiple contract periods and contract amounts are displayed from the recommended discounted product information according to the time.

Next, in step S7, the collection unit 17 collects user contract information. By including the collection unit 17, the setting device 1A of embodiment 2 can obtain the subsequent contract status of the user of the terminal 2 that received the recommended discounted product information. Therefore, as described below, the setting device 1A of embodiment 2 can update the purchase probability information 107 using the user contract information collected by the collection unit 17. The user contract information is information necessary for updating the purchase probability information 107, and includes, for example, whether or not the user of terminal 2 has a subscription service contract and user information of terminal 2. The contract includes the service contract period and the service contract price.

Specifically, the collection unit 17 judges whether or not the user has applied for a subscription service from the terminal 2 during a pre-specified period after the output unit 16 outputs the recommended discounted product information. If there is no application for the subscription service, the collection unit 17 collects, as the user's contract information, information that there is no subscription service contract, i.e., information that there is no service contract period and service contract price contracted by the user of the terminal 2, by linking it with the user information of the terminal 2. On the other hand, if there is an application for the subscription service, the collection unit 17 collects, as the user's contract information, information that there is no subscription service contract, i.e., information that there is no service contract period and service contract price contracted by the user of the terminal 2, by linking it with the user information of the terminal 2.

Next, in step S8, the update unit 18 updates the purchase probability information 107 using the contract information of the user. As described above, the purchase probability information 107 is linked to past user information, service contract period, service contract price, and purchase probability distribution. Therefore, the update unit 18 updates the purchase probability information 107 by adding the user information, service contract period, and service contract price of the terminal 2 included in the user's contract information collected by the collection unit 17 to the past user information, service contract period, and service contract price of the purchase probability information 107, respectively. Then, the update unit 18 calculates a new purchase probability distribution using a combination of the updated past user information, service contract period, and service contract price. The calculation of the new purchase probability distribution can be calculated by a probabilistic statistical method, and as an example, can be calculated using Bayesian statistics. The new purchase probability distribution may be calculated using reinforcement learning such as a bandit algorithm. Then, the update unit 18 updates the purchase probability distribution of the purchase probability information 107 to the new purchase probability distribution. Then, the setting device 1A ends the process.

In the setting device 1A of the second embodiment, the recommended discounted product information set by the setting device 1A is presented to a new user, and the purchase probability information 107 can be updated by collecting data on the user's contract behavior in response to the results. Therefore, the setting device 1A can set recommended discounted product information that is more suitable for the new user.

In the setting device 1A of the second embodiment, only the purchase probability information 107 is updated, but the present disclosure is not limited to this, and the setting device 1A may be configured to update the user's cancellation information 108 instead of or in addition to updating the purchase probability information 107. In this case, the collection unit 17 also collects the contract period from the user's contract to cancellation when the user of the terminal 2 cancels the contract after the user contracts, over time as the user's contract information. Then, the update unit 18 uses the user's contract information to update the user's cancellation information 108. As described above, the user's cancellation information 108 includes past user information, the user's service contract period, the user's contract price, and the service cancellation rate. Therefore, the update unit 18 updates the user information of the terminal 2, the contract period from the contract to cancellation, and the service contract price included in the user's contract information collected by the collection unit 17 by adding them to the past user information, service contract period, and service contract price of the cancellation information 108, respectively. Next, the update unit 18 calculates the service churn rate based on the updated service contract period of the past user and the service contract price of the past user. Then, the update unit 18 updates the service churn rate in the churn information 108 to the new service churn rate.

(Embodiment 3)
The program of this embodiment is a program that causes a computer to execute the setting method of the present disclosure. In the program of this embodiment, the "processing" can also be referred to as, for example, a "procedure" or an "instruction". The program of this embodiment may be recorded, for example, in a computer-readable recording medium. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples thereof include random access memory (RAM), read-only memory (ROM), hard disk (HD), solid state drive (SSD), optical disk, floppy (registered trademark) disk (FD), etc.

Although the present disclosure has been described above with reference to embodiments and examples, the present disclosure is not limited to the above embodiments and examples. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

<Additional Notes>
Some or all of the above-described embodiments and examples may be described as follows, but are not limited to the following supplementary notes.
<Discounted item setting device>
(Appendix 1)
A device for setting discounted items in a subscription service, comprising:
The apparatus includes an acquisition unit, a first extraction unit, a second extraction unit, a calculation unit, and a third extraction unit,
The acquisition unit acquires user information,
The first extraction unit extracts two or more pieces of candidate discount product information from the user information and the purchase probability information,
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction unit extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
the calculation unit calculates an expected profit to be obtained from the user's contract to cancellation for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
The third extraction unit extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit.
(Appendix 2)
The second extraction unit includes:
The device described in Appendix 1 extracts, from each candidate discount product information, candidate discount product information having a combination of candidate service contract price and purchasing probability such that the purchasing probability becomes relatively low when the candidate service contract price becomes relatively high, or candidate discount product information having a combination of candidate service contract period and purchasing probability such that the purchasing probability becomes relatively high when the candidate service contract price becomes relatively low, as selected discount product information.
(Appendix 3)
The calculation unit is
Matching the user information with past user information in the cancellation information of the user, and extracting the cancellation information of the user including the past user information corresponding to the user information;
The device according to claim 1 or 2, wherein the expected profit is calculated using a service churn rate in the extracted user churn information.
(Appendix 4)
The calculation unit is
The device according to any one of claims 1 to 3, wherein the expected profit is calculated by the following formula (1):

(Expected revenue) = (1/service cancellation rate) × candidate service contract price × purchase probability ... (1)
(Appendix 5)
The device described in any one of appendices 1 to 4, wherein the third extraction unit extracts selected discounted product information having the maximum expected profit among the expected profits of each selected discounted product information as the recommended discounted product information.
(Appendix 6)
Further, an output unit is provided,
The device described in any one of appendixes 1 to 5, wherein the output unit outputs the recommended discounted product information to a user's terminal.
(Appendix 7)
The output unit is
The device described in Appendix 6, which outputs the recommended discounted product information linked to a time for presenting the recommended discounted product information to the user terminal.
(Appendix 8)
Further, a collecting section is provided,
The collection unit collects contract information of users,
The user's contract information includes whether or not the user has a subscription service contract and the user information,
The user's contract information further includes, if the user has a subscription service contract, a service contract period and a service contract price contracted by the user;
8. The apparatus of claim 6 or 7.
(Appendix 9)
Further, an update unit is provided,
The update unit is
The device of claim 8, further comprising: updating the purchasing probability information using the user's subscription information.
(Appendix 10)
The user's contract information is
Including the contract period until the user's cancellation,
The update unit is
10. The device of claim 8 or 9, further comprising: updating cancellation information for the user using the user's contract information.
(Appendix 11)
The first extraction unit
Matching the user information with past user information in the purchase probability information to extract purchase probability information including past user information corresponding to the user information;
The device according to any one of claims 1 to 10, further comprising: a purchase probability distribution in the extracted purchase probability information to extract the two or more candidate discounted product information.
(Appendix 12)
The first extraction unit
A purchase probability is output by inputting a service contract period and a service contract price into the purchase probability distribution;
12. The device according to any one of claims 1 to 11, wherein the candidate discount product information is extracted from a combination of the output purchase probability and the input service contract period and service contract price.
(Appendix 13)
13. The device of any one of appendices 1 to 12, wherein the user information includes user contract information, the user's age, the user's gender, and/or the user's behavioral history.
(Appendix 14)
14. The apparatus of any one of claims 1 to 13, wherein the subscription service is a newspaper subscription service.
<How to set discount items>
(Appendix 15)
1. A method for setting discounts in a subscription service, the method comprising:
The method includes an acquisition step, a first extraction step, a second extraction step, a calculation step, and a third extraction step,
In the acquiring step, user information is acquired,
In the first extraction step, two or more pieces of candidate discounted product information are extracted from the user information and purchase probability information;
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction step extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information as selected discount product information;
In the calculation step, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information in which past user information, a service contract period, a service contract price, and a service cancellation rate are linked together,
In the third extraction step, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit.
(Appendix 16)
In the second extraction step,
The method described in Appendix 15, in which, from each candidate discount product information, candidate discount product information having a combination of candidate service contract period and candidate service contract price such that the candidate service price becomes relatively lower when the candidate service contract period becomes relatively longer, or candidate discount product information having a combination of candidate service contract period and candidate service contract price such that the candidate service price becomes relatively higher when the candidate service contract period becomes relatively shorter, is extracted as selected discount product information.
(Appendix 17)
In the calculation step,
Matching the user information with past user information in the cancellation information of the user, and extracting the cancellation information of the user including the past user information corresponding to the user information;
17. The method according to claim 15 or 16, wherein the expected profit is calculated using a service churn rate in the extracted user churn information.
(Appendix 18)
In the calculation step,
18. The method according to any one of claims 15 to 17, wherein the expected profit is calculated by the following formula (1):

(Expected revenue) = (1/service cancellation rate) × candidate service contract price × purchase probability ... (1)
(Appendix 19)
A method according to any one of appendices 15 to 18, wherein in the third extraction step, selected discounted product information having the maximum expected profit among the expected profits of each selected discounted product information is extracted as the recommended discounted product information.
(Appendix 20)
Further, an output step is included,
20. The method according to any one of appendices 16 to 19, wherein in the output step, the recommended discounted product information is output to a user's terminal.
(Appendix 21)
In the output process,
The method according to claim 20, wherein the recommended discounted product information is output in association with a time for presenting the recommended discounted product information to the user terminal.
(Appendix 22)
Further comprising a collecting step,
The collecting step collects contract information of a user,
The user's contract information includes whether or not the user has a subscription service contract and the user information,
The user's contract information further includes, if the user has a subscription service contract, a service contract period and a service contract price contracted by the user;
22. The method of claim 20 or 21.
(Appendix 23)
Further, the method includes an updating step,
In the updating step,
The method of claim 22, further comprising updating the purchase probability information using the user's contract information.
(Appendix 24)
The user's contract information is
Including the contract period until the user's cancellation,
In the updating step,
24. The method of claim 22 or 23, further comprising updating the user's cancellation information using the user's contract information.
(Appendix 25)
In the first extraction step,
Matching the user information with past user information in the purchase probability information to extract purchase probability information including past user information corresponding to the user information;
A method according to any one of appendices 15 to 24, further comprising extracting the two or more candidate discounted product information using a purchase probability distribution in the extracted purchase probability information.
(Appendix 26)
In the first extraction step,
A purchase probability is output by inputting a service contract period and a service contract price into the purchase probability distribution;
A method according to any one of appendices 15 to 25, wherein the candidate discount product information is extracted from a combination of the output purchase probability and the input service contract period and service contract price.
(Appendix 27)
27. The method of any of appendices 15 to 26, wherein the user information includes user contract information, the user's age, the user's gender, and/or the user's behavioral history.
(Appendix 28)
28. The method of any one of claims 15 to 27, wherein the subscription service is a newspaper subscription service.
<Program>
(Appendix 29)
A program for causing a computer to execute an acquisition process, a first extraction process, a second extraction process, a calculation process, and a third extraction process,
In the acquisition process, user information is acquired,
In the first extraction process, two or more pieces of candidate discounted product information are extracted from the user information and the purchase probability information;
The purchase probability information is information in which past user information, a service contract period, a service contract price, and a purchase probability distribution are linked together,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction process extracts candidate discount product information that matches the user's demand from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
In the calculation process, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction process, a program extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit.
(Appendix 30)
In the second extraction process,
The program described in Appendix 29 extracts, from each candidate discount product information, candidate discount product information having a combination of candidate service contract period and candidate service contract price such that the candidate service price becomes relatively lower when the candidate service contract period becomes relatively longer, or candidate discount product information having a combination of candidate service contract period and candidate service contract price such that the candidate service price becomes relatively higher when the candidate service contract period becomes relatively shorter, as selected discount product information.
(Appendix 31)
In the calculation process,
Matching the user information with past user information in the cancellation information of the user, and extracting the cancellation information of the user including the past user information corresponding to the user information;
The program described in appendix 29 or 30, which calculates the expected profit using a service cancellation rate in the extracted user cancellation information.
(Appendix 32)
In the calculation process,
32. The program described in any one of appendices 29 to 31, which calculates the expected profit using the following formula (1):

(Expected revenue) = (1/service cancellation rate) × candidate service contract price × purchase probability ... (1)
(Appendix 33)
A program described in any one of appendices 15 to 18, wherein in the third extraction process, selected discounted product information having the maximum expected profit among the expected profits of each selected discounted product information is extracted as the recommended discounted product information.
(Appendix 34)
Further, output processing is included,
The program described in any one of appendices 30 to 33, wherein the output process outputs the recommended discounted product information to a user's terminal.
(Appendix 35)
In the output process,
The program described in Appendix 34, which links the recommended discounted product information to a time for presenting the recommended discounted product information to the user terminal and outputs the information.
(Appendix 36)
Further, the collection process includes:
The collection process collects contract information of the user,
The user's contract information includes whether or not the user has a subscription service contract and the user information,
The user's contract information further includes, if the user has a subscription service contract, a service contract period and a service contract price contracted by the user;
36. The program according to claim 34 or 35.
(Appendix 37)
Further, an update process is included.
In the update process,
The program described in Appendix 36, which updates the purchase probability information using the user's contract information.
(Appendix 38)
The user's contract information is
Including the contract period until the user's cancellation,
In the update process,
24. The program described in claim 22 or 23, which updates the user's cancellation information using the user's contract information.
(Appendix 39)
In the first extraction process,
Matching the user information with past user information in the purchase probability information to extract purchase probability information including past user information corresponding to the user information;
A program described in any one of appendices 29 to 38, which extracts the two or more candidate discounted product information using a purchase probability distribution in the extracted purchase probability information.
(Appendix 40)
In the first extraction process,
A purchase probability is output by inputting a service contract period and a service contract price into the purchase probability distribution;
A program according to any one of appendices 29 to 39, which extracts the candidate discounted product information from a combination of the output purchase probability and the input service contract period and service contract price.
(Appendix 41)
41. The program of any one of appendices 29 to 40, wherein the user information includes the user's contract information, the user's age, the user's gender, and/or the user's behavioral history.
(Appendix 42)
42. The program of any one of appendixes 29 to 41, wherein the subscription service is a newspaper subscription service.

As described above, according to the present disclosure, it is possible to provide a device for setting discounted products in a subscription service that can design discounted products suitable for new users and improve the expected profits of the subscription service provider. For this reason, the present disclosure is extremely useful, for example, in the field of online sales promotion.

Reference Signs List 1, 1A Setting device 11 Acquisition unit 12 First extraction unit 13 Second extraction unit 14 Calculation unit 15 Third extraction unit 16 Output unit 17 Collection unit 18 Update unit 2 Terminal 3 Communication network 100, 200 Setting system

Claims (14)

A device for setting discounted items in a subscription service, comprising:
The apparatus includes an acquisition unit, a first extraction unit, a second extraction unit, a calculation unit, and a third extraction unit,
The acquisition unit acquires user information,
The first extraction unit extracts two or more pieces of candidate discount product information from the user information and the purchase probability information,
The purchase probability information is information that links information of a user who has previously subscribed to the subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction unit extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
the calculation unit calculates an expected profit to be obtained from the user's contract to cancellation for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
The third extraction unit extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit;
The first extraction unit
Matching the user information with past user information of the purchase probability information;
If past user information that matches the user information is present, purchase probability information associated with the past user information that corresponds to the user information is extracted;
If there is no past user information that matches the user information, a part of the user information is used to compare the purchase probability information with the past user information, and purchase probability information associated with the past user information that corresponds to the user information is extracted;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
The device extracts the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price. A device for setting discounted items in a subscription service, comprising:
The apparatus includes an acquisition unit, a first extraction unit, a second extraction unit, a calculation unit, and a third extraction unit,
The acquisition unit acquires user information,
The user information includes attributes of the user,
The first extraction unit extracts two or more pieces of candidate discount product information from the user information and the purchase probability information,
The purchase probability information is information that links information of a user who has previously subscribed to the subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The past user information includes attributes of users who have previously subscribed to the subscription service,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction unit extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
the calculation unit calculates an expected profit to be obtained from the user's contract to cancellation for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
The third extraction unit extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit;
The first extraction unit
comparing user attributes in the user information with user attributes in past user information of the purchase probability information, and extracting purchase probability information associated with past user information that is the same as or similar to the user information;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
The device extracts the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price. The second extraction unit includes:
The device described in claim 1 or 2 extracts, from each candidate discount product information, candidate discount product information having a combination of candidate service contract price and purchasing probability such that the purchasing probability becomes relatively low when the candidate service contract price becomes relatively high, or candidate discount product information having a combination of candidate service contract period and purchasing probability such that the purchasing probability becomes relatively high when the candidate service contract price becomes relatively low, as selected discount product information. The calculation unit is
Matching the user information with past user information in the cancellation information of the user, and extracting the cancellation information of the user including the past user information corresponding to the user information;
The device according to claim 1 or 2, wherein the expected profit is calculated using a service churn rate in the extracted user churn information. The calculation unit is
The device according to claim 1 or 2, wherein the expected profit is calculated by the following formula (1):

(Expected revenue) = (1/service cancellation rate) × candidate service contract price × purchase probability ... (1) Further, an output unit is provided,
The device according to claim 1 , wherein the output unit outputs the recommended discounted product information to the user's terminal in association with a time for presenting the recommended discounted product information to the user's terminal. Further, a collection unit and an update unit are provided,
The collection unit collects contract information of users,
The user's contract information includes whether or not the user has a subscription service contract and the user information,
The user's contract information further includes, if the user has a subscription service contract, a service contract period and a service contract price contracted by the user;
The update unit is
updating the purchase probability information using the contract information of the user;
7. The apparatus of claim 6 . The user's contract information is
Including the contract period until the user's cancellation,
The update unit is
The apparatus of claim 7 , further comprising: updating said user's cancellation information using said user's contract information. Further, a collection unit and an update unit are provided ,
The second extraction unit includes:
extracting, from each candidate discount product information, candidate discount product information having a combination of a candidate service contract price and a purchase probability in which the purchase probability becomes relatively low when the candidate service contract price becomes relatively high, or candidate discount product information having a combination of a candidate service contract period and a purchase probability in which the purchase probability becomes relatively high when the candidate service contract price becomes relatively low, as selected discount product information;
The collection unit collects contract information of users,
The user's contract information includes whether or not the user has a subscription service contract and the user information,
The user's contract information further includes, if the user has a subscription service contract, a service contract period and a service contract price contracted by the user;
The update unit is
The device according to claim 1 or 2, further comprising: updating said purchase probability information using subscription information of said user. The device of claim 1 or 2, wherein the subscription service is a newspaper subscription service. 1. A method for setting discounts in a subscription service executed on a computer, comprising:
The method includes an acquisition step, a first extraction step, a second extraction step, a calculation step, and a third extraction step,
In the acquiring step, user information is acquired,
In the first extraction step, two or more pieces of candidate discounted product information are extracted from the user information and purchase probability information;
The purchase probability information is information that links information of a user who has previously subscribed to the subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction step extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information as selected discount product information;
In the calculation step, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction step, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit;
In the first extraction step,
Matching the user information with past user information of the purchase probability information;
If past user information that matches the user information is present, purchase probability information associated with the past user information that corresponds to the user information is extracted;
If there is no past user information that matches the user information, a part of the user information is used to compare the purchase probability information with the past user information, and purchase probability information associated with the past user information that corresponds to the user information is extracted;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
The method extracts the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price. 1. A method for setting discounts in a subscription service executed on a computer, comprising:
The method includes an acquisition step, a first extraction step, a second extraction step, a calculation step, and a third extraction step,
In the acquiring step, user information is acquired,
The user information includes attributes of the user,
In the first extraction step, two or more pieces of candidate discounted product information are extracted from the user information and purchase probability information;
The purchase probability information is information that links information of a user who has previously subscribed to the subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The past user information includes attributes of users who have previously subscribed to the subscription service,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction step extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information as selected discount product information;
In the calculation step, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction step, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit;
In the first extraction step,
comparing the user attributes in the user information with the user attributes in the past user information of the purchase probability information;
Extracting purchase probability information linked to past user information that is the same as or similar to the user information;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
The method extracts the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price. A program for causing a computer to execute an acquisition process, a first extraction process, a second extraction process, a calculation process, and a third extraction process,
In the acquisition process, user information is acquired,
In the first extraction process, two or more pieces of candidate discounted product information are extracted from the user information and the purchase probability information;
The purchase probability information is information that links information of a user who has previously signed up for a subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction process extracts candidate discount product information that matches the user's needs from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information, as selected discount product information;
In the calculation process, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction process, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit;
The first extraction process includes:
Matching the user information with past user information of the purchase probability information;
If past user information that matches the user information is present, purchase probability information associated with the past user information that corresponds to the user information is extracted;
If there is no past user information that matches the user information, a part of the user information is used to compare the purchase probability information with the past user information, and purchase probability information associated with the past user information that corresponds to the user information is extracted;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
A program for extracting the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price. A program for causing a computer to execute an acquisition process, a first extraction process, a second extraction process, a calculation process, and a third extraction process,
In the acquisition process, user information is acquired,
The user information includes attributes of the user,
In the first extraction process, two or more pieces of candidate discounted product information are extracted from the user information and the purchase probability information;
The purchase probability information is information that links information of a user who has previously signed up for a subscription service (past user information), a service contract period, a service contract price, and a purchase probability distribution,
The past user information includes attributes of users who have previously subscribed to the subscription service,
The candidate discount product information is information in which two or more candidate service contract periods are linked to a candidate service contract price and a purchase probability for each candidate service contract period,
The second extraction process extracts candidate discount product information that matches the user's demand from the candidate discount product information based on a candidate service contract period and a candidate service contract price of each candidate discount product information as selected discount product information;
In the calculation process, an expected profit to be obtained from the user's contract until cancellation is calculated for each selected discounted product information based on the selected discounted product information and past user cancellation information;
The user cancellation information is information linking past user information, a service contract period, a service contract price, and a service cancellation rate,
In the third extraction process, recommended discounted product information to be presented to a user is extracted from the selected discounted product information based on the expected profit;
The first extraction process includes:
comparing the user attributes in the user information with the user attributes in the past user information of the purchase probability information;
Extracting purchase probability information linked to past user information that is the same as or similar to the user information;
outputting a purchase probability by inputting the service contract period and the service contract price into the purchase probability distribution included in the extracted purchase probability information;
A program for extracting the candidate discount product information from a combination of the output purchase probability and the input service contract period and service contract price.