Discounted product setting device, discounted product setting method, and program

Abstract

To provide a discounted product setting device that can design an appropriate discounted product even for a new user, and improve an expected profit for a subscription service provider.SOLUTION: In a setting system 100, an acquisition unit of a setting device 1 acquires user information on the basis of the identification information of a terminal 2, a first extraction unit extracts two or more pieces of candidate discounted product information from the user information and purchase probability information, a second extraction unit extracts candidate discounted product information that matches the user's needs from the candidate discounted product information as selected discounted product information on the basis of a candidate service contract period and candidate service contract price of each candidate discounted product information, a calculation unit calculates an expected profit obtained in a period from contract to cancellation of a user for each selected discounted product information from 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 on the basis of the expected profit.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a device for setting discounted items, a method for setting discounted items, and a program. Regarding. [Background technology]

[0002] In various services such as subscription services, various methods for sales promotion, such as the presentation of time-limited coupons, are used to acquire new users. Patent Document 1 describes that a rebate value is set according to the user's reaction when a rebate value according to user information is presented. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-163046 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, when the rebate value is corrected based on the user's response, a process of checking the user's response is required multiple times. This makes it difficult to use the rebate value to acquire new users. In addition, when the rebate value is set based on the user's response, the subscription service provider tends to expect a lower profit.

[0005] Therefore, an object of the present disclosure is to provide a device for setting discounted products in a subscription service that can design discounted products suitable for users, even for new users, and can improve the expected profits of the subscription service provider. [Means for solving the problem]

[0006] 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 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; 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.

[0007] 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.

[0008] 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 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. Effect of the Invention

[0009] According to the present disclosure, discounted products suitable for new users can be designed, and the expected profits of subscription service providers can be improved. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing an example of a design system including a design apparatus according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of the design apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of a design method and program according to the first embodiment. [Figure 4] FIG. 4 is a block diagram showing an example of a design system including a design apparatus according to the second embodiment. [Diagram 5] FIG. 5 is a flowchart showing an example of a design method and program according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] 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 Figs. 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 convenience of description, the structure of each part may be appropriately simplified, and the dimensional ratio of each part may be shown schematically, different from the actual one. In addition, each embodiment and description can be mutually referred to 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".

[0012] (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 (can communicate) with a user's terminal 2 in one or both directions 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.

[0013] The setting device 1 of the present embodiment may be incorporated into a personal computer (PC) in which the program of the present disclosure is installed, or into a server or the like as a system. The setting device 1 of the present embodiment may also be a system consisting of one or more computers or servers capable of executing the program of the present disclosure, that is, a cloud computing system. The personal computers may constitute 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 the communication line network 3, so that the system administrator can manage the setting device 1 from the external terminal. In the present embodiment, the setting system 100 includes one setting device 1, but may include multiple setting devices.

[0014] Examples of the terminal 2 include a PC; a mobile terminal such as a mobile phone, a smartphone, or a tablet terminal; a smart watch, a smart glass, or a wearable terminal; and the like.

[0015] The communication network 3 is not particularly limited and may be a known network, for example, a wired or wireless network. Examples of the communication network 3 include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), and WiFi (Wireless Fidelity).

[0016] 2 illustrates a block diagram of a hardware configuration of the setting device 1. The setting device 1 includes, 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, and a communication device (communication unit) 111. Each unit of the setting device 1 is connected via the bus 103 by its respective interface (I / F).

[0017] 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 include other calculation devices such as a GPU (Graphics Processing Unit) and 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.

[0018] 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 operation programs, such as a program 105 of the present disclosure, stored in a 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).

[0019] The bus 103 can also be connected to external devices. Examples of the external devices include an external storage device (external database, etc.), a printer, etc. The setting device 1 can be connected to a communication network 3 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.

[0020] The storage device 104 is also called an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operation 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 an internal or external type, and examples of the storage medium include a hard disk (HD), a floppy disk (FD), a CD-ROM, a CD-R, a CD-RW, an MO, a DVD, a flash memory, and a memory card, 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.

[0021] 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 and a scanner; a card reader such as an IC card reader and a magnetic card reader; and a voice input means such as a microphone. Examples of the display 110 include a display device 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, in the setting device 1, the input device 109 and the display 110 are of any configuration, and may be omitted or may include one or more of them.

[0022] 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 accesses a site that contains an online version of a newspaper that can be purchased as a subscription service using the terminal 2, and sets a discounted item of the subscription service for the user. As shown in Fig. 3, the setting method and program of the first embodiment executes each process of S1 (acquisition), S2 (first extraction), S3 (second extraction), S4 (calculation), and S5 (third extraction) in this order.

[0023] Prior to processing by the setting device 1, first, a user accesses the newspaper site using terminal 2. A 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.

[0024] 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 collates 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., whether or not there is a subscription contract, the type of contract (monthly contract, annual contract, etc.), the period of time 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.

[0025] 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, a plurality of 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 a past subscription service contract. The purchase probability information 107 is linked to past user information, a service contract period, a service contract price, and a 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. Then, using these, the first extraction unit 12 can generate (extract) candidate discounted product information including multiple pieces of information linking 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.

[0026] 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 conditions of the user information 106 and performs a similar comparison to extract purchase probability information 107 linked to past user information corresponding to the user information 106.

[0027] 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. Then, the first extraction unit 12 extracts the obtained sets of data as candidate discounted product information. Then, the first extraction unit 12 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 a plurality of contract periods and contract prices specified in advance may be set as the candidate service contract period and the candidate service contract price. Also, in step S2, for example, a plurality of contract periods and contract prices may be set within a range of a contract period and a contract price specified in advance, and the set contract period and contract price may be set as the candidate service contract period and the candidate service contract price.

[0028] Next, in step S3, the second extraction unit 13 extracts candidate discount product information that matches the user's demand as selected discount product information from the candidate discount product information based on the candidate service contract price and purchase probability of each candidate discount product information. In step S3, the candidate discount product information is extracted based on the past user information. The candidate discount 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 purchase probability of a higher service contract price is the same as or higher than the purchase probability of a lower service contract price despite the increase in the service contract price, the user is unlikely to select such a candidate discount product, and does not match the user's demand. Therefore, in step S3, candidate discount product information that matches the user's demand is selected.

[0029] Specifically, in step S3, the second extraction unit 13 extracts, as selected discounted product information, candidate discounted 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 from each candidate discounted product information. It can also be said that the second extraction unit 13 extracts, as selected discounted product information, candidate discounted product information having a combination of a candidate service contract period and a purchase probability in which the purchase probability becomes relatively high from each candidate discounted product information when the candidate service contract price becomes relatively low from each candidate discounted product information.

[0030] Next, in step S4, the calculation unit 14 calculates the expected profits that can 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, 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.

[0031] 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 signs a contract, and can be calculated by a known financial engineering method for calculating future expected profit. As a specific example, the expected profit can be calculated by the following formula (1). The following formula (1) can 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 flow 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 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)

[0032] 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 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 ~ Horizon] {(1 - service churn rate) × candidate service contract price × purchase probability / candidate service contract period} (2) t: number of months passed

[0033] 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 the 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)

[0034] 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 ~ Horizon] {(1 - service cancellation rate - discount rate for future cash flows) × candidate service contract price × purchase probability / candidate service contract period} (4) t: number of months passed

[0035] In step S4, 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.

[0036] 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 process. 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 the selected discounted product information with a relatively high expected profit. The third extraction unit 15 may extract the recommended discounted product information by using, for example, an average value of expected profits of the selected discounted product information.

[0037] 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, extract candidate discounted product information to be presented to the new user, and further extract candidate discounted product information that matches the user's demand 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.

[0038] In addition, in 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, in 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 extracting the 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 the 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.

[0039] The setting device 1 of the first embodiment may further include an output unit, and the output unit may output the recommended discounted product information to the user's terminal 2. In this case, the output unit may output the recommended discounted product information to the user's terminal 2 via, for example, the authentication server and the communication line network 3. This allows the user of the terminal 2 to be encouraged 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 a 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 the output unit, the setting device 1 may also be called, for example, a suggestion device.

[0040] The setting device 1 of the first embodiment has been described taking 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.

[0041] (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.

[0042] Next, an example of the processing of the setting system 200 including the setting device 1A of the present 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 a step S6 (output), a step S7 (collection), and a step S8 (update) in addition to the steps S1 to S5 of the setting method of the first embodiment.

[0043] First, the setting system 200 of this embodiment performs steps S1 to S5 in the same manner as the setting system 100 of the first embodiment.

[0044] 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. In this way, the setting system 200 can encourage the user of the terminal 2 to purchase a subscription. When outputting the recommended discounted product information, the output unit 16 may add information limiting the display time for displaying (presenting) the recommended discounted product information on the user's terminal 2. In this case, the output unit 16 outputs the recommended discounted product information by linking it to the time for presenting the recommended discounted product information on the user's terminal 2. Then, on the user's terminal 2, a plurality of contract periods and contract amounts are displayed from the recommended discounted product information according to the time.

[0045] Next, in step S7, the collection unit 17 collects user contract information. The setting device 1A of the second embodiment includes the collection unit 17, and can acquire the subsequent contract status of the user of the terminal 2 that has received the recommended discounted product information. Therefore, the setting device 1A of the second embodiment can update the purchase probability information 107 using the user contract information collected by the collection unit 17, as described below. The user contract information is information necessary for updating the purchase probability information 107, and includes, for example, whether or not the user of the terminal 2 has a subscription service contract and user information of the terminal 2. The contract includes a service contract period and a service contract price.

[0046] Specifically, the collection unit 17 judges whether or not the user has applied for a subscription service from the terminal 2 within 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.

[0047] 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 contract information of the user 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 new purchase probability distribution can be calculated by a probabilistic statistical method, and as an example, can be calculated using Bayesian statistics. Note that 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.

[0048] 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 contract behavior of the user in response to the result is collected as data, and the purchase probability information 107 can be updated. Therefore, the setting device 1A can set recommended discounted product information more suitable for the new user.

[0049] 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. 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, over time, the contract period from the user's contract to the cancellation of the contract when the user of the terminal 2 cancels the contract after the user has signed the contract. 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 the cancellation, and the service contract price, which are included in the user's contract information collected by the collection unit 17, by adding them to the past user information, the service contract period, and the 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 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.

[0050] (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 a random access memory (RAM), a read-only memory (ROM), a hard disk (HD), a solid state drive (SSD), an optical disk, and a floppy disk (FD).

[0051] Although the present disclosure has been described above with reference to the 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.

[0052] <Additional Notes> Some or all of the above-described embodiments and examples may be described as follows, but are not limited to the following: <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 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; 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 cancellation information of the user including 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, which calculates the expected profit 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 in association with 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 contract 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 includes: 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; An apparatus according to any one of appendices 1 to 10, which extracts the two or more candidate discounted product information using a purchase probability distribution in the extracted purchase probability information. (Appendix 12) The first extraction unit includes: A purchase probability is output by inputting a service contract period and a service contract price into the purchase probability distribution; An apparatus according to any one of appendices 1 to 11, 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 13) 13. The device of any one of appendices 1 to 12, wherein the user information includes user contract information, user age, user gender, and / or user behavior 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 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. (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 cancellation information of the user including past user information corresponding to the user information; 17. The method according to claim 15 or 16, wherein the expected revenue 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 step, The method described in Appendix 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 according to claim 20 or 21. (Appendix 23) Further, the method includes an updating step, In the updating step, 23. 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 claim 15, 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, the 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, as selected 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. (Appendix 31) In the calculation process, Matching the user information with past user information in the cancellation information of the user, and extracting cancellation information of the user including 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 in the output process, the recommended discounted product information is output to a user's terminal. (Appendix 35) In the output process, The program described in Appendix 34, which outputs the recommended discounted product information linked to a time for presenting the recommended discounted product information to the user terminal. (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 described in 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) 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. [Industrial Applicability]

[0053] 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 profit of the subscription service provider. Therefore, the present disclosure is extremely useful in, for example, online sales promotion fields. [Explanation of symbols]

[0054] 1. 1A setting device 11 Acquisition Department 12 First Extraction Section 13 Second Extraction Section 14 Calculation section 15 Third Extraction Section 16 Output section 17 Collection Department 18 Update section 2. Terminal 3. Communication Network 100, 200 setting system

Claims

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.

2. The second extraction unit includes: The device of claim 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.

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.

4. 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)

5. 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.

6. 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 user's contract information; 6. The apparatus of claim 5.

7. The user's contract information is Including the contract period until the user's cancellation, The update unit is The apparatus of claim 6 , further comprising: updating said user's cancellation information using said user's contract information.

8. Further, a collection unit and an update unit are provided, The first extraction unit is 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; extracting the two or more candidate discounted product information using a purchase probability distribution in the extracted purchase probability information; The second extraction unit includes: extracting, from each of the candidate discounted product information, candidate discounted 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 discounted 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 discounted 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.

9. The first extraction unit is A purchase probability is output by inputting a service contract period and a service contract price into the purchase probability distribution; 3. The device according to claim 1, 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.

10. 3. Apparatus according to claim 1 or 2, wherein the subscription service is a newspaper subscription service.

11. 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 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.

12. 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, a program extracts recommended discounted product information to be presented to a user from the selected discounted product information based on the expected profit.

Images