JP2019185595A - Information processor, method for processing information, information processing program, determination device, method for determination, and determination program - Google Patents

Abstract

An object of the present invention is to improve the accuracy of credit screening. An information processing apparatus according to the present application includes an acquisition unit and an estimation unit. The acquisition unit acquires information on a first action history, which is an action history before the first user is provided with the predetermined credit, from the action history on the network of the first user to which the predetermined credit has been provided. The estimating unit is configured to determine, based on the information on the first action history acquired by the acquiring unit and the result of whether or not the first user has defaulted on a debt, a network of a second user to be subjected to a credit check for a predetermined credit. The credibility of the second user is estimated from information on the second action history, which is the above action history. [Selection diagram] Fig. 1

Description

  The present invention relates to an information processing device, an information processing method, an information processing program, a determination device, a determination method, and a determination program.

  Conventionally, a technique for providing an index used for credit examination such as credit card examination is known. For example, a technique has been proposed in which personal information such as user attribute information and credit history information is digitized by a scoring engine to determine whether or not a credit card can be issued.

JP 2003-44668 A

  However, with the above-described conventional technology, the accuracy of credit screening cannot always be improved. In the above prior art, personal information such as user attribute information and credit history information is only digitized, and credit information has been damaged due to overdue in the past, but the situation has changed and there is currently a problem with repayment ability Even a non-user may determine that a credit card cannot be issued.

  The present application has been made in view of the above, and an object thereof is to provide an information processing device, an information processing method, an information processing program, a determination device, a determination method, and a determination program that can improve the accuracy of credit examination. To do.

  The information processing apparatus according to the present application includes a first action history that is an action history before the first user is granted the predetermined credit among the action histories on the network of the first user who is given the predetermined credit. A credit examination for the predetermined credit based on an acquisition unit for acquiring information on the information, information on the first action history acquired by the acquisition unit, and a record of whether or not the first user has defaulted And an estimation unit for estimating the creditworthiness of the second user from information related to the second behavior history, which is a behavior history on the network of the second user as a target.

  According to one aspect of the embodiment, there is an effect that the accuracy of credit examination can be improved.

FIG. 1 is a diagram illustrating an example of a first model generation process according to the embodiment. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a repayment record storage unit according to the embodiment. FIG. 7 is a diagram illustrating a configuration example of the determination apparatus according to the embodiment. FIG. 8 is a flowchart illustrating a first model generation processing procedure according to the embodiment. FIG. 9 is a flowchart illustrating an information processing procedure according to the embodiment. FIG. 10 is a diagram illustrating an example of the second model generation process according to the modification. FIG. 11 is a diagram illustrating an example of information processing according to the modification. FIG. 12 is a flowchart illustrating a second model generation processing procedure according to the modification. FIG. 13 is a flowchart illustrating an information processing procedure according to the modification. FIG. 14 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, an information processing program, a determination apparatus, a determination method, and a mode for implementing the determination program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. explain. In addition, the information processing apparatus, the information processing method, the information processing program, the determination apparatus, the determination method, and the determination program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. Example of first model generation process]
First, an example of the first model generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a first model generation process according to the embodiment. The first model generation process according to the present application is performed by the information processing apparatus 100. The information processing apparatus 100 is a server apparatus that estimates the creditworthiness of a new user who is a new applicant for a credit card in cooperation with a credit card company. Hereinafter, a new credit card applicant is referred to as a new user as appropriate.

  Here, “default” means that the obligor does not perform in accordance with the purpose of the obligation even though there is no valid reason. Specifically, “default” includes non-payment or arrears of credit card payments. In other words, if the payment is finally made only after the payment of the credit card is overdue, it is a default. In the case of arrears, if payment is made in the period up to 3 months from the payment deadline, the fact that a default has occurred is not recorded in the credit information. If payment is not made after three months from the payment deadline, the fact that a default has occurred is recorded in the credit information even if the payment is finally made.

  In the example illustrated in FIG. 1, the information processing apparatus 100 includes information related to an action history on the network of the first user before the first user who has issued a credit card has a credit card, and the first user performs default. Based on the history of whether or not it has occurred, a first model M1 is generated that calculates an index value regarding whether or not the new user will default on the basis of information on the behavior history of the new user on the network. For example, the information processing apparatus 100 uses information related to a commercial transaction history, a browsing history, a search history, an SNS usage history, and the like on the user's network as information related to the user's behavior history.

  Specifically, the information processing apparatus 100 generates a first model M1 that calculates a default probability, which is a probability that a new user will default on a debt, when information related to an action history on the network of the new user is input. . Although details of the generation process will be described later, the information processing apparatus 100 uses, for example, the first user who has a credit card issuance record as correct data (teacher data, objective variable), and the action history on the network of the first user. Then, a regression learning model such as a support vector machine (Support Vector Machine) having information on the first action history, which is an action history before the first user has a credit card, as a feature (explanatory variable) is generated.

  Here, the occurrence time of the act that the user has a credit card is defined. In this specification, it is assumed that the act of the user having a credit card occurs after the card issue date, which is the date when the credit card is issued to the user by the credit card company. Conversely, it is assumed that the user does not have a credit card before the card issuance date, which is the date when the credit card is issued to the user. Note that the fact that a credit card has been issued means that the user has a credit card, which means that the credit card has been issued to the user.

  The information processing apparatus 100 uses the credit card issuance date for the first user as a reference date as information regarding the action history on the network of the first user before the first user has a credit card, and a period 1 ( = 1 year), information on the business transaction history, browsing history, etc. on the first user's network is used. For example, assuming that the credit card issuance date for the first user U11 is February 1, 2016, the information processing apparatus 100 starts from February 1, 2015 as information regarding the action history on the network of the first user U11. Information on the business transaction history, browsing history, etc. on the network of the first user U11 in the year up to January 31, 2016 is used.

  In addition, the information processing apparatus 100 uses the credit card issuance date for the first user as a reference date as a record of whether or not the first user has defaulted, and a period 2 after the reference date (= one year and three months) The record of whether or not the first user has defaulted is used. For example, in the case of the above-described first user U11, the information processing apparatus 100 determines that the first user U11 has defaulted for one year from February 1, 2016 to April 30, 2017. A record of whether or not the first user U11 has defaulted in three months is used. For example, the information processing apparatus 100 uses a track record that the first user U11 has defaulted during one year and three months from February 1, 2016 to April 30, 2017.

  Period 2 is a total period of three months from the card issuance date, which is the reference date, and one year after three months from the reference date. Here, three months from the card issuance date is a period during which the user is not considered to be defaulting even if the user does not pay the credit card company. For example, there is a case where the user inadvertently forgets to pay the credit card company inadvertently. Therefore, for the three months from the card issuance date, even if the user does not pay to the credit card company, the fact that a default has occurred is not recorded in the credit information. On the other hand, after three months from the card issuance date, if the user does not pay the credit card, the fact that a default has occurred is recorded in the credit information.

  Generally, in the financial industry, the fact that a default or a long-term delinquency is recorded in credit information is referred to as “credit information is damaged”. In addition, the financial institution examines based on the credit information acquired from the credit information institution in order to determine whether or not the loan is possible and the amount that can be financed. In general, a user whose credit information is damaged is regarded as having no repayment ability, making it difficult to obtain a loan.

  Generally, in the credit card industry, the fact that the user has defaulted is recorded in the credit information when the user does not pay the credit card even after three months from the payment deadline. Note that the fact that the user does not pay the credit card even after three months from the payment deadline may be referred to as “accrual 3”, “payment past”, “reminder”, “negative”, or the like. Here, “non-accrual” is an abbreviation for non-accommodation. In other words, “unpaid” means that money or the like has not yet been collected or stored.

  Generally, when a user uses a credit card, the payment deadline for the credit card company varies depending on the credit card company. For example, a case where the payment due date for the credit card company is the end of the month following the month in which the user uses the credit card will be described as an example. Generally, payment to a credit card company is made by automatically debiting the payment due date from the bank account registered by the user at the time of credit card application. For example, when a certain user U3 performs shopping A using a credit card in February 2016, it is assumed that the payment due date for the purchase A to the credit card company is the end of March 2016. At this time, the fact that the user U3 does not pay for the shopping A at the end of March 2016 is referred to as “accrual 1”, for example. More specifically, “accrued 1” is a case where the balance of the bank account registered by the user U3 at the end of March 2016, which is the payment deadline, is insufficient, and the price for shopping A cannot be withdrawn. Point to. Further, for example, the fact that the user U3 does not pay for the shopping A even after the end of April 2016, which is the month following the payment due date, is referred to as “accrued 2”. More specifically, “accrued 2” means that the balance of the bank account registered by the user U3 is insufficient even at the end of April 2016, which is the month after the payment deadline, and the purchase A is deducted. This refers to cases where there is no such thing. Further, the fact that the user U3 does not pay for the shopping A even after the end of May 2016, which is two months after the payment deadline, is referred to as “accrued 3”. More specifically, “accrued 3” means that the balance of the bank account registered by the user U3 is insufficient even at the end of May 2016, which is the month after the payment deadline, and the purchase A is deducted. This refers to cases where there is no such thing. When the user U3 becomes “accrued 3”, the fact that he / she has defaulted is recorded in the credit information.

[2. Example of information processing)
Next, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. In the example illustrated in FIG. 2, the information processing apparatus 100 uses the first model M1 described in FIG. 1 to determine the second user from the information regarding the action history on the network of the second user who is a new applicant for a credit card. Calculate an index value for whether or not the company will default.

  More specifically, the information processing apparatus 100 calculates a default probability, which is a probability that the second user will default, by inputting information related to the behavior history on the second user's network to the first model M1. To do.

  The information processing apparatus 100 uses the credit card application date by the second user as a reference date as information regarding the action history on the second user's network, and the second user's network in the period 1 (= 1 year) before the reference date Information on the above commercial transaction history, browsing history, etc. is used. For example, if the credit card application date by the second user U1 is February 1, 2018, the information processing apparatus 100 uses the information regarding the behavior history on the network of the second user U1 who is a new user as of February 2017. Information relating to a business transaction history, a browsing history, etc. on the network of the second user U1 for one year from January 1 to January 31, 2018 is used.

  In addition, the information processing apparatus 100 uses a credit card application date by the second user as a reference date, and sets a default probability that is a probability that the second user will default on a period 2 (= 1 year and three months) after the reference date. calculate. For example, in the case of the second user U1 described above, the information processing apparatus 100 sets the default probability that is the probability that the second user U1 will default on debt as one year from February 1, 2018 to April 30, 2019. A default probability is calculated, which is the probability that the second user U1 will default in three months.

  Subsequently, the information processing apparatus 100 estimates the creditworthiness of the second user based on the calculated default probability. For example, if the calculated default probability is below a predetermined threshold, the information processing apparatus 100 considers that the second user is unlikely to default, and the second user has sufficient credit to issue a credit card. Estimate that there is power. On the other hand, if the calculated default probability is equal to or greater than a predetermined threshold, the information processing apparatus 100 considers that the second user has a high probability of defaulting, and the second user is sufficient to issue a credit card. Estimate that there is no creditworthiness. Subsequently, when estimating the creditworthiness of the second user, the information processing apparatus 100 transmits information on the creditworthiness of the second user estimated to the determination device 200 that is a server device managed by the credit card company. When the determination device 200 receives information related to the creditworthiness of the second user from the information processing device 100, based on the information related to the creditworthiness of the second user, whether or not the second user is a user who can issue a credit card. Determine. If the determination device 200 determines that the second user is a user who can issue a credit card, the determination device 200 issues a credit card to the second user.

  As described above, the information processing apparatus 100 is a first action history that is an action history before a first user is issued a credit card, among action histories on a network of a first user who has issued credit cards. Get information about. Then, the information processing apparatus 100 is connected to the network of the second user who is the object of the new credit card credit based on the acquired information on the first action history and the record of whether or not the first user has defaulted. The second user's creditworthiness is estimated from the information related to the second behavior history that is the behavior history of the second user. For example, the information processing apparatus 100 calculates a default probability, which is a probability that the user will default. Then, the information processing apparatus 100 estimates the user's creditworthiness from the calculated default probability. As a result, the information processing apparatus 100 can appropriately estimate the creditworthiness of a user who has no problem in creditworthiness, for example, although the credit information has been damaged due to delinquencies in the past, for example. .

  In the past credit examination, the user's creditworthiness could be estimated only based on credit information acquired from an external credit information agency. Therefore, a user whose credit information has been damaged even once is presumed to have no creditworthiness in the credit examination, and it has been determined that a credit card cannot be issued. However, in practice, it is known that there are a certain number of users with creditworthiness among users who are determined not to issue credit cards. Despite this situation, there has been no way to remedy such users in credit reviews so far. With the information processing apparatus 100 according to the present invention, the user's creditworthiness can be estimated from a different axis from the credit information. That is, the information processing apparatus 100 can estimate the user's creditworthiness based on the action history on the network. In other words, since the credit information has been damaged due to delinquencies in the past by the information processing apparatus 100, the user's creditworthiness that has no problem in creditworthiness is accurately estimated from the users who have failed the conventional credit examination. I was able to do that. The information processing apparatus 100 can now issue a credit card for a user who has no problem with creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  2 illustrates an example in which the information processing apparatus 100 calculates the default probability and estimates the creditworthiness of the second user from the calculated default probability. However, the default probability calculated by the information processing apparatus 100 is determined by the determination apparatus 200. The determination device 200 may estimate the creditworthiness of the second user based on the default probability.

[3. Configuration of information processing system]
The configuration of the information processing system 1 including the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the information processing system 1 according to the embodiment. As illustrated in FIG. 3, the information processing system 1 according to the embodiment includes a user terminal 10, a credit information agency server 20, an electronic commerce server 30, a content server 40, a search server 50, and an SNS (Social Networking Service) server 60, information processing apparatus 100, and determination apparatus 200 are included. These various apparatuses are communicably connected via a network N (for example, the Internet) in a wired or wireless manner.

  The information processing system 1 shown in FIG. 3 includes a plurality of user terminals 10, a plurality of determination devices 200, a plurality of credit information agency servers 20, a plurality of electronic commerce servers 30, a plurality of May include a plurality of content servers 40, a plurality of search servers 50, a plurality of SNS servers 60, and a plurality of information processing apparatuses 100.

  The user terminal 10 is an information processing device used by the second user U1. For example, the user terminal 10 is a tablet terminal, a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 10 acquires the web page from the determination apparatus 200 by accessing the determination apparatus 200, and displays the acquired web page on the display screen. The user terminal 10 transmits information related to the credit card membership application to the determination device 200 in response to the operation of the second user U1 through the acquired web page.

  The credit information institution server 20 is a server device managed by a credit information institution that provides a credit check service for checking user credit information. For example, the credit information institution server 20 investigates the credit information of the user, and contract information related to credit transactions such as credits and loans, information on credit history that is a transaction history such as repayment / payment status, usage balance (credit information) ). When a user has defaulted (default) or long-term delinquency in the past, there remains a record that default or long-term delinquency has occurred in the credit information for a predetermined period. For example, for credit card payments, the fact that a default has occurred is recorded in the credit information if the user does not pay the credit card even after three months from the payment deadline. When the credit information institution server 20 receives a credit information acquisition request from the determination device 200, the credit information organization server 20 transmits the credit information to the determination device 200.

  The electronic commerce server 30 is a server device that provides electronic commerce services such as shopping services and auction services. For example, the electronic commerce server 30 holds information related to a commercial transaction history that is a usage history of the user's electronic commercial service. For example, the electronic commerce server 30 uses the number of purchases of products and the like by the user, the total amount of purchases, the number of points used, the number of purchases for each payment method, the payment status of membership fees, the evaluation in interpersonal transactions, etc. The information of is retained. The electronic commerce server 30 also provides information on the user's bid history, successful bid history, and exhibition history for the auction service by the user, such as the bid price, bid count, successful bid price, successful bid count, etc. Hold. Upon receiving a commercial transaction history acquisition request from the information processing apparatus 100, the electronic commerce server 30 transmits the commercial transaction history to the information processing apparatus 100.

  The content server 40 is a server device that provides content distribution services such as news articles. For example, the content server 40 holds information related to the browsing history of content by the user. When the content server 40 receives an acquisition request for information related to the browsing history from the information processing apparatus 100, the content server 40 transmits information related to the browsing history to the information processing apparatus 100.

  The search server 50 is a server device that provides a search service. For example, the search server 50 holds information related to a search history that is a history of search queries searched by the user. When the search server 50 receives an acquisition request for information related to the search history from the information processing apparatus 100, the search server 50 transmits information related to the search history to the information processing apparatus 100.

  The SNS server 60 is a server device that provides an SNS service. For example, the SNS server 60 holds information regarding the usage history of the SNS service used by the user. When the SNS server 60 receives an acquisition request for information regarding the usage history of the SNS service from the information processing device 100, the SNS server 60 transmits information regarding the usage history of the SNS service to the information processing device 100.

  The information processing apparatus 100 is a server apparatus that performs the first model generation process described with reference to FIG. The information processing apparatus 100 is a server apparatus that performs the information processing described with reference to FIG. The information processing apparatus 100 acquires, from various servers, information related to the user's network action history used in the first model generation process described in FIG. 1 and the information processing described in FIG. For example, the information processing apparatus 100 acquires information related to the user's electronic commerce history from the electronic commerce server 30. In addition, the information processing apparatus 100 acquires information related to the user browsing history from the content server 40. Further, the information processing apparatus 100 acquires information related to the user search history from the search server 50. In addition, the information processing apparatus 100 acquires information regarding the use history of the user's SNS service from the SNS server 60. In addition, the information processing apparatus 100 acquires user attribute information from the determination apparatus 200 and the electronic commerce server 30. In addition, the information processing apparatus 100 acquires a record of whether or not the user has defaulted from the determination apparatus 200.

  The determination device 200 is a server device managed by a credit card issuing company (so-called issuer). When receiving a credit card issuance request from the user terminal 10 of a new user who is a new credit card applicant, the determination device 200 examines the new user. First, the determination apparatus 200 acquires the new user's credit information from the credit information institution server 20, and examines whether the new user has been delinquent or defaulted in the past. If there is no problem in the credit history examination, the determination device 200 passes the examination. Then, the determination apparatus 200 issues a credit card to the new user.

  On the other hand, the determination apparatus 200 requests the information processing apparatus 100 to estimate the creditworthiness of a new user who is rejected in the credit information examination. For example, the determination apparatus 200 requests the information processing apparatus 100 to estimate the creditworthiness of the new user. When the determination apparatus 200 receives information on the creditworthiness of the new user from the information processing apparatus 100, the determination apparatus 200 determines whether the new user is a user who can issue a credit card based on the information on the creditworthiness of the new user. . If the determination device 200 determines that the new user is a user who can issue a credit card, the determination device 200 issues a credit card to the new user. On the other hand, if the determination apparatus 200 determines that the new user is not a user who can issue a credit card, the determination apparatus 200 does not issue a credit card to the new user. In addition, the determination apparatus 200 determines whether the new user is a user who can issue a credit card comprehensively by combining the examination result of the credit information and the information regarding the creditworthiness received from the information processing apparatus 100. May be. And when the determination apparatus 200 determines that there is no problem in the comprehensive determination, the determination apparatus 200 may issue a credit card to the new user.

  Further, when the determination apparatus 200 receives from the information processing apparatus 100 an acquisition request for a record of whether or not a user who has issued credit cards has defaulted, the information about the record of whether or not the user has defaulted is displayed. It transmits to the processing apparatus 100.

  In the example illustrated in FIG. 3, the information processing apparatus 100 and the determination apparatus 200 are illustrated as separate apparatuses. However, the information processing apparatus 100 and the determination apparatus 200 may be integrated. Specifically, when estimating the creditworthiness of the second user, the information processing apparatus 100 determines whether the second user is a user who can issue a credit card based on information on the creditworthiness of the second user. judge. Subsequently, when the information processing apparatus 100 determines that the second user is a user who can issue a credit card, the information processing apparatus 100 issues a credit card to the second user.

[4. Configuration of information processing apparatus]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As illustrated in FIG. 4, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the information processing apparatus 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wirelessly. For example, the communication unit 110 includes the user terminal 10, the credit information institution server 20, the electronic commerce server 30, the content server 40, the search server 50, the SNS server 60, and the determination device 200. Send and receive information between them.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 4, the storage unit 120 includes a user information storage unit 121, a repayment record storage unit 122, and a model storage unit 123.

(User information storage unit 121)
The user information storage unit 121 stores various types of information related to the first user who has issued credit cards. FIG. 5 shows an example of a user information storage unit according to the embodiment. In the example illustrated in FIG. 5, the user information storage unit 121 includes “user ID”, “period category”, “user attribute”, “commerce transaction history”, “browsing history”, “search history”, “SNS usage history”, and the like. Have items.

  “User ID” indicates identification information for identifying a first user who has issued a credit card. The “period division” indicates a period in which the period 1 (= 1 year) before the reference date is divided into 12 sections every month, with the credit card issuance date for the first user as the reference date. For example, in the example shown in the first record in FIG. 5, the period division “first month” indicates the first month of period 1 (= 1 year). For example, in the example shown in the second record in FIG. 5, the period division “second month” indicates the next month of period 1 (= 1 year). For example, in the example shown in the fifth record in FIG. 5, the period division “12th month” indicates the last month of period 1 (= 1 year).

  “User attribute” indicates the attribute information of the first user every month in the period 1 (= 1 year) before the reference date with the credit card issue date for the first user as the reference date. For example, “user attribute” indicates attribute information on a date determined every month (for example, 27th of every month) as attribute information of the first user for each month in period 1. Specifically, the user attribute information is customer attribute information of the user as a credit card company customer acquired from the determination device 200. For example, the user attribute information is demographic information such as the user's gender, age, occupation, annual income, and residence. The user attribute information may be information combined with information acquired from the electronic commerce server 30. In the example shown in the first record in FIG. 5, the user attribute “(1) user attribute # U11” indicates attribute information of the first user U11 in the first month of period 1.

  The “commercial transaction history” indicates information related to the first user's commercial transaction history for each month in the period 1 before the reference date with the credit card issue date for the first user as the reference date. In the example shown in the first record of FIG. 5, the user attribute “(1) commerce history # U11” indicates the commerce history of the first user U11 in the first month of period 1 before the reference date shown in FIG. Correspond to information about.

  The “browsing history” indicates information related to the browsing history of the first user every month in the period 1 before the reference date with the credit card issue date for the first user as the reference date. The browsing history includes an access history that the user has selected predetermined advertisement content. In the example shown in the first record in FIG. 5, the browsing history “(1) browsing history # U11” is the browsing history of the first user U11 in the first month of the period 1 before the reference date shown in FIG. Correspond to information about.

  “Search history” indicates information related to the search history of the first user for each month in the period 1 before the reference date with the credit card issuance date for the first user as the reference date. In the example shown in the first record in FIG. 5, the search history “(1) search history # U11” is the search history of the first user U11 in the first month of period 1 before the reference date shown in FIG. Correspond to information about.

  “SNS usage history” indicates information related to the SNS usage history of the first user every month in the period 1 before the reference date, with the credit card issuance date for the first user as the reference date. In the example shown in the first record in FIG. 5, the SNS usage history “(1) SNS usage history # U11” indicates that the first user U11 in the first month of period 1 before the reference date shown in FIG. This corresponds to information related to the SNS usage history.

(Repayment record storage unit 122)
The repayment record storage unit 122 stores various types of information related to the repayment record of the first user who has a credit card issue record. FIG. 6 shows an example of the repayment record storage unit 122 according to the embodiment. In the example illustrated in FIG. 6, the repayment record storage unit 122 includes items such as “user ID”, “loan amount (yen)”, and “repayment record”.

  “User ID” indicates identification information for identifying the first user. “Loan amount (yen)” indicates the loan amount for the first user. The “repayment record” indicates a record of whether or not the first user has defaulted in a period 2 (= one year and three months) after the reference date with the credit card issuance date for the first user as the reference date. . In the example shown in the first record in FIG. 6, the first user identified by the user ID “U11” (user U11) corresponds to the first user U11 shown in FIG. The loan amount “200,000 (yen)” indicates that the loan amount for the first user U11 is 200,000 yen. The repayment record “x” indicates that the first user U11 has defaulted in the period 2 after the reference date, with the credit card issuance date for the first user U11 as the reference date.

(Model storage unit 123)
The model storage unit 123 stores information related to the first model M1 generated by the information processing apparatus 100. Specifically, the model storage unit 123 stores a “model ID” for identifying the first model generated by the information processing apparatus 100 in association with the model data of the first model M1. For example, the first model identified by the model ID “M1” corresponds to the first model M1 of FIGS.

(Control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. The various programs (corresponding to an example of the generation program) are executed by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a generation unit 132, an estimation unit 133, a reception unit 134, and a transmission unit 135, and realizes the information processing operation described below. Or run. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as information processing described later is performed.

(Acquisition part 131)
The acquisition unit 131 acquires information on the first action history that is an action history before the first user is given a predetermined credit among the action histories on the network of the first user who is given a predetermined credit. . Here, “predetermined credit has been granted” means that a financial institution or the like has been granted a loan, a credit line, a payment acceptance (guarantee), etc. This means that the credit limit has been increased. “Credit screening related to specified credit” refers to credit screening related to loans, credit lines, payment acceptance (guarantee), etc. provided to users by financial institutions, etc., and credits related to available credits provided to users by credit card companies. This means a credit examination concerning a change in a credit limit such as a review or an increase or decrease in a credit limit provided to a user by a credit card company.

  Specifically, the acquisition unit 131 obtains information on the first action history, which is an action history before the first user has a credit card, out of the action history on the network of the first user who has issued credit cards. get. For example, the acquisition unit 131 uses the credit card issuance date for the first user in the action history on the network of the first user as a reference date, and the network of the first user in the period 1 (= 1 year) before the reference date The information regarding the 1st action history which is the upper action history is acquired. For example, the acquisition unit 131 may acquire information on the action history on the network of the first user in the period 1 every month. And the acquisition part 131 will be stored in the user information storage part 121, if the information regarding a 1st action history is acquired. For example, the acquisition unit 131 acquires information about the first action history every month, and stores the information about the first action history acquired every month in the user information storage unit 121 in association with the period section. To do. In addition, the acquisition part 131 does not necessarily acquire the information regarding the action history on a 1st user's network every month. For example, the acquisition unit 131 may acquire information related to the behavior history of the first user on the network every predetermined period (for example, every day or every four months).

  For example, the acquisition unit 131 acquires information related to the first user's commercial transaction history for each month in the period 1 before the reference date from the electronic commercial transaction server 30. For example, the acquisition unit 131 uses information relating to the first user's commercial transaction history as the number of purchases, purchase price, number of points used, number of purchases for each payment method, the number of purchases for each month in the period 1 in the electronic commerce service, member Acquire information related to the payment status (non-payment of membership fees, etc.) and evaluations between individuals (evaluation based on numerical values in 5 stages from 1 to 5 and evaluation based on discrete values such as excellence, goodness, and goodness) . In addition, the acquisition unit 131 includes, as information related to the first user's commercial transaction history, bidding history (bidding price, number of bids, etc.) for each month in the period 1 to the auction service by the first user, successful bid history (successful bid price, Information on the number of successful bids) and the exhibition history (exhibition amount, number of exhibitions, etc.). And the acquisition part 131 will store the information regarding the 1st user's commercial transaction log | history in the item of the "commerce transaction log | history" of the user information storage part 121 for every period division, if the information regarding the commercial transaction log | history of a 1st user is acquired.

  For example, the acquisition unit 131 acquires the browsing history of the first user for each month in the period 1 before the reference date from the content server 40. For example, the acquisition unit 131 acquires, as information about the first user's browsing history, the number of times the first user browsed text content such as a predetermined news article every month. For example, the acquisition unit 131 acquires, as information about the first user's browsing history, the number of times the first user has viewed a predetermined video content every month. For example, the acquisition unit 131 acquires, as information about the browsing history of the first user, the number of times the first user has accessed a predetermined advertisement content every month. And if the acquisition part 131 acquires the information regarding a 1st user's browsing history, it will store the information regarding the acquired 1st user's browsing history in the item of "browsing history" of the user information storage part 121 for every period division.

  For example, the acquisition unit 131 acquires information related to the search history of the first user every month in the period 1 before the reference date from the search server 50. For example, the acquisition unit 131 acquires, as information about the search history of the first user, the number of searches that the first user has searched for a predetermined search query every month. For example, the acquisition unit 131 acquires the search frequency with which the first user has searched for a predetermined search query. For example, the acquisition unit 131 acquires whether or not the first user has searched for a predetermined search query. For example, the acquisition unit 131 acquires the score of the search query searched by the first user. For example, the acquisition unit 131 acquires a weight value such as tf-idf (Term Frequency, Inverse Document Frequency). For example, the acquisition unit 131 may determine a search query characteristic of the first user using a weight value such as tf-idf. Note that the acquisition unit 131 may acquire the weight of the co-occurrence word that co-occurs in the search query searched by the first user. The weight of the co-occurrence word corresponds to, for example, a numerical value scored by tf-idf or the like, a predetermined index value based on the appearance rate of the co-occurrence word, and the like. And the acquisition part 131 will store the information regarding the search history of a 1st user in the item of "search history" of the user information storage part 121 for every period division, if the information regarding the search history of a 1st user is acquired.

  For example, the acquisition unit 131 acquires information about the SNS usage history of the first user for each month in the period 1 before the reference date from the SNS server 60. For example, the acquisition unit 131 acquires the number of times the first user has used a predetermined SNS as information related to the SNS usage history of the first user. For example, the acquisition unit 131 acquires the number of postings posted by the first user to a predetermined SNS as information related to the SNS usage history of the first user. For example, the acquisition unit 131 acquires the number of appearances of keywords included in a posted article posted by the first user to a predetermined SNS as information related to the SNS usage history of the first user. For example, the acquisition unit 131 may acquire, for each posted article posted on the SNS, a word extracted as a word characterizing a short sentence as a keyword and the number of appearances. For example, the acquisition unit 131 may extract a keyword that characterizes a short sentence by using an algorithm that scores each word that appears in the short sentence, such as tf-idf. And the acquisition part 131 will acquire the information regarding the SNS utilization history of the 1st user in the item of "SNS utilization history" of the user information storage part 121 for every period division, if the information regarding the SNS utilization history of the 1st user is acquired. Store.

  Moreover, the acquisition part 131 acquires the track record whether the 1st user caused default. Specifically, the acquisition unit 131 uses the credit card issuance date for the first user as a reference date, and determines whether or not the first user has defaulted in period 2 (= 1 year and three months) after the reference date. The result is acquired from the determination device 200. When the acquisition unit 131 acquires the record of whether or not the first user has defaulted, the acquisition unit 131 stores the acquired information in the repayment record storage unit 122.

(Generator 132)
Based on the information on the first behavior history acquired by the acquisition unit 131 and the information on whether or not the first user has defaulted, the generation unit 132 obtains the first information from the information on the second behavior history of the second user. 2 Generate a model that calculates an index value regarding whether or not the user will default. When the generation unit 132 generates a model, the generation unit 132 stores the generated model in the model storage unit 123.

  Specifically, the generation unit 132 includes information on a first action history that is an action history before the first user has a credit card among action histories on the network of the first user who has issued credit cards. Whether or not the second user will default on the basis of the information on the second behavior history of the second user who is a new applicant for a credit card, based on the record of whether or not the first user has defaulted A first model for calculating an index value for the is generated. For example, the generation unit 132 includes information regarding the first action history that is the action history before the first user has a credit card, and whether or not the first user has defaulted among the action history on the network of the first user. A first model that is generated based on the actual results, and calculates a default probability that is the probability that the second user will default on default when information about the second action history of the second user is input. A first model M1 is generated.

  Below, an example of the model which the production | generation part 132 produces | generates is shown. Note that the model generated by the generation unit 132 is not limited to the following model, and is a model generated based on information on the first action history and a record of whether or not the first user has defaulted. 2 Any model may be used as long as the model outputs a default probability that is a probability that the second user will default on default when information on the action history is input.

  Specifically, the generation unit 132 sets the result information indicating whether or not the first user has defaulted as an objective variable in machine learning. And the production | generation part 132 makes each information regarding the action history on the network of the 1st user for every month in the period 1 an explanatory variable (feature). In other words, the generation unit 132 sets each piece of information regarding the action history on the network of the first user in the period division “M month” (M = 1, 2,..., 12) of the period 1 as an explanatory variable (feature). .

  For example, the generation unit 132 refers to the user information storage unit 121, and relates to the business transaction history on the network of the first user in the period division “M month” (M = 1, 2,..., 12) of the period 1. Is a feature. For example, the generation unit 132 sets the number of purchases, the purchase amount, the number of used points, and the payment method by the first user in the period division “M month” (M = 1, 2,..., 12) of the period 1. Number of purchases, payment status of membership fees (whether or not non-payment of membership fees, etc.), evaluation in individual transactions (evaluation based on numerical values of 5 levels from 1 to 5 and evaluation based on discrete values such as excellent / good / good) Each information is a feature. For example, the generation unit 132 sets the bid amount, the number of bids, the successful bid amount, the successful bid number, the exhibition for the auction service by the first user in the period division “M month” (M = 1, 2,..., 12) of the period 1. Information on the amount of money, the number of times of listing, etc. is the feature.

  In addition, the generation unit 132 refers to the user information storage unit 121, and relates to the browsing history of the first user on the network in the period division “M month” (M = 1, 2,..., 12) of the period 1. Is a feature. For example, the generation unit 132 uses the number of times the first user browses text content such as a predetermined news article in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. . For example, the acquisition unit 131 uses the number of times the first user views a predetermined moving image content in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the acquisition unit 131 uses the number of times the first user has accessed predetermined advertisement content in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature.

  In addition, the generation unit 132 refers to the user information storage unit 121, and relates to the search history of the first user on the network in the period division “M month” (M = 1, 2,..., 12) of the period 1. Is a feature. For example, the generation unit 132 uses the number of searches that the first user has searched for a predetermined search query in the period division “M month” of period 1 (M = 1, 2,..., 12) as a feature. For example, the generation unit 132 uses the search frequency at which the first user searches for a predetermined search query in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the generation unit 132 uses the search presence / absence in which the first user searches for a predetermined search query in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the generation unit 132 uses the score of the search query searched by the first user in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the generation unit 132 uses a weight value such as tf-idf of the search query searched by the first user in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. .

  Further, the generation unit 132 refers to the user information storage unit 121 and relates to the SNS usage history of the first user on the network in the period division “M month” (M = 1, 2,..., 12) of the period 1. Make information a feature. For example, the generation unit 132 uses the number of times the first user has used a predetermined SNS in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the generation unit 132 uses the number of postings made by the first user to the predetermined SNS in the period division “M month” (M = 1, 2,..., 12) of period 1 as a feature. For example, the generation unit 132 determines the number of appearances of keywords included in a posted article posted by the first user to a predetermined SNS in the period division “M month” (M = 1, 2,..., 12) of the period 1. And

  Then, the generating unit 132 generates a model using the objective variable and the explanatory variable. The generation unit 132 generates a model using various explanatory variables. For example, the generation unit 132 can use any information stored in the user information storage unit 121 as an explanatory variable.

  For example, the generating unit 132 generates a result information indicating whether or not the first user has defaulted, and an expression indicating information regarding an action history before the first user has a credit card. Furthermore, the generation unit 132 has a weight of each piece of information regarding the action history before the first user holds the credit card with respect to the event as a result of whether or not the first user has defaulted. Learn and calculate. Thereby, the production | generation part 132 can acquire the information of how much each information contributes with respect to the event that a user causes default. For example, the generation unit 132 creates the following formula (1).

y = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ ... + ω _N · x _N (1) (N is an arbitrary number)

  The above equation (1) is created for each individual first user, for example. In the above formula (1), “y” indicates an event “whether or not the first user has defaulted”. In learning, if the first user U11 who has defaulted is taken as correct data, “y” takes a value of “1”. In learning, if the correct data is the first user U12 who did not default, “y” takes a value of “0”.

Further, in the above formula (1), “x” corresponds to each explanatory variable that is information (feature) about the action history on the network of the first user every month in period 1. That is, “x” is information (features) on the action history on the network of the first user in the period division “M month” of period 1 (M = 1, 2,..., 12). In the above formula (1), “ω” is a coefficient of “x” and indicates a predetermined weight value. Specifically, “ω ₁ ” is a weight value of “x ₁ ”, “ω ₂ ” is a weight value of “x ₂ ”, and “ω ₃ ” is a weight value of “x ₃ ”. It is. As described above, the above equation (1) is obtained by using the explanatory variable “x” corresponding to the feature information extracted from the information regarding the behavior history on the network of the first user every month in the period 1 and the predetermined weight value. It is created by combining variables including “ω” (for example, “ω ₁ · x ₁ ”).

For example, in the above formula (1), suppose that “x ₁ ” is “the number of purchases of the first user U11 for the first user U11 in the period division“ first month ”of period 1”. For example, “x ₁ ” is assumed to be “20 (times)”. Further, “x ₂ ” is assumed to be “the total amount of the purchase amount of the goods of the first user U11 in the period classification“ first month ”of period 1”. For example, “x ₂ ” is assumed to be “50,000 (yen)”. Further, “x ₃ ” is assumed to be “evaluation in the inter-individual transaction of the first user U11 in the period division“ first month ”of period 1”. For example, it is assumed that “x ₃ ” is “5” (when the inter-personal transaction evaluation is evaluated with five-stage numerical values from 1 to 5). In this case, the above equation (1) corresponding to the first user U11 can be expressed as the following equation (2).

y (first user U11 who defaulted) (= 1) = ω ₁ · (number of purchases of goods etc. of first user U11 in period category “first month” of period 1 (= 20 (times))) + Ω ₂ · (total amount of purchase amount of goods of the first user U11 in the period division “first month” of period 1 (= 50,000 (yen))) + ω ₃ · (period division of period 1 “ Evaluation in the interpersonal transaction of the first user U11 in the “first month” (= 5)) + ω _N · x _N (2)

The generation unit 132 generates an expression for each first user as in the above expression (2). Then, the generation unit 132 sets the generated expression as a machine learning sample. Then, the generation unit 132 derives a value corresponding to the predetermined weight value “ω” by performing calculation processing (regression learning) of a sample expression. That is, the generation unit 132 determines a predetermined weight value “ω” that satisfies the above equation (2). In other words, the generation unit 132 can determine the weight value “ω” indicating the influence of the predetermined explanatory variable on the objective variable “y”. For example, in response to an event “the first user U11 has defaulted”, “total amount of purchase price of the first user U11's products etc. in the period category“ first month ”of period 1” is another variable. The value of the weight value “ω ₂ ” corresponding to “total amount of purchase price of the first user U11 for the first user U11 in the period segment“ first month ”” Is larger than other variables.

  As described above, the generation unit 132 obtains the relationship between the tendency that the first user will default and the information (feature) related to the action history before the first user has a credit card. Generate a model. In other words, when the generation unit 132 inputs information on the behavior history on the network of the second user who is a new applicant for a credit card to the generated model, the information is “the second user causes default”. ", In other words, how similar the tendency is to the first user can be output. In the calculation process using the above equation (2), the left side is not set to “1” or “0” itself, but a predetermined error is assumed, and a value obtained by squaring the difference from the error is a minimum value. The optimal solution of “ω” may be calculated using a method such as a least square method that approximates to

  In addition, for example, the generation unit 132 has a high tendency that the first user whose evaluation value in the personal transaction of the first user U11 in the period division “12th month” of the period 1 is lower than a predetermined threshold, It is possible to generate a model that finds a tendency that a first user whose interpersonal transaction evaluation value is equal to or greater than a predetermined threshold is less liable to default. This means that if the value of the inter-personal transaction evaluation in the period category “12th month” of the second user's period 1 to be processed falls below a predetermined threshold, the second user may cause default in the future. Means high. In other words, “the numerical value of the interpersonal transaction evaluation in the period classification“ 12th month ”of period 1” has a heavy weight (as a feature for obtaining the correlation with the first user) for the result of “performing default”. It can be said that it is an element.

  Note that the generation unit 132 may generate the model using any learning algorithm. For example, the generation unit 132 generates a model using a learning algorithm such as a neural network, a support vector machine, clustering, reinforcement learning, or the like. As an example, when the generation unit 132 generates a model using a neural network, the model includes an input layer including one or more neurons, an intermediate layer including one or more neurons, and an output layer including one or more neurons. Have

  The model includes an input layer to which information on the second user's second action history is input, an output layer, and a first element belonging to any layer other than the output layer from the input layer to the output layer A second element whose value is calculated based on the first element and the weight of the first element, and the second user is obligated according to information on the predetermined second action history input to the input layer The computer is made to function to output from the output layer an index value relating to whether or not default occurs.

  The model includes an input layer to which information on the second user's second action history is input, an output layer, and a first element belonging to any layer other than the output layer from the input layer to the output layer Each of the layers other than the output layer with respect to the information on the predetermined second action history input to the input layer, the second element having a value calculated based on the first element and the weight of the first element In order to output from the output layer an index value regarding whether or not the second user will perform default by performing an operation based on the first element and the weight of the first element, with each element belonging to Make the computer work.

Here, it is assumed that the model is realized by a regression model represented by “y = ω ₁ * x ₁ + ω ₂ * x ₂ +... + Ω _i * x _i ”. In this case, the first element included in the model corresponds to input data (x _i ) such as x ₁ and x ₂ . The weight of the first element corresponds to the coefficient ω _i corresponding to x _i . Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can correspond to any node of the input layer, and the second element can be regarded as a node of the output layer.

  Further, it is assumed that the model is realized by a neural network having one or a plurality of intermediate layers such as a DNN (Deep Neural Network). In this case, the first element included in the model corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  The information processing apparatus 100 calculates an index value using a model having an arbitrary structure such as the above-described regression model or neural network. Specifically, in the model, when information related to the second action history of the second user is input, a coefficient is set so as to output an index value relating to whether or not the second user causes default. The information processing apparatus 100 calculates an index value using such a model.

  In the above example, the model outputs an index value related to whether or not the second user will default on the debt when the information about the action history on the network of the second user is input (model MX). ) Is shown. However, the model according to the embodiment may be a model generated based on a result obtained by repeatedly inputting / outputting data to / from the model MX. For example, the model is a model (model that has been learned so that the second user's behavior history on the network is input, and the index value regarding whether or not the second user that the model MX outputs defaults is output. MY). Alternatively, the model may be a model that has been learned so that information on an action history on a network of a predetermined second user is input and an output value of the model MY is output.

  When the information processing apparatus 100 performs a calculation process using GAN (Generative Adversarial Networks), the model may be a model that constitutes a part of the GAN.

(Estimation unit 133)
The estimation unit 133 is a second user who is a subject of a credit examination regarding a predetermined credit based on the information on the first action history acquired by the acquisition unit 131 and the result of whether or not the first user has defaulted. The second user's creditworthiness is estimated from the information regarding the second action history. Specifically, the estimation unit 133 estimates the creditworthiness of the second user when the reception unit 134 receives an examination request for the second user from the determination device 200. For example, the estimation unit 133 calculates the default probability of the second user as the creditworthiness of the second user. Moreover, the estimation part 133 may estimate a 2nd user's creditworthiness based on the calculated default probability. In addition, the estimation unit 133 may estimate the repayment ability of the second user based on the calculated default probability.

  More specifically, the estimation unit 133 determines the second action of the second user based on the information on the first action history acquired by the acquisition part 131 and the record of whether or not the first user has defaulted. An index value relating to whether or not the second user will default is calculated from the history information. For example, the estimation unit 133 uses the model generated by the generation unit 132 to calculate an index value related to whether or not the second user causes default. For example, the estimation unit 133 calculates an index value regarding whether or not the second user causes default by inputting information related to the second user's second behavior history to the first model generated by the generation unit 132. To do. For example, the estimation unit 133 calculates a default probability as an index value regarding whether or not the second user causes default.

  Subsequently, the estimation unit 133 estimates the creditworthiness of the second user based on the calculated index value. For example, when the calculated default probability falls below a predetermined threshold, the estimation unit 133 considers that the second user is unlikely to default, and the second user has sufficient creditworthiness to issue a credit card. Estimate that there is. On the other hand, when the calculated default probability is equal to or greater than a predetermined threshold, the estimation unit 133 considers that the second user is likely to default, and the second user has sufficient credit to issue a credit card. Estimate that there is no power.

(Reception unit 134)
The accepting unit 134 accepts a request for examination for the second user from the determination apparatus 200. For example, the reception unit 134 receives a request for examination for all new users from the determination device 200. For example, the reception unit 134 receives from the determination device 200 a request for screening for a new user who is rejected in the credit information screening.

(Transmitter 135)
The transmission unit 135 transmits the creditworthiness of the second user estimated by the estimation unit 133 to the determination device 200. Specifically, the transmission unit 135 transmits information regarding the presence or absence of the creditworthiness of the second user estimated by the estimation unit 133 to the determination device 200. Alternatively, the transmission unit 135 may transmit the default probability calculated by the estimation unit 133 to the determination apparatus 200.

[5. (Configuration of judgment device)
Next, the configuration of the determination apparatus 200 according to the embodiment will be described with reference to FIG. FIG. 7 is a diagram illustrating a configuration example of the determination apparatus 200 according to the embodiment. As illustrated in FIG. 7, the determination apparatus 200 includes a communication unit 210, a storage unit 220, and a control unit 230. The determination device 200 includes an input unit (for example, a keyboard and a mouse) that receives various operations from the administrator of the determination device 200 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 210)
The communication unit 210 is realized by a NIC or the like, for example. The communication unit 210 is connected to the network by wire or wirelessly, and transmits and receives information between the user terminal 10 and the information processing apparatus 100, for example.

(Storage unit 220)
The storage unit 220 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 7, the storage unit 220 includes a user information storage unit 221 and a repayment record storage unit 222.

(User information storage unit 221)
The user information storage unit 221 stores customer information of a user as a credit card company customer. Specifically, the user information storage unit 221 stores user attribute information as user customer information. For example, the user information storage unit 221 stores demographic information such as a user's sex, age, occupation, annual income, and residence as user attribute information. For example, the user information storage unit 221 stores attribute information related to a first user who has a credit card issue record. The user information storage unit 221 stores attribute information related to the second user who is a new applicant for a credit card. Further, the user information storage unit 221 stores the loan amount and the repayment record for the first user who has a credit card issuance record as customer customer information.

(Control unit 230)
Returning to the description of FIG. 7, the control unit 230 is a controller. For example, various programs (corresponding to an example of a generation program) stored in the storage device inside the determination device 200 are stored in the RAM by the CPU, the MPU, or the like. This is realized by being executed as a work area. The control unit 230 is a controller, and is realized by an integrated circuit such as an ASIC or FPGA, for example.

  As shown in FIG. 7, the control unit 230 includes a reception unit 231, a screening unit 232, an acquisition unit 233, a determination unit 234, and a service providing unit 235, and performs the information processing operation described below. Realize or execute. The internal configuration of the control unit 230 is not limited to the configuration illustrated in FIG. 7, and may be another configuration as long as the information processing described later is performed.

(Reception unit 231)
The accepting unit 231 accepts a credit card issuance request from the user terminal 10 of a new user who is a new credit card applicant. For example, the accepting unit 231 accepts a credit card issuance request from the new user's user terminal 10 via a page for accepting a credit card issuance request distributed to the new user's user terminal 10.

(Examination Department 232)
The examination unit 232 acquires the credit information of the second user from the credit information agency, and performs a credit examination based on the acquired credit information. For example, when the accepting unit 231 accepts a credit card issuance request, the examining unit 232 acquires the new user's credit information from the credit information institution server 20, and whether the new user has caused delinquency or default in the past. Review whether. If there is no problem in the credit information examination, the examination unit 232 passes the examination.

  On the other hand, the examination unit 232 requests the information processing apparatus 100 to estimate the creditworthiness of a new user who is rejected in the credit information examination. For example, the examination unit 232 requests the information processing apparatus 100 to estimate the creditworthiness of the new user.

  In addition, when the examination unit 232 receives from the information processing apparatus 100 an acquisition request for a record of whether or not a user who has issued a credit card has defaulted, the information about the record of whether or not the user has defaulted is displayed. It transmits to the processing apparatus 100.

(Acquisition unit 233)
The acquisition unit 233 acquires the creditworthiness of the second user. Specifically, the acquisition unit 233 is a first action history that is an action history before a first user is given a predetermined credit among action histories on a network of a first user who is given a predetermined credit. Based on the information on the second behavior history, which is the behavior history on the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the information on the first user and the record of whether or not the first user has defaulted The creditworthiness of the second user is acquired. Specifically, the acquisition unit 233 acquires information about the new user's creditworthiness estimated by the information processing apparatus 100 from the information processing apparatus 100.

  Alternatively, the acquisition unit 233 may acquire the second user by estimating the creditworthiness. For example, the acquisition unit 233 acquires the default probability calculated by the information processing apparatus 100 from the information processing apparatus 100. Subsequently, if the acquired default probability falls below a predetermined threshold, the acquisition unit 233 considers that the new user is unlikely to default, and the new user has sufficient creditworthiness to issue a credit card. Presume that there is. On the other hand, if the acquired default probability is greater than or equal to a predetermined threshold, the acquisition unit 233 regards the new user as having a high probability of defaulting, and the new user has sufficient creditworthiness to issue a credit card. Estimated not.

  In addition, for example, the acquisition unit 233 determines whether the second user has obtained information from the second user's second action history based on the information on the first action history and the record of whether or not the first user has defaulted. A model for calculating an index value related to whether or not default occurs may be acquired from the information processing apparatus 100. When the acquisition unit 233 acquires a model from the information processing apparatus 100, the acquisition unit 233 inputs information related to the second user's second behavior history to the acquired model, thereby indicating an index value regarding whether or not the second user will default. The default probability may be calculated.

(Determination unit 234)
The determination unit 234 determines whether or not a service related to a credit card can be provided to the second user based on the creditworthiness of the second user acquired by the acquisition unit 233. Specifically, when the determination unit 234 receives information related to the creditworthiness of the new user from the information processing apparatus 100, whether the new user is a user who can issue a credit card based on the information related to the creditworthiness of the new user. Determine whether or not. For example, the determination unit 234 determines the credit card for the second user based on the creditworthiness of the second user estimated from the information regarding the second user's second action history that has been rejected as a result of the screening by the screening unit 232. It is determined whether or not the service can be provided. For example, the determination unit 234 determines whether or not a credit card can be issued to the second user as the availability of the service related to the credit card for the second user. Note that the determination unit 234 determines whether or not the new user is a user who can issue a credit card comprehensively by combining the credit information examination result and the information regarding the creditworthiness received from the information processing apparatus 100. May be.

(Service provider 235)
The service providing unit 235 provides the credit card service to the second user when the determination unit 234 determines that the credit card service can be provided to the second user. Specifically, the service providing unit 235 issues a credit card to the new user when the determining unit 234 determines that the new user is a user who can issue a credit card. On the other hand, when the determining unit 234 determines that the new user is not a user who can issue a credit card, the service providing unit 235 does not issue a credit card to the new user.

[6. Generation process flow)
Next, a generation process procedure according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating a first model generation processing procedure according to the embodiment.

  As illustrated in FIG. 8, the information processing apparatus 100 obtains information regarding an action history on a network of a user who has issued a credit card, and information regarding an action history on the network before the user has the card. (Step S101).

  Subsequently, the information processing apparatus 100 determines whether or not the user who has issued is on the network of the new user based on the information about the action history on the network before the card is held and whether or not the user has defaulted. A first model for calculating a default probability of a new user is generated from the information regarding the behavior history of the user (step S102).

[7. Information processing flow)
Next, an information processing procedure according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating an information processing procedure according to the embodiment.

  As illustrated in FIG. 9, the information processing apparatus 100 determines whether an examination request for a new user has been received from the determination apparatus 200 (step S <b> 201). If the information processing apparatus 100 determines that an examination request for a new user has not been accepted (step S201; No), the information processing apparatus 100 waits until an examination request for a new user is accepted.

  Further, when the information processing apparatus 100 determines that the examination request for the new user has been received (step S201; Yes), the information processing apparatus 100 acquires information regarding the action history on the network of the new user (step S202).

  Subsequently, the information processing apparatus 100 calculates the default probability of the new user by inputting the information related to the action history on the network of the new user into the first model (Step S203).

  Subsequently, the information processing apparatus 100 estimates the new user's creditworthiness (step S204).

  Note that the procedure of step S201 and the procedure of steps S202 to S203 are out of order. For example, when the information regarding the new user is received from the determination apparatus 200, the information processing apparatus 100 acquires information regarding the action history on the network of the new user. Subsequently, the information processing apparatus 100 calculates the default probability of the new user by inputting the information related to the action history on the network of the new user into the first model. Subsequently, the information processing apparatus 100 estimates a new user's creditworthiness. Thereafter, the information processing apparatus 100 may accept an examination request for a new user from the determination apparatus 200.

[8. (Modification)
The information processing system 1 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, in the following, another embodiment of the information processing system 1 will be described. In addition, the same code | symbol is attached | subjected to the part same as embodiment, and description is abbreviate | omitted.

[8-1. (In the case of developing credit)
On-the-job credit refers to examining (checking) the use status and repayment status of a user's credit after granting credit such as a credit card. The credit on the way is performed for the purpose of reviewing (changing) the credit limit (usage limit) for the user, preventing the occurrence of delinquency, and early detection of counterfeit / illegal cards. For example, if the credit card company determines that the user is likely to default on the credit due to the credit in progress, the credit card company stops using the credit card or reduces the credit limit. On the other hand, if the credit card company determines that the credit can be collected from the user even if the credit limit is increased due to the credit in progress, the credit card company proposes an increase in the credit limit to the user.

  1 and 2 show an example in which the information processing apparatus 100 estimates the creditworthiness of a new user who is a new applicant for a credit card. It may be estimated. This point will be described with reference to FIGS.

[8-1-1. Example of second model generation process]
First, an example of the second model generation process according to the modification will be described with reference to FIG. FIG. 10 is a diagram illustrating an example of the second model generation process according to the modification. The information processing apparatus 100 estimates the creditworthiness of a developing user who is a subject of a credit card developing credit in cooperation with a credit card company. In the following description, the subject of credit card halfway credit is referred to as a halfway user as appropriate.

  In the example illustrated in FIG. 10, the generation unit 132 includes information regarding an action history before the first user's credit frame is increased, among the action histories on the network of the first user who has a credit frame increase record. Based on the record of whether or not the first user has defaulted after an increase in the number of slots, the second user is obliged from the information regarding the behavior history on the network of the second user who is the subject of credit on the credit card. A second model for calculating an index value relating to whether or not default occurs is generated.

  That is, the generation unit 132 calculates a default probability that is a probability that the second user will default on the debt when the information regarding the behavior history on the network of the second user who is the subject of the credit card mid-course credit is input. A second model M2 to be generated is generated. For example, the generating unit 132 sets the first user who has a credit frame increase record as the correct answer data (teacher data, objective variable), and the credit frame of the first user is increased in the action history on the network of the first user. A regression learning model such as a support vector machine having information (explanatory variable) as information on the first action history that is an action history before being framed is generated.

  The generation unit 132 sets the date 1 of the credit limit for the first user as a reference date as information on the action history of the first user before the credit limit of the first user is increased, and a period 1 before the reference date. Information regarding the business transaction history, browsing history, etc. on the network of the first user in (= 1 year) is used. For example, assuming that the credit limit increase date for the first user U21 is February 1, 2016, the generation unit 132 uses February 1, 2015 as information regarding the action history on the network of the first user U21. 1 to January 31, 2016, information on the business transaction history, browsing history, etc. on the network of the first user U21 is used.

  In addition, the generation unit 132 sets the credit limit increase date for the first user as the reference date as a record of whether or not the first user has defaulted after the increase, and the period 2 after the reference date (= 1 year) 3 months) is used to determine whether the first user has defaulted after an increase. For example, in the case of the first user U21 described above, the generation unit 132 determines whether the first user U21 has defaulted as a result of 1 year 3 from February 1, 2016 to April 30, 2017. A record of whether or not the first user U21 has defaulted in a month is used. For example, the generation unit 132 uses a record that the first user U21 has defaulted during one year and three months from February 1, 2016 to April 30, 2017.

[8-1-2. Example of information processing)
Next, an example of information processing according to the modification will be described with reference to FIG. FIG. 11 is a diagram illustrating an example of information processing according to the modification. In the example illustrated in FIG. 11, the information processing apparatus 100 uses the second model M2 described in FIG. 10 to calculate the first information from the information regarding the behavior history on the network of the second user who is a credit card target credit. 2 Calculate an index value regarding whether or not the user will default.

  More specifically, the estimation unit 133 inputs the information related to the behavior history on the network of the second user who is the subject of the credit card halfway credit to the second model M2 described in FIG. 2 Calculate a default probability, which is the probability that the user will default. For example, the estimation unit 133 inputs information related to the behavior history on the network of the second user U2 who is a credit card target credit to the regression learning model such as the support vector machine described in FIG. A default probability, which is a probability that the second user U2 will default, is calculated.

  The estimation unit 133 uses the credit date of the on-going credit for the second user as a reference date as information on the action history on the network of the second user who is the subject of the credit card on-the-go credit, and the period 1 ( = 1 year), information on the business transaction history, browsing history, etc. on the second user's network is used. For example, assuming that the credit date of the credit on the way to the second user U2 is February 1, 2018, the estimation unit 133 uses the information on the action history on the network of the second user U2 who is the way user as of February 2017. Information relating to the business transaction history, browsing history, etc. on the network of the second user U2 for one year from January 1 to January 31, 2018 is used.

  In addition, the estimation unit 133 uses the credit date of the developing credit for the second user as a reference date as an index value related to whether or not the second user will default, and the period 2 after the reference date (= one year and three months) ) To calculate an index value regarding whether or not the second user will default. For example, in the case of the second user U2 described above, the estimation unit 133 sets the default probability that is the probability that the second user U2 will default to 1 year 3 from February 1, 2018 to April 30, 2019. A default probability is calculated, which is the probability that the second user U2 will default on a month.

  Subsequently, the estimating unit 133 estimates the second user's creditworthiness based on the calculated default probability. For example, when the calculated default probability falls below a predetermined threshold, the estimation unit 133 considers that the second user is unlikely to default, and the second user has sufficient credit to increase the credit line. Estimate that there is power. On the other hand, when the calculated default probability is equal to or higher than the predetermined threshold, the estimation unit 133 considers that the second user is likely to default, and the second user is sufficient to increase the credit limit. Estimate that there is no creditworthiness. Subsequently, the transmission unit 135 transmits information on the creditworthiness of the second user estimated by the estimation unit 133 to the determination device 200. The determination unit 234 determines whether or not it is possible to change a credit frame related to a predetermined credit for the second user, as to whether or not a service related to a credit card can be provided to the second user. Specifically, when the determination unit 234 receives information related to the creditworthiness of the second user from the information processing apparatus 100, the second user can increase the credit frame based on the information related to the creditworthiness of the second user. It is determined whether or not the user is a user. When the determination unit 234 determines that the second user is a user who can increase the credit frame, the service providing unit 235 increases the credit frame for the second user. On the other hand, when the determination unit 234 determines that the second user is not a user who can increase the credit frame, the service providing unit 235 reduces the credit frame for the second user. Note that reducing the credit limit includes not only reducing the available loan amount but also stopping the use of the credit card itself.

  As described above, the information processing apparatus 100 is the first action history that is before the first user's credit frame is increased, out of the action history on the network of the first user who has a credit frame increase record. Get information about action history. Then, the information processing apparatus 100 determines whether or not the second user who is the object of credit card halfway credit based on the acquired information on the first action history and the record of whether or not the first user has defaulted after the increase of the frame. The creditworthiness of the second user is estimated from the information related to the second action history which is the action history on the network. Thereby, for example, the information processing apparatus 100 appropriately estimates the creditworthiness of the user who has no problem in creditworthiness, although the credit information has been damaged due to arrears before the credit on the way, but the situation has changed. Can do. That is, the information processing apparatus 100 can make it possible to increase the credit card credit limit for a user who has no problem with creditworthiness. In addition, the information processing apparatus 100 can allow the credit card credit limit to be reduced for a user having a problem with creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

[8-1-3. Generation process flow)
Next, a generation process procedure according to the modification will be described with reference to FIG. FIG. 12 is a flowchart illustrating a second model generation processing procedure according to the modification.

  As illustrated in FIG. 12, the information processing apparatus 100 is information regarding an action history on the network of the user whose credit frame is increased, and the action history on the network before the user is increased in the credit frame. The information regarding is acquired (step S301).

  Subsequently, the information processing apparatus 100 uses the information regarding the action history on the network before the user who has the credit frame increase record and the credit limit increase, and whether or not the user has defaulted. Based on the information regarding the behavior history of the developing user on the network, a second model for calculating the default probability of the developing user is generated (step S302).

[8-1-4. Information processing flow)
Next, an information processing procedure according to the modification will be described with reference to FIG. FIG. 13 is a flowchart illustrating an information processing procedure according to the modification.

  As illustrated in FIG. 13, the information processing apparatus 100 determines whether an examination request for a halfway user has been received from the determination apparatus 200 (step S <b> 401). If the information processing apparatus 100 determines that the examination request for the developing user has not been accepted (step S401; No), the information processing apparatus 100 waits until the examination request for the developing user is accepted.

  In addition, when the information processing apparatus 100 determines that the examination request for the developing user has been received (step S401; Yes), the information processing apparatus 100 acquires information regarding the behavior history of the developing user on the network (step S402).

  Subsequently, the information processing apparatus 100 calculates the default probability of the developing user by inputting the information related to the action history on the network of the developing user into the second model (Step S403).

  Subsequently, the information processing apparatus 100 estimates the creditworthiness of the user on the way (step S404).

  Note that the procedure of step S401 and the procedure of steps S402 to S403 are out of order. For example, when the information processing apparatus 100 receives information about the halfway user from the determination apparatus 200, the information processing apparatus 100 acquires information about the behavior history of the halfway user on the network. Subsequently, the information processing apparatus 100 calculates the default probability of the developing user by inputting the information related to the action history on the network of the developing user into the second model. Thereafter, the information processing apparatus 100 may accept an examination request for the halfway user from the determination apparatus 200.

[8-2. (Estimation process with greater weight for new behavior information)
In FIG. 1 and FIG. 2, and FIG. 10 and FIG. 11, the information processing apparatus 100 estimates the second user's creditworthiness without giving temporal weight to the information related to the second user's second action history. Although an example is shown, among the behavior information included in the information related to the second behavior history, the behavior information of the time closer to the current time may be weighted to increase the second user's creditworthiness.

  Specifically, the estimation unit 133 estimates the second user's creditworthiness by increasing the weight of action information closer to the current time among the action information included in the information related to the second action history. For example, the generation unit 132 increases the weight of behavior information that is closer to the current time among the information related to the first user's first behavior history, and the information related to the first behavior history and the first user cause default. A first model is generated that calculates an index value related to whether or not the second user will default on the basis of information related to the second action history of the second user based on whether or not the second user has performed.

  For example, the generation unit 132 uses the period segment “((1)) rather than the information regarding the behavior history on the network of the first user in the period segment“ k month ”(k = 1, 2,..., 11) of the period 1. The first model is generated so that the weight “ω” of the information related to the action history of the first user on the network of “k + 1) month” becomes large. For example, the generation unit 132 determines the period division “(k + 1) for the period 1 rather than the number of purchases of the first user's products in the period division“ k month ”(k = 1, 2,..., 11) for the period 1. The first model is generated so that the weight “ω” of the number of purchases of the first user's products and the like in the “month” is increased. Subsequently, the estimation unit 133 inputs information related to the second user's second behavior history to the first model generated by the generation unit 132, so that the current time out of the behavior information included in the second behavior history is input. The default probability of the second user is calculated by increasing the weight of the behavior information of the closer time. Subsequently, the estimation unit 133 estimates the creditworthiness of the second user based on the index value calculated by increasing the weight of the behavior information closer to the current time.

  Thereby, the information processing apparatus 100 can estimate the creditworthiness of the second user by placing emphasis on behavior information with higher freshness among the behavior information included in the second behavior history. That is, the information processing apparatus 100 can estimate the second user creditworthiness based on action information with high freshness that is considered to reflect the current creditworthiness of the second user. Therefore, the information processing apparatus 100 can more accurately determine whether there is currently a problem with the user's creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

[8-3. (Estimation processing based on changes in default probability)
Although FIG. 1 and FIG. 2 and FIG. 10 and FIG. 11 show examples in which the information processing apparatus 100 estimates the creditworthiness of the second user based on the default probability that is the index value calculated on the reference date. The creditworthiness of the second user may be estimated based on the transition of the default probability.

  Specifically, the estimation unit 133 estimates the creditworthiness of the second user based on the transition of the default probability calculated by the estimation unit 133. For example, the generation unit 132 includes the transition of the repayment record of the first user in the information related to the first action history, based on the information related to the first action history and the record of whether or not the first user has defaulted. Then, a first model for calculating an index value relating to whether or not the second user causes default is generated from information related to the second action history of the second user who is a new applicant for a credit card. That is, the generation unit 132 generates the first model by adding the transition of the repayment record of the first user to the feature of the first model. Subsequently, the estimation unit 133 calculates the default probability of the second user by inputting information on the second action history including the transition of the default probability of the second user to the first model generated by the generation unit 132. To do. Subsequently, the estimation unit 133 estimates the creditworthiness of the second user based on the index value calculated by the estimation unit 133.

  As a result, the information processing apparatus 100 can calculate the default probability of the second user by using a model that has learned a tendency such that it is difficult for default to occur for a user whose default probability is getting better. On the contrary, the information processing apparatus 100 can calculate the default probability of the second user based on a model that learns a tendency that default default is likely to occur for a user whose default probability is getting worse. Therefore, the information processing apparatus 100 can estimate more accurately whether there is currently no problem in the user's creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

[8-4. Estimating process based on action history of first user group satisfying predetermined condition]
In FIG. 1 and FIG. 2 and FIG. 10 and FIG. 11, the information processing apparatus 100 estimates the creditworthiness of the second user based on the information related to the first action history of the first user who has issued credit cards. Although the example to do was shown, based on the information about the 1st action history of the selected 1st user group, the 1st user's group which satisfies a predetermined condition from the 1st user was chosen, and the 2nd user's Creditworthiness may be estimated. Specifically, the estimation unit 133 is a first user that satisfies the first screening criteria set before the predetermined credit screening for the second user, and is the predetermined credit screening screening criteria for the second user. The creditworthiness of the second user is estimated based on information related to the first action history of the first user who does not satisfy the second examination criteria. For example, the generation unit 132 is a first user that satisfies a first examination standard set before a predetermined credit examination for the second user, and is a second examination that is a predetermined credit examination examination standard for the second user. Based on the information on the first action history of the first user that does not satisfy the criteria and the repayment record of the first user, the information on the second action history of the second user, whether or not the second user will default A first model for calculating the index value is generated. Subsequently, the estimation unit 133 calculates the default probability of the second user by inputting information on the second action history of the second user into the first model generated by the generation unit 132. Subsequently, the estimating unit 133 estimates the second user's creditworthiness based on the calculated default probability.

  Thereby, for example, when the first examination standard is looser than the second examination standard, the information processing apparatus 100 has been issued a credit card from the first user to satisfy the first examination standard. Since the examination standard is not satisfied, a model can be generated based on information on the first action history of the first user group that falls in the credit examination under the current situation. Here, the first user group is a user group that does not pass the current credit examination. The second user is a user who has been rejected in the credit information examination by the card company. Therefore, the first user group is estimated to be a user group having similar attributes to the second user. That is, the information processing apparatus 100 generates a model for calculating the default probability of the second user based on the first action history of the first user group considered to have an attribute closer to the second user. Can improve the accuracy. Therefore, the information processing apparatus 100 can estimate more accurately whether there is currently no problem in the user's creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

[8-5. Examples of other estimation processes)
Although FIG. 1 and FIG. 2 and FIG. 10 and FIG. 11 show examples in which the information processing apparatus 100 estimates the creditworthiness of the second user, it may estimate other than the creditworthiness of the second user.

[8-5-1. (Calculation of index value related to user creditworthiness)
1 and FIG. 2 and FIG. 10 and FIG. 11 show examples in which the information processing apparatus 100 calculates a default probability and estimates the user's creditworthiness based on the calculated default probability. 100 may calculate the index value itself regarding the creditworthiness of the second user. For example, the estimation unit 133 determines the second user's second behavior history from the second user's second behavior history based on the first behavior history information acquired by the acquisition unit 131 and the first user's creditworthiness record. Calculate index values related to creditworthiness. The estimation unit 133 estimates the creditworthiness of the second user based on the calculated index value. For example, the estimation unit 133 estimates that the second user has creditworthiness when the calculated index value regarding creditworthiness is equal to or less than a predetermined threshold. Moreover, the estimation part 133 estimates that the 2nd user does not have creditworthiness, when the calculated index value regarding creditworthiness exceeds a predetermined threshold value.

[8-5-2. (Indicator value calculation processing regarding whether or not the user takes a problem with money)
Further, the information processing apparatus 100 may calculate an index value related to whether or not the second user takes some trouble behavior related to money. Some problem behavior related to money may be, for example, arrears of payments other than default. For example, the estimation unit 133 determines, based on the information on the second action history of the second user, based on the information on the first action history acquired by the acquisition unit 131 and the record whether or not the first user has caused the problem action. An index value relating to whether or not the second user takes a problem behavior is calculated. Based on the calculated index value, the estimation unit 133 estimates an index regarding whether or not the second user causes a problem behavior. For example, the estimation unit 133 estimates that the second user is less likely to cause a problem behavior when the calculated index value regarding whether to cause the problem behavior is equal to or less than a predetermined threshold. In addition, the estimation unit 133 estimates that the second user is likely to cause a problem behavior when the calculated index value regarding whether to cause the problem behavior exceeds a predetermined threshold value.

[8-5-3. (Calculation process of index value regarding user's repayment ability)
Further, the information processing apparatus 100 may calculate an index value related to the repayment ability of the second user. For example, the estimation unit 133 determines the second user's second behavior history from the second user's second behavior history based on the information on the first behavior history acquired by the acquisition unit 131 and the repayment ability of the first user. Calculate index value for repayment ability. The estimation unit 133 estimates the repayment capacity of the second user based on the calculated index value. For example, the estimation unit 133 estimates that the second user has the repayment capability when the calculated index value regarding the repayment capability is equal to or less than a predetermined threshold. Moreover, the estimation part 133 estimates that the 2nd user does not have repayment capability, when the index value regarding the calculated repayment capability exceeds a predetermined threshold value.

[9. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the acquisition unit 131 and the estimation unit 133. The acquisition unit 131 acquires information on the first action history that is an action history before the first user is given a predetermined credit among the action histories on the network of the first user who is given a predetermined credit. . The estimation unit 133 is a second user who is a subject of a credit examination regarding a predetermined credit based on the information on the first action history acquired by the acquisition unit 131 and the result of whether or not the first user has defaulted. The creditworthiness of the second user is estimated from the information related to the second action history which is the action history on the network.

  As a result, the information processing apparatus 100 can appropriately estimate the creditworthiness of the user who has no problem in creditworthiness, for example, although the credit information has been damaged due to past due and the situation has changed. Until now, credit screening has only been able to estimate a user's creditworthiness based on credit information. Therefore, a user whose credit information has been damaged even once is presumed to have no creditworthiness in the credit examination, and it has been determined that a credit card cannot be issued. However, in practice, it is known that there are a certain number of users with creditworthiness among users who are determined not to issue credit cards. Despite this situation, there has been no way to remedy such users in credit reviews so far. Here, the information processing apparatus 100 can estimate the user's creditworthiness based on the action history on the network. As a result, the information processing apparatus 100 can accurately measure the creditworthiness of a user who has been determined not to issue a credit card. In other words, the information processing apparatus 100 can provide a predetermined credit to a user who has no problem with creditworthiness at present. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  In addition, the estimation unit 133 is a first user who satisfies the first examination standard set before the credit examination and does not satisfy the second examination standard which is the examination standard for the credit examination. The creditworthiness of the second user is estimated based on the information regarding.

  Thereby, for example, when the first examination standard is looser than the second examination standard, the information processing apparatus 100 has been issued a credit card from the first user to satisfy the first examination standard. Since the examination standard is not satisfied, a model can be generated based on information on the first action history of the first user group that falls in the credit examination under the current situation. Here, the first user group is a user group that does not pass the current credit examination. The second user is a user who has been rejected in the credit information examination by the card company. Therefore, the first user group is estimated to be a user group having similar attributes to the second user. That is, the information processing apparatus 100 generates a model for calculating the default probability of the second user based on the first action history of the first user group considered to have an attribute closer to the second user. Can improve the accuracy. Therefore, the information processing apparatus 100 can estimate more accurately whether there is currently no problem in the user's creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  In addition, the estimation unit 133 estimates the creditworthiness of the second user by increasing the weight of behavior information that is closer to the current time among the behavior information included in the information related to the second behavior history.

  Thereby, the information processing apparatus 100 can estimate the creditworthiness of the second user by placing emphasis on fresher behavior information among the behavior information included in the information on the second behavior history. That is, the information processing apparatus 100 can estimate the creditworthiness of the second user based on action information with high freshness that is considered to reflect the current creditworthiness of the second user. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  In addition, the estimation unit 133 determines from the information regarding the second action history of the second user based on the information about the first action history acquired by the acquisition unit 131 and the record of whether or not the first user has defaulted. Then, an index value relating to whether or not the second user will default is calculated.

  As a result, the information processing apparatus 100 can, for example, objectively evaluate numerically whether or not a user who has no problem with creditworthiness will default on credit although the credit information has been damaged due to delinquencies in the past. Can be estimated. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  Moreover, the estimation part 133 estimates a 2nd user's creditworthiness based on transition of an index value.

  As a result, the information processing apparatus 100 can calculate the default probability of the second user by using a model that has learned a tendency such that it is difficult for default to occur for a user whose default probability is getting better. On the contrary, the information processing apparatus 100 can calculate the default probability of the second user based on a model that learns a tendency that default default is likely to occur for a user whose default probability is getting worse. Therefore, the information processing apparatus 100 can estimate more accurately whether there is currently no problem in the user's creditworthiness. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  In addition, the information processing apparatus 100 according to the embodiment further includes a generation unit 132. Based on the information on the first behavior history acquired by the acquisition unit 131 and the record on whether or not the first user has defaulted, the generation unit 132 obtains the first information from the information on the second behavior history of the second user. 2 Generate a model for calculating an index value regarding whether or not the user will default. The estimation unit 133 uses the model generated by the generation unit 132 to calculate an index value related to whether or not the second user causes default.

  Thereby, the information processing apparatus 100 can calculate the index value related to whether or not the second user will default on debt with higher accuracy. Therefore, the information processing apparatus 100 can increase the accuracy of credit examination.

  In addition, the determination apparatus 200 according to the embodiment includes an acquisition unit 233 and a determination unit 234. The acquisition unit 233 includes information on the first action history that is an action history before the first user is given a predetermined credit among the action histories on the network of the first user who is given the predetermined credit, and the first The second user estimated from the information about the second action history, which is the action history on the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the record of whether or not the user has defaulted Get creditworthiness. Based on the second user's creditworthiness acquired by the acquisition unit 233, the determination unit 234 determines whether or not a service related to a credit card can be provided to the second user.

  Thereby, for example, the determination device 200 appropriately determines whether or not the credit card service can be provided to a user who has no credit problems at the present time because the credit information has been damaged due to past due, but the situation has changed. Can do.

  In addition, the determination apparatus 200 according to the embodiment further includes a screening unit 232. The examination unit 232 acquires the credit information of the second user from the credit information agency, and performs a credit examination based on the acquired credit information. The determination unit 234 is a service related to a credit card for the second user based on the second user's creditworthiness estimated from the second user's second action history that has been rejected as a result of the examination by the examination unit 232. It is determined whether or not the service can be provided.

  Thereby, the determination apparatus 200 can appropriately determine whether or not the credit card service can be provided to the user who is rejected in the credit information examination. Thereby, the determination apparatus 200 can accurately determine whether or not a service related to a credit card can be provided even for a user who is rejected in the credit information examination.

  Moreover, the determination part 234 determines whether a credit card can be issued with respect to a 2nd user as the availability of the service regarding the credit card with respect to a 2nd user.

  Thereby, the determination apparatus 200 can accurately determine whether or not a credit card is issued even for a user who is rejected in the credit information examination. In other words, the determination device 200 issues a credit card if it is determined that a user who has no problem in creditworthiness from the users who are rejected in the credit information examination and can issue a credit card. can do.

  Moreover, the determination part 234 determines whether the credit frame regarding a predetermined | prescribed credit with respect to a 2nd user can be changed as the availability of the service regarding the credit card with respect to a 2nd user.

  Thereby, the determination apparatus 200 can accurately determine whether or not the credit frame can be changed for a user who is rejected in the credit information examination. In other words, the determination apparatus 200 relieves a user who has no problem in creditworthiness from users who are rejected in the credit information examination, and changes the credit frame if it is determined that the credit frame can be changed. can do.

[10. Hardware configuration)
Further, the information processing apparatus 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 14, for example. FIG. 14 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via a predetermined communication network, sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. The CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program or data loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from other devices via a predetermined communication network.

  As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to implement the present invention in other forms with improvements.

[11. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the estimation unit can be read as estimation means or an estimation circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 10 User terminal 20 Credit information agency server 30 Electronic commerce server 40 Content server 50 Search server 60 SNS server 100 Information processing apparatus 121 User information storage part 122 Repayment result storage part 123 Model storage part 131 Acquisition part 132 Generation part 133 Estimation unit 134 Reception unit 135 Transmission unit 200 Determination device 221 User information storage unit 222 Repayment result storage unit 231 Reception unit 232 Examination unit 233 Acquisition unit 234 Determination unit 235 Service provision unit

Claims (14)

An acquisition unit that acquires information on a first action history that is an action history before the first user is given the predetermined credit among the action histories on the network of the first user who is given the predetermined credit; ,
On the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the information on the first action history acquired by the acquisition unit and the record of whether or not the first user has defaulted An information processing apparatus comprising: an estimation unit that estimates the creditworthiness of the second user from information related to a second behavior history that is a behavior history of the second user. The estimation unit includes
Based on information on the first action history of the first user who satisfies the first screening criteria set before the credit screening and does not satisfy the second screening criteria which is the screening criteria of the credit screening. The information processing apparatus according to claim 1, wherein the creditworthiness of the second user is estimated. The estimation unit includes
3. The credit information of the second user is estimated by increasing the weight of behavior information that is closer to the current time among the behavior information included in the information related to the second behavior history. 4. The information processing apparatus described in 1. The estimation unit includes
Based on the information on the first action history acquired by the acquisition unit and the information on whether or not the first user has defaulted, information on the second action history of the second user is obtained from the information on the second action history of the second user. The information processing apparatus according to claim 1, wherein an index value relating to whether or not the second user causes default is calculated as the creditworthiness of the information processing apparatus. The estimation unit includes
The information processing apparatus according to claim 4, wherein the second user's creditworthiness is estimated based on a transition of the index value. Based on the information on the first action history acquired by the acquisition unit and the information on whether or not the first user has defaulted, information on the second action history of the second user is obtained from the second user. Further includes a generation unit that generates a model for calculating an index value regarding whether or not a default occurs.
The estimation unit includes
6. The information processing apparatus according to claim 4, wherein an index value relating to whether or not the second user causes default is calculated using the model generated by the generation unit. An information processing method executed by a computer,
An acquisition step of acquiring information related to a first action history that is an action history before the first user is provided with the predetermined credit among the action histories on the network of the first user provided with the predetermined credit; ,
On the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the information on the first action history acquired by the acquisition step and the record of whether or not the first user has defaulted The information processing method characterized by including the estimation process of estimating the creditworthiness of the said 2nd user from the information regarding the 2nd action history which is no action history. An acquisition procedure for acquiring information related to a first action history, which is an action history before the first user is given the predetermined credit, among action histories on the network of the first user who is given the predetermined credit; ,
Based on the first action history acquired by the acquisition procedure and the record of whether or not the first user has defaulted, the action on the network of the second user who is the subject of the credit examination related to the predetermined credit An information processing program for causing a computer to execute an estimation procedure for estimating the creditworthiness of the second user from information related to a second action history that is a history. Among the action histories on the network of the first user who has been given a predetermined credit, information on the first action history, which is the action history before the first user has been given the predetermined credit, and the first user The second user estimated from the information on the second behavior history, which is the behavior history on the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the record of whether or not default has occurred. An acquisition department to acquire the creditworthiness of
A determination device comprising: a determination unit that determines whether a service related to a credit card can be provided to the second user based on the creditworthiness of the second user acquired by the acquisition unit. . The credit information of the second user is acquired from a credit information agency, and further comprises a screening unit that performs credit screening based on the acquired credit information,
The determination unit
Whether or not to provide a credit card service to the second user based on the second user's creditworthiness estimated from the second user's second action history that was rejected as a result of the examination by the examination unit The determination apparatus according to claim 9, wherein: The determination unit
11. The determination apparatus according to claim 9, wherein it is determined whether or not a credit card can be issued to the second user, as to whether or not a service related to a credit card can be provided to the second user. The determination unit
11. The method according to claim 9, wherein it is determined whether or not a credit frame related to a predetermined credit can be changed for the second user, as to whether or not a service related to a credit card can be provided to the second user. Judgment device. A determination method executed by a computer,
Among the action histories on the network of the first user who has been given a predetermined credit, information on the first action history, which is the action history before the first user has been given the predetermined credit, and the first user The second user estimated from the information on the second behavior history, which is the behavior history on the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the record of whether or not default has occurred. Acquisition process to acquire the creditworthiness of
The determination method characterized by including the determination process of determining whether the service regarding a credit card can be provided with respect to the said 2nd user based on the creditworthiness of the 2nd user acquired by the said acquisition process. . Among the action histories on the network of the first user who has been given a predetermined credit, information on the first action history, which is the action history before the first user has been given the predetermined credit, and the first user The second user estimated from the information on the second behavior history, which is the behavior history on the network of the second user who is the subject of the credit examination related to the predetermined credit, based on the record of whether or not default has occurred. Acquisition procedure to acquire the creditworthiness of
And causing the computer to execute a determination procedure for determining whether or not a service related to a credit card can be provided to the second user based on the creditworthiness of the second user acquired by the acquisition procedure. Judgment program to do.

Images