Information processing system, information processing method, and program

Abstract

To set payment-by-installments conditions set when a user pays by installments to more appropriate conditions.SOLUTION: An information processing system comprises a credit score estimation unit 23 which estimates a credit score set in a user on the basis of an attribute data group related to the user, and a condition setting unit 25 which sets payment-by-installments conditions selectable by the user when the user pays by installments on the basis of the credibility of the user indicated by the credit score.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a technique for determining a user's trustworthiness. [Background technology]

[0002] Conventionally, a judgment device has been proposed that includes a user information acquisition unit that acquires behavioral information indicating a user's behavior, and a credit judgment unit that judges the creditworthiness of the user regarding his or her future ability to repay a loan based on the behavioral information (see Patent Document 1).

[0003] In addition, an information processing device has been proposed that includes a product information acquisition unit that acquires product information including at least the sales status of the product, a user information acquisition unit that acquires a search history from a service server and a purchase history from an e-commerce server, and an interest rate setting unit that sets an interest rate when a user purchases a product in installments based on the product information (see Patent Document 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2021-174039 A [Patent Document 2] Patent Publication No. 2022-077048 Summary of the Invention [Problem to be solved by the invention]

[0005] Conventionally, a technique has been proposed for setting an interest rate when a user purchases a product in installments based on product information. However, the previously set conditions for installment payments, such as interest rates, have not always been appropriate.

[0006] In view of the above-mentioned problems, an object of the present disclosure is to make the installment payment conditions set when a user makes installment payments more appropriate. [Means for solving the problem]

[0007] One example of the present disclosure is an information processing system comprising: a credit score estimation means for estimating a credit score to be set for a user based on a group of attribute data relating to the user; and a condition setting means for setting installment payment conditions selectable by the user when making installment payments based on the user's creditworthiness indicated by the credit score.

[0008] The present disclosure can be understood as an information processing device, a system, a method executed by a computer, or a program executed by a computer. The present disclosure can also be understood as such a program recorded on a recording medium readable by a computer or other device, machine, etc. Here, a recording medium readable by a computer, etc. refers to a recording medium that stores information such as data and programs by electrical, magnetic, optical, mechanical, or chemical action and can be read by a computer, etc. Effect of the Invention

[0009] According to the present disclosure, it is possible to set installment payment conditions when a user makes installment payments to more appropriate conditions. [Brief description of the drawings]

[0010] [Figure 1] 1 is a schematic diagram showing a configuration of an information processing system according to an embodiment. [Diagram 2] 1 is a diagram illustrating an outline of a functional configuration of an information processing device according to an embodiment. [Diagram 3] 1 is a simplified diagram of a credit score estimation process according to an embodiment. [Figure 4] FIG. 1 is a simplified diagram illustrating the concept of a decision tree of a machine learning model employed in an embodiment. [Diagram 5] FIG. 13 is a diagram showing a predetermined range of credibility in an embodiment. [Figure 6] 1 is a flowchart illustrating a flow of a machine learning process according to an embodiment. [Figure 7] 10 is a flowchart showing a flow of a score calculation process according to the embodiment. [Figure 8] 11 is a flowchart showing the flow of a payment terms setting process according to the embodiment. [Figure 9] FIG. 13 is a diagram showing an outline of the functional configuration of an information processing device according to a variation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of an information processing device, method, and program according to the present disclosure will be described with reference to the drawings. However, the embodiment described below is merely an example of an embodiment, and the information processing device, method, and program according to the present disclosure are not limited to the specific configuration described below. In carrying out the present invention, a specific configuration according to the embodiment may be appropriately adopted, and various improvements and modifications may be made. The present invention can appropriately adopt at least a part of the configurations in the embodiments and variations described below.

[0012] In this embodiment, a case where the technology according to the present disclosure is implemented to set and notify a user of installment payment conditions for the purchase price of a mobile terminal, for the purpose of increasing the number of new mobile communication service subscribers or for the purpose of improving the convenience of existing mobile communication service subscribers, will be described. However, the technology according to the present disclosure can be widely used as a technology for setting installment payment conditions for a user, and the application of the present disclosure is not limited to the examples shown in the embodiment. For example, the technology according to the present disclosure may be implemented to set installment payment conditions for the purchase price of other products and services for each user. In addition, installment payment conditions are various conditions that are set when the price is paid in installments rather than in a lump sum, and the types of conditions are not limited.

[0013] <System configuration> 1 is a schematic diagram showing a configuration of an information processing system according to this embodiment. In the information processing system according to this embodiment, an information processing device 1 and one or more service providing systems 5 are connected to each other so that they can communicate with each other. A user is a user of a service provided by the service providing system 5, and receives the service by accessing the service providing system 5 from a user terminal.

[0014] The information processing device 1 is a computer including a central processing unit (CPU) 11, a read only memory (ROM) 12, a random access memory (RAM) 13, a storage device 14 such as an electrically erasable and programmable read only memory (EEPROM) or a hard disk drive (HDD), a communication unit 15 such as a network interface card (NIC), etc. However, the specific hardware configuration of the information processing device 1 can be omitted, replaced, or added as appropriate depending on the embodiment. In addition, the information processing device 1 is not limited to a device consisting of a single housing. The information processing device 1 may be realized by multiple devices using so-called cloud or distributed computing technology, etc.

[0015] The service providing system 5 is a computer equipped with a CPU, a ROM, a RAM, a storage device, a communication unit, an input device, an output device, and the like (not shown). Furthermore, these systems and terminals are not limited to devices consisting of a single housing. These systems and terminals may be realized by multiple devices using so-called cloud or distributed computing technology, etc.

[0016] The services provided by the service providing system 5 include, for example, an online shopping service, an online reservation service, a mobile terminal sales service, a mobile communication service, a banking service, a credit card / deferred payment service, an electronic money payment service, an advertising service, an operation center service, a map information service, etc. Note that the "deferred payment" is not limited to a service called Buy Now Pay Later (BNPL), and may include any purchase of a product / service with deferred payment.

[0017] The services provided by the service providing system 5 are not limited to the examples in this embodiment. The service providing system 5 notifies the information processing device 1 of user-related data when providing a service. Here, the user-related data includes service usage history data by the user. The content of the service usage history data varies depending on the content of the service, and may include, for example, history data of the user's location information, payment history data of credit card usage amount / postpaid payment usage amount, electronic money usage history data, transaction history data (including purchase history data of products, etc.), reservation history data, operation history data for the user from the operation center, etc.

[0018] In this embodiment, an aspect will be described in which installment payment terms for the purchase price of a mobile terminal are set for a user for a mobile terminal sales service and a mobile communication service among various services provided by the service providing system 5. However, the product or service for which installment payment terms are set for a user is not limited to the purchase price of a mobile terminal, and various products or services may be the target.

[0019] The installment payment conditions include 1) whether installment payments are possible, 2) the interest rate for installment payments, 3) the maximum number of installments for installment payments, 4) the maximum amount of installment payments (credit limit), and 5) the minimum amount of the first payment (minimum down payment and first installment payment amount), etc. In the system according to this embodiment, for example, the installment payment conditions may be set as shown below. 1) Regarding whether or not installment payments are possible, installment payments are set to permitted for users whose creditworthiness, as indicated by their credit score, is equal to or greater than a specified creditworthiness, and installment payments are set to rejected for users whose creditworthiness, as indicated by their credit score, is less than the specified creditworthiness. 2) Regarding interest rates for installment payments, the higher the credit rating indicated by the credit score, the lower the interest rate is set, and the lower the credit rating indicated by the credit score, the higher the interest rate is set (however, the interest rate may have a preset upper and / or lower limit). 3) Regarding the upper limit on the number of installments for installment payments, the higher the credit rating indicated by the credit score, the higher the upper limit is set, and the lower the credit rating indicated by the credit score, the lower the upper limit is set (however, there may be a preset upper and / or lower limit on the upper limit on the number of installments). 4) Regarding the upper limit of the amount to be paid in installments, the higher the credit rating indicated by the credit score, the higher the upper limit is set, and the lower the credit rating indicated by the credit score, the lower the upper limit is set (however, there may be a preset upper and / or lower limit for the upper limit of the amount to be paid in installments). 5) Regarding the minimum initial payment amount, the higher the creditworthiness indicated by the credit score, the lower the minimum is set, and the lower the creditworthiness indicated by the credit score, the higher the minimum is set (however, there may be a preset upper and / or lower limit for the minimum initial payment amount).

[0020] The information processing device according to the present disclosure uses a machine learning model that takes user attribute data and the like as input and outputs a credit score (in this embodiment, a score indicating deferred payment risk). The attribute data used as input here may also include data indicating default (non-performance of debt). By using various attribute data as input, the information processing device 1 according to the present disclosure calculates a universal and generalized credit score that is generated by uniformly reflecting the overall attributes of the user. The calculated credit score can be used for credit screening (a judgment involving approval or rejection of deferred payment) in deferred payment services and the like, but as described above, in this embodiment, the calculated credit score is used to set installment payment conditions that can be selected by the user.

[0021] Here, the user attribute data includes fact attribute data and estimated attribute data. The attribute data includes data expressed in a data format such as a score (e.g., a continuous value between 0 and 1) or a label (e.g., a binary value corresponding to presence / absence or yes / no). However, the format of the attribute data is not limited to the examples in the present disclosure. The attribute data may also include, for example, online service usage status and electronic value usage status including points. The online service usage status may also include at least one of the number of cancellations, cancellation rate, and number of orders in an online shopping service or an online reservation service.

[0022] The factual attribute data is data indicating factual attributes that can be confirmed as factual for the user based on user-provided data obtained by being provided by the user himself / herself and history data collected about the user. Examples of the user-provided data include registration data including the name, email address, telephone number, address, place of employment, place of study, etc. registered by the user himself / herself, and data obtained as a result of the user himself / herself answering a questionnaire, etc. Examples of the history data include the above-mentioned usage history data of the electronic commerce service provided by the service providing system 5. The factual attribute data is preferably data obtained by converting the above-mentioned user-provided data or history data into a data format suitable for marketing and / or analysis purposes. For example, examples of the factual attribute data that can be obtained based on the usage history data include genres / categories and brands of products / services frequently used by the user, as well as commercial locations, recreational spots, and tourist spots frequently visited by the user.

[0023] The estimated attribute data is data indicating an inferred attribute obtained by estimation based on user-provided data, history data, fact attribute data, etc. In this embodiment, the estimated attribute data includes a user's personality estimated or predicted using machine learning technology. The estimated attribute data is preferably data on an attribute that influences a user's behavior when used for targeting.

[0024] In this embodiment, a weight is set for each attribute data. The weight indicates the degree of correlation between the attribute data and the credit score when the attribute data is used to calculate the credit score, and each time the appropriateness of the credit score is evaluated by the machine learning unit 24 described later, the parameters of the model are adjusted so that the credit score becomes a more appropriate value. The weight corresponding to each attribute data corresponds to the weight corresponding to each node (each regression tree) in a model for calculating the credit score, such as a decision model described later, for example, and is appropriately determined in the process of calculating the credit score. Note that the credit score is determined based on the weight of each node, for example.

[0025] Here, the attribute data group may include demographic attributes, behavioral attributes, or psychographic attributes. The demographic attributes are, for example, the user's gender, family structure, age, etc., and the behavioral attributes may be based on service usage history data, such as whether or not cash advances have been used, whether or not revolving payments have been used, deposit and withdrawal history for a specific account, commercial transaction history for some product / service including gambling or lottery (which may include online transaction history in an online marketplace, etc.), and user movement history using location information or place information, and the psychographic attributes are, for example, preferences for gambling or lottery. However, the available user attributes are not limited to the examples in this embodiment. For example, "time required for operation (calls, etc.)" and "credit card usage amount / postpaid settlement usage amount" from an operation center service, etc. may also be used as attributes. The demographic attributes and behavioral attributes may be treated as factual attributes. The psychographic attributes may be treated as estimated attributes. In addition, attributes similar to demographic attributes may be estimated attributes estimated based on factual attributes based on user-provided data or history data. Similarly, attributes similar to behavioral attributes may be estimated based on factual attributes based on user-provided data or history data. Psychographic attributes may be factual attributes based on user-provided data, including, for example, the result of a user's intention input.

[0026] 2 is a diagram showing an outline of the functional configuration of the information processing device 1 according to this embodiment. The information processing device 1 functions as an information processing device including a fact attribute determination unit 21, an estimated attribute determination unit 22, a credit score estimation unit 23, a machine learning unit 24, a condition setting unit 25, and a notification unit 26, by a program recorded in the storage device 14 being read into the RAM 13 and executed by the CPU 11, and each piece of hardware included in the information processing device 1 is controlled. Note that in this embodiment and other embodiments described later, each function included in the information processing device 1 is executed by the CPU 11, which is a general-purpose processor, but some or all of these functions may be executed by one or more dedicated processors.

[0027] The fact attribute determination unit 21 determines fact attribute data that can be confirmed as fact for the user based on user-provided data provided by the user himself / herself and / or the user's history data. In this embodiment, the fact attribute determination unit 21 determines fact attribute data related to the user using a method such as aggregating user-provided data and / or history data, determining corresponding attributes by referring to other data such as a map, or using the user-provided data and / or history data as is. Note that, although this embodiment employs a method of determining fact attribute data related to a user based on user-provided data and / or the user's history data, fact attribute data related to a user may be acquired by other methods.

[0028] The estimated attribute determination unit 22 determines estimated attribute data estimated for the target user based on user-related data including at least one or more fact attribute data determined for the target user by the fact attribute determination unit 21. In this embodiment, the estimated attribute determination unit 22 determines an estimated attribute based on an output value obtained by inputting user-related data including one or more fact attribute data related to the target user to an attribute estimation model, which is a machine learning model. In this embodiment, the output value from the attribute estimation model is a value indicating the probability that the target user has a predetermined estimated attribute, and the estimated attribute determination unit 22 determines that the target user has the estimated attribute when the output value obtained from the attribute estimation model is within a predetermined range. When it is determined that the target user has a predetermined estimated attribute, the estimated attribute determination unit 22 sets the label of the attribute data estimated for the target user to a value indicating the presence or absence of an attribute or the type of the attribute. The estimated attribute data may be indicated by a score instead of a label. In this case, the estimated attribute determination unit 22 sets a value indicating the degree (probability) that the estimated attribute can be applied to the score of the attribute data estimated for the target user. The degree may be the output value of the attribute estimation model.

[0029] The credit score estimation unit 23 estimates the credit score of the target user (in this embodiment, the credit score calculated based on the deferred payment risk) based on an attribute data group including the fact attribute and the estimated attribute related to the target user. Here, the deferred payment risk is a risk that the settlement of the deferred payment will not be properly performed by the target user when the target user uses the deferred payment, expressed by some index (in this embodiment, the credit score that changes according to the magnitude of the deferred payment risk). At this time, the credit score estimation unit 23 may perform some processing (normalization, ranking, labeling, etc.) on the determined fact attribute and / or estimated attribute to make it a part of the attribute data group, or may use the determined fact attribute and / or estimated attribute to calculate other types of scores (for example, so-called credit scores, etc.) or labels as the whole or part of the attribute data group. Here, other machine learning models may be involved in the calculation of other types of scores or labels.

[0030] 3 is a simplified diagram of the credit score estimation process according to this embodiment. In this embodiment, the credit score estimation unit 23 estimates (calculates) the credit score of a user by inputting a group of attribute data of the user into a credit score estimation model. Here, the output value of the credit score estimation model is, for example, a credit score normalized / standardized with 0 as the minimum value and 1 as the maximum value.

[0031] The machine learning unit 24 generates and / or updates a credit score estimation model used for credit score estimation by the credit score estimation unit 23. The credit score estimation model is a machine learning model that outputs a credit score indicating the degree of risk that the target user will not correctly settle the deferred payment if the target user uses deferred payment when one or more attribute data (attribute data group) related to the target user are input. By using such a machine learning model, in this embodiment, it is possible to obtain an output as a credit score that takes into account factors specialized for deferred payment, rather than a simple credit score. In addition, in this embodiment, an example is shown and described in which a credit score in which the larger the credit score value, the higher the creditworthiness (lower the risk) and the smaller the credit score value, the lower the creditworthiness (higher the risk), but the relationship between the magnitude of the score value and the level of risk may be reversed.

[0032] In generating and / or updating the credit score estimation model, the machine learning unit 24 creates teacher data for each user, in which a group of attribute data of the user is defined as an input value and a credit score related to a user having the same group of attribute data is defined as an output value. Then, the machine learning unit 24 generates and / or updates the credit score estimation model based on the teacher data. As described above, the group of attribute data input to the credit score estimation model includes fact attribute data determined by the fact attribute determination unit 21 and estimated attribute data estimated by the estimated attribute determination unit 22 based on user-related data including the fact attribute data, and is combined with the credit score of the corresponding user and input to the machine learning unit 24 as teacher data. In this embodiment, the credit score set in the teacher data is a credit score determined based on the payment history data of the deferred payment of the user corresponding to the combination of user attributes as the input value. Here, the payment history data of the deferred payment includes data indicating the presence or absence of default (non-performance of debt) in the deferred payment and the default amount. In this case, the credit score may be a rule-based credit score or may be a manually set (annotated) credit score. It may also be a credit score that was previously output by a credit score estimation model and then revised by an administrator or the like.

[0033] A machine learning model generation / update framework that can be adopted as a credit score estimation model or the like when implementing the technology according to the present disclosure is based on an ensemble learning algorithm, for example. For example, a machine learning framework (for example, LightGBM) based on a gradient boosting decision tree (GBDT) may be adopted as the framework. In other words, the framework may be a machine learning framework based on a decision tree model that transfers the error between the correct answer and the predicted value between previous and next weak learners (weak classifiers). The predicted value here refers to the predicted value of the credit score, for example. In addition to LightGBM, the framework may adopt a boosting method such as XGBoost or CatBoost. According to a framework using a decision tree, a machine learning model having a relatively high performance can be generated / updated with less effort in parameter adjustment compared to a framework using a neural network. However, the machine learning model generation / update framework that can be adopted when implementing the technology according to the present disclosure is not limited to the example in this embodiment. For example, instead of a gradient boosting decision tree, another learning device such as a random forest may be adopted as a learning device, or a learning device other than a so-called weak learning device such as a neural network may be adopted. In particular, when a learning device other than a so-called weak learning device such as a neural network is adopted, ensemble learning does not need to be adopted.

[0034] FIG. 4 is a simplified diagram showing the concept of a decision tree of a machine learning model employed as a credit score estimation model or the like in this embodiment. When adopting a gradient boosting machine learning framework based on a decision tree algorithm, the branching conditions of each node of the decision tree are optimized. Specifically, in the gradient boosting machine learning framework based on a decision tree algorithm, a credit score is calculated for each user group having attributes indicated by two child nodes branched from one parent node, and the branching condition of the parent node is optimized so that the difference between these credit scores becomes large (for example, so that the difference becomes maximum or is equal to or greater than a predetermined threshold), that is, so that the two child nodes branch neatly. For example, when the attribute indicated as the branching condition of a node is age, the age set as the branching threshold may be changed, or the branching condition may be changed to an attribute other than age. In this way, the branching conditions of all nodes of the decision tree are recursively optimized, thereby improving the estimation accuracy of the credit score based on the attribute data group.

[0035] The condition setting unit 25 sets installment payment conditions that the user can select when making installment payments, based on the user's creditworthiness indicated by the credit score. As described above, the condition setting unit 25 sets at least one of the following installment payment conditions: 1) whether installment payments are possible, 2) the interest rate for installment payments, 3) the upper limit of the number of installments for installment payments, 4) the upper limit of the amount subject to installment payments, and 5) the lower limit of the initial payment amount. Note that in this embodiment, an example will be described in which the subject of installment payments is the purchase price of a mobile terminal, but as described above, products or services to which the technology disclosed herein can be applied are not limited to the examples in this embodiment.

[0036] In this embodiment, when "1) whether installment payments are possible" is set as the installment payment condition, the condition setting unit 25 determines whether installment payments are possible by comparing the user's credit score with a predetermined threshold. The credit score used in this embodiment is a score in which the higher the value, the higher the creditworthiness. For this reason, the condition setting unit 25 sets the installment payment of the user to permitted when the credit score is equal to or greater than the predetermined threshold, and sets the installment payment of the user to rejected when the credit score is less than the predetermined threshold.

[0037] Here, the threshold for determining whether installment payments are possible is preferably determined according to the possibility that the installment payments of the user corresponding to the credit score will default. In other words, the threshold is preferably set to a value that can exclude users who have a certain or higher possibility of defaulting (failing to pay) on installment payments.

[0038] In this embodiment, when "2) interest rate for installment payments" is set as the installment payment condition, the condition setting unit 25 sets the interest rate for installment payments within a range having a predetermined upper or lower limit. Here, the specific method for calculating the interest rate corresponding to the credit score is not limited, but it is sufficient to execute a process that obtains an interest rate as an output when at least a credit score is input, and for example, a predetermined calculation formula, a map that defines the relationship between the credit score and the interest rate, a machine learning model that has learned the relationship between the credit score and the appropriate interest rate, etc. can be used. By setting an upper and / or lower limit for the interest rate, it is possible to prevent the interest rate from becoming endlessly higher or lower depending on the credit score, and to set the interest rate within an appropriate range.

[0039] Fig. 5 is a diagram showing the relationship between creditworthiness and interest rates in this embodiment. According to the example shown in Fig. 5, the interest rate for installment payments is set lower as the creditworthiness indicated by the credit score increases and higher as the creditworthiness indicated by the credit score decreases within a preset upper and / or lower limit range, and it can be seen that the lower limit interest rate is set for users whose credit score is equal to or higher than a first threshold, and the upper limit interest rate is set for users whose credit score is less than a second threshold.

[0040] In this embodiment, when "3) Upper limit of number of installments for installment payment" is set as the installment payment condition, the condition setting unit 25 sets the interest rate for the installment payment within a settable range of the upper limit of the number of installments, with a predetermined upper or lower limit set in advance. Here, the specific method for calculating the interest rate corresponding to the credit score is not limited, but it is sufficient to execute a process that obtains an interest rate as an output when a credit score is input, and for example, a predetermined calculation formula, a map that defines the relationship between credit score and interest rate, a machine learning model that has learned the relationship between credit score and appropriate interest rate, etc. can be used.

[0041] Here, the range in which the upper limit number of installments can be set may be further set based on the length of the life cycle (update cycle of the product or service) predefined for the product or service that is the subject of the installment payment. For example, if the update cycle of a mobile terminal (cycle for changing models, release cycle of the latest model, etc.) is 3 to 4 years, the range in which the upper limit number of installments can be set may be set to an installment payment period close to the length of the cycle (for example, the upper limit may be set to 48 installments per month, etc.). In addition, for example, for products or services that are more expensive and have a longer life cycle (luxury clothing, luxury bags, accessories, real estate, etc.), the range in which the upper limit number of installments can be set may be set to a longer installment payment period, and for products or services that are more fixed and have a shorter life cycle (daily necessities, etc.), the range in which the upper limit number of installments can be set may be set to a shorter installment payment period. Since the life cycle of a product or service differs for each type of product or service, it is possible to set appropriate and safe installment payment conditions by setting the range in which the upper limit number of installments can be set to match the life cycle.

[0042] In this embodiment, when "4) Upper limit of installment payment amount" is set as the installment payment condition, the condition setting unit 25 sets the upper limit of the installment payment amount within a predetermined range. Here, "4) Upper limit of installment payment amount" is specifically a credit limit such as an upper limit of revolving payment, and is the upper limit of the amount that can be paid by credit. There is no specific method for calculating the upper limit of the installment payment amount corresponding to the credit score, but it is sufficient to execute a process that obtains the upper limit of the installment payment amount as an output when at least a credit score is input, and for example, a predetermined calculation formula, a map that defines the relationship between the credit score and the upper limit of the installment payment amount, a machine learning model that learns the relationship between the credit score and an appropriate upper limit of the installment payment amount, etc. can be used.

[0043] In this embodiment, when "5) minimum initial payment amount" is set as the installment payment condition, the condition setting unit 25 sets the minimum initial payment amount within a predetermined range. Here, "5) minimum initial payment amount" is specifically the down payment, the minimum of the first installment payment amount, etc. A specific method for calculating the minimum initial payment amount corresponding to the credit score is not limited, but it is sufficient that a process is executed that obtains the minimum initial payment amount as an output when the credit score is input, and for example, a predetermined calculation formula, a map that defines the relationship between the credit score and the minimum initial payment amount, a machine learning model that learns the relationship between the credit score and the appropriate minimum initial payment amount, etc. can be used.

[0044] In this embodiment, an example of setting the installment payment terms using only the credit score is described, but when setting the installment payment terms, other credit information may be referenced in addition to the credit score. For example, the condition setting unit 25 may set the installment payment terms based on user attribute data (which may include the above-mentioned actual attribute data and estimated attribute data) in addition to the credit score, may set the installment payment terms based on conventional credit information in addition to the credit score, may set the installment payment terms taking into account the results of identity authentication (e.g., identity authentication using eKYC may be used) in addition to the credit score, or may set the installment payment terms taking into account details of the installment payment (such as the amount and number of installments) in addition to the credit score.

[0045] When setting installment payment terms taking into consideration the result of identity authentication in addition to the credit score, identity authentication may be performed by an authentication unit (not shown) of the information processing device 1 or the service providing system 5 extracting feature vectors from a first face image obtained by capturing an image of the user's identity document such as a driver's license using a terminal owned by the user, and a second face image obtained by capturing an image of the user himself using the terminal when instructions to the user are displayed on the terminal from the authentication unit, and determining whether the feature vectors are similar. At this time, the condition setting unit 25 may provide preferential installment payment terms to the user on the condition that the feature vectors are similar. For example, the condition setting unit 25 may set the installment payment to "permitted" in relation to "1) whether installment payment is possible" on the condition that each feature vector is similar, may lower the installment payment interest rate from a reference interest rate in relation to "2) installment payment interest rate", may raise the maximum number of installments from a reference number in relation to "3) upper limit of installment number of installments", may raise the installment payment amount from a reference amount in relation to "4) upper limit of installment payment amount", or may lower the minimum initial payment amount from a reference amount in relation to "5) minimum initial payment amount". Here, the "standard" may be an installment payment condition set based on a credit score without considering the result of the personal authentication. In addition, a machine learning model used for the process of setting the installment payment condition taking into account other information such as the result of personal authentication may be trained using training data in which a payment history indicating whether or not an installment payment has been made is further labeled with information other than a credit score such as the result of personal authentication.

[0046] The notification unit 26 notifies the user of the installment payment conditions that are set by the condition setting unit 25 and that the user can select. Here, when the technology according to the present disclosure is implemented for setting the installment payment conditions for the purchase price of a mobile terminal, the users to whom the installment payment conditions are notified may be limited to existing users (users who have already signed up for a line), new users (users who have not yet signed up for a line), or not limited to any user group. For this reason, in this embodiment, the notification unit 26 may further notify the user of a proposal to subscribe to a communication service for mobile terminals. In this way, it is possible to effectively appeal to users who have not yet signed up for the service and who are likely not to have accumulated credit information, to sign up for the service by using the credit score of the deferred payment risk. If the user has already signed up for the communication service, the above-mentioned identity authentication may be completed.

[0047] Furthermore, the specific method of notifying the user by the notification unit 26 is not limited to a specific notification method. For example, the method of notifying the user by the notification unit 26 may be a notification by advertisement delivery, a notification by an in-app message, a notification by a general-purpose message service (a social network system, a short message service, etc.), etc. Furthermore, the notification by advertisement delivery may be performed while the user is browsing a site of an online shopping service (if the target product is a mobile terminal, a site introducing the mobile terminal or a communication service).

[0048] <Processing flow> Next, a flow of processing executed by the information processing device according to the present embodiment will be described. Note that the specific contents and processing order of the processing described below are an example for implementing the present disclosure. The specific contents and processing order may be appropriately selected according to the embodiment of the present disclosure.

[0049] 6 is a flowchart showing the flow of machine learning processing according to this embodiment. The processing shown in this flowchart is executed periodically or at a timing designated by an administrator.

[0050] In this embodiment, in the machine learning process, a credit score estimation model is generated and / or updated. The machine learning unit 24 creates training data including a combination of a group of attribute data for each user accumulated in the past and a credit score determined in advance for the corresponding user (step S101). Then, the machine learning unit 24 inputs the created training data into the credit score estimation model, and creates and / or updates the credit score estimation model used for credit score estimation by the credit score estimation unit 23 (step S102). After that, the process shown in this flowchart ends.

[0051] 7 is a flowchart showing the flow of the score calculation process according to this embodiment. The process shown in this flowchart is executed for each target user periodically or at a specified timing.

[0052] In steps S201 and S202, the fact attribute data and the estimated attribute data are determined. The fact attribute determination unit 21 determines the fact attribute data related to the target user based on the user-provided data and / or history data of the target user (step S201). Then, the estimated attribute determination unit 22 determines the estimated attribute data related to the target user based on at least the fact attribute data determined in step S201 (step S202). After that, the process proceeds to step S203.

[0053] In steps S203 and S204, a credit score is determined and output. The credit score estimation unit 23 determines an attribute data group including the actual attribute data determined in step S201 and the estimated attribute data determined in step S202 (step S203). Then, the credit score estimation unit 23 inputs the attribute data group determined in step S203 into a credit score estimation model, and acquires the output value as a credit score that changes according to the risk that the target user will not correctly settle the deferred payment when the target user uses the deferred payment (step S204). However, the method of estimating the credit score is not limited to the example in this embodiment. For example, the credit score may include a value calculated by inputting the attribute data group into a predetermined function or statistical model that is not a machine learning model. After that, the process shown in this flowchart ends.

[0054] 8 is a flowchart showing the flow of the payment terms setting process according to this embodiment. The process shown in this flowchart is executed for each target user who is the target of advertisement display, advertisement message transmission, etc. The timing of execution of the payment terms setting process is not limited, and may be any of the following: a preset timing, a timing designated by an administrator, a timing when an operation by a target user that triggers the transmission of an advertisement, etc. (for example, a data request for a web page in which an advertisement is embedded, etc.) is detected, etc.

[0055] In steps S301 and S302, installment payment terms selectable by the user are set based on the target user's credit score. The condition setting unit 25 acquires the target user's credit score estimated in the score calculation process (step S301), and sets installment payment terms selectable by the user when making installment payments based on the user's creditworthiness indicated by the credit score (step S302). Details of setting installment payment terms are as described above in the description of the condition setting unit 25, and therefore will not be described here. Processing then proceeds to step S303.

[0056] In step S303, the installment payment conditions are notified to the target user. The notification unit 26 notifies the user of the installment payment conditions selectable by the user, which have been set by the condition setting unit 25. As described above, at this time, the notification unit 26 may further notify the user of an offer to subscribe to a communication service for the mobile terminal. After that, the process shown in this flowchart ends.

[0057] <Effects> According to this embodiment, when a user pays for a mobile terminal or the like in installments, the installment payment terms that the user can select can be set to more appropriate terms according to the user's credit score.

[0058] <Variations> In the above-described embodiment, a credit assessment based on the deferred payment risk is performed without narrowing down the target user group, and the installment payment conditions are set and notified to the user whose credit is determined to be within a predetermined range. However, for a user group with sufficient accumulated credit data (credit history, communication service payment history, etc.), the installment payment conditions based on the deferred payment risk may not be set and notified, and for a user group with insufficient accumulated credit data, the installment payment conditions based on the deferred payment risk may be set and notified. Here, the user group with insufficient accumulated credit data is, for example, a user group such as a young person, who has a high need for installment payments due to relatively low financial power and credit. Hereinafter, the information processing device 1b according to this variation will be described with reference to the parts common to the first variation described above, and the differences from the first variation described above will be described.

[0059] 9 is a diagram showing an outline of the functional configuration of the information processing device 1b according to the variation. The hardware configuration of the information processing device 1b is the same as that of the information processing device 1 described with reference to FIG. 1, and therefore the description will be omitted. The information processing device 1b functions as an information processing device including a fact attribute determination unit 21, an estimated attribute determination unit 22, a credit score estimation unit 23, a machine learning unit 24, a condition setting unit 25, a notification unit 26, and a credit data determination unit 27, by a program recorded in the storage device 14 being read into the RAM 13 and executed by the CPU 11, and each hardware included in the information processing device 1 being controlled. That is, the information processing device 1b according to this variation further includes a credit data determination unit 27.

[0060] The credit data determination unit 27 determines whether or not a user has accumulated a quantity of credit data (e.g., credit history, payment history for communication services, etc.) suitable for processing to set installment payment conditions without being based on a credit score that changes according to deferred payment risk. Specifically, the credit data determination unit 27 determines whether or not a predetermined criterion set in advance is met based on the type and / or amount of credit history accumulated for the user. Here, the predetermined criterion is, for example, the presence or absence of a required specific type of credit history, or a threshold value for the amount of credit history.

[0061] In this variation, the credit score estimation unit estimates a credit score that changes according to the deferred payment risk for a user who is determined to have at least an insufficient amount of accumulated credit data. The notification unit 26 proposes installment payment terms to a user who is determined to have at least an insufficient amount of accumulated credit data. The process flow for calculating the credit score and notifying the installment payment terms is roughly the same as in the embodiment described above, so a description thereof will be omitted.

[0062] According to this variation, by setting and notifying installment payment conditions based on the risk of deferred payment for users who do not have sufficient accumulated credit data, it is possible to provide the convenience of installment payments under appropriate conditions to users with a high need for installment payments. [Explanation of symbols]

[0063] 1. Information processing device

Claims

1. a credit score estimation means for estimating a credit score to be set for a user using a credit score estimation model generated and / or updated using training data in which a group of attribute data relating to a user is used as an input value and a credit score determined based on a payment history of a deferred payment related to a user who has a common group of attribute data as an output value is a credit score that changes according to a deferred payment risk that the settlement of the deferred payment will not be properly fulfilled by the user when the user uses the deferred payment; a condition setting means for setting installment payment conditions selectable by the user when the user makes installment payments based on the creditworthiness of the user indicated by the credit score; a credit data determination means for determining whether or not a sufficient amount of credit data has been accumulated for the user for setting installment payment conditions without being based on a credit score that changes according to the deferred payment risk; a notification means for notifying the user of the installment payment conditions selectable by the user, which are set by the condition setting means; The condition setting means sets the interest rate for the installment payments within a range having a preset upper or lower limit, The credit score estimation means estimates a credit score that changes according to the deferred payment risk for at least a user determined to have an insufficient amount of accumulated credit data, The condition setting means sets the installment payment conditions for at least a user who is determined to have an insufficient amount of accumulated credit data, the notification means notifies at least the user for whom it is determined that the accumulated amount of the credit data is insufficient of the installment payment conditions; Information processing system.

2. The condition setting means sets, as the installment payment conditions, at least one of the following: whether installment payments are possible, the interest rate of installment payments, the upper limit of the number of installments of the installment payments, the upper limit of the installment payment amount, and the lower limit of the initial payment amount. The information processing system according to claim 1 .

3. the condition setting means sets the upper limit of the number of installments of the installment payment further based on the length of a life cycle of the product or service that is the subject of the installment payment; The information processing system according to claim 2 .

4. The payment method further includes a notification means for notifying a user of the installment payment conditions selectable by the user, which are set by the condition setting means. The information processing system according to claim 1 .

5. the condition setting means sets installment payment conditions selectable by the user when the user makes installment payments for the purchase price of the mobile terminal, based on the creditworthiness of the user indicated by the credit score; the notification means further notifying the user of an offer to subscribe to a communications service for the mobile terminal.

5. The information processing system according to claim 4.

6. The credit score estimation means estimates the credit score using the credit score estimation model generated and / or updated using a machine learning framework based on gradient boosting decision trees. The information processing system according to claim 1 .

7. a fact attribute determining means for determining a fact attribute that can be confirmed as a fact about the user based on user-provided data provided by the user himself or history data of the user; and determining an estimated attribute of the user based on at least the factual attribute of the user, The credit score estimation means estimates a credit score of the target user based on a group of attribute data including the fact attributes and estimated attributes related to the target user. The information processing system according to claim 1 .

8. The computer a credit score estimation step of estimating a credit score to be set for the user using a credit score estimation model generated and / or updated using training data in which a group of attribute data relating to a user is used as an input value and a credit score determined based on a payment history of a deferred payment related to a user who has a common group of attribute data as an output value, the credit score varying according to a deferred payment risk that the settlement of the deferred payment will not be properly fulfilled by the user when the user uses the deferred payment; a condition setting step of setting installment payment conditions selectable by the user when the user makes installment payments based on the creditworthiness of the user indicated by the credit score, and notifying the user of the set installment payment conditions; In the condition setting step, an interest rate for the installment payment is set within a range having a predetermined upper or lower limit set in advance, In the credit score estimation step, for a user who is determined to have insufficient accumulated credit data because the amount of accumulated credit data is not sufficient for setting installment payment terms without being based on the credit score, a credit score that changes according to the deferred payment risk is estimated; In the condition setting step, the installment payment conditions are set for at least the user who is determined to have an insufficient amount of accumulated credit data, and the installment payment conditions are notified to at least the user who is determined to have an insufficient amount of accumulated credit data. Information processing methods.

9. Computer, a credit score estimation means for estimating a credit score to be set for a user using a credit score estimation model generated and / or updated using training data in which a group of attribute data relating to a user is used as an input value and a credit score determined based on a payment history of a deferred payment related to a user who has a common group of attribute data as an output value is a credit score that changes according to a deferred payment risk that the settlement of the deferred payment will not be properly fulfilled by the user when the user uses the deferred payment; a condition setting means for setting installment payment conditions selectable by the user when the user makes installment payments based on the creditworthiness of the user indicated by the credit score, and notifying the user of the set installment payment conditions; The condition setting means sets the interest rate for the installment payments within a range having a preset upper or lower limit, The credit score estimation means estimates a credit score that changes according to the deferred payment risk for a user who is determined to have insufficient accumulated credit data because the amount of accumulated credit data is not sufficient for setting installment payment terms without being based on at least the credit score, the condition setting means sets the installment payment conditions for at least the users who are determined to have an insufficient amount of accumulated credit data, and further notifies the installment payment conditions to at least the users who are determined to have an insufficient amount of accumulated credit data; program.

Images