Program, information processing method, and information processing system

Abstract

To provide a technique for predicting whether a receivable is likely to be a bad debt or a business operator is highly creditworthy.SOLUTION: A program causes an information processing system to execute the following steps: an acquisition step of acquiring predictive examination information, the predictive examination information being information on a business operator or a receivable for which potential bad debt is predicted; an output control step of outputting bad-debt information based on the predictive examination information and a bad-debt estimation model, the bad-debt information being information indicating whether the receivable is to become a bad debt or not, the bad-debt estimation model being a learning model obtained through machine learning using information included in training examination information as features, and the training examination information being information on the business operator or the receivable subjected to credit screening.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a program, an information processing method, and an information processing system.

Background Art

[0002] In the prior art, a system, a program, an information processing apparatus, and a method for credit examination for more accurately performing a credit examination of a user have been disclosed (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in recent years, there has been a demand for a technology that can predict whether a debt may become bad or whether a business operator has a high creditworthiness.

[0005] In view of the above circumstances, the present invention aims to provide a technology capable of predicting whether a debt may become bad or whether a business operator has a high creditworthiness.

Means for Solving the Problems

[0006] According to one aspect of the present invention, there is provided a program for causing an information processing system to execute the following steps. In an acquisition step, prediction examination information is acquired. The prediction examination information is information regarding an operator or a claim that is a target of prediction of bankruptcy. In an output control step, bankruptcy information is output based on the prediction examination information and a bankruptcy estimation model. The bankruptcy information is information indicating whether a claim will go bankrupt. The bankruptcy estimation model is a learning model obtained by performing machine learning using information included in learning examination information as feature amounts. The learning examination information is information regarding an operator or a claim that is a target of credit examination. The program is provided.

[0007] According to the present disclosure, it is possible to provide a technology capable of predicting whether a claim may go bankrupt or whether an operator has a high credit rating.

Brief Description of Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic matters shown in the following embodiments can be combined with each other.

[0010] [Embodiment 1] 1. Definition of Terms By the way, a program for realizing software appearing in one embodiment may be provided as a non-transitory computer-readable medium that can be read by a computer, may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its function is realized on a client terminal (so-called cloud computing).

[0011] Also, in various information processes according to one embodiment, an input and an output corresponding to the input can be realized. Here, if an output is obtained as a result of the input, the mode of information (hereinafter referred to as reference information) referred to in such information processing is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, a predetermined function (including a determination formula such as a regression formula constructed by a statistical method), a learned model in which the correlation between the input and the output is learned in advance, or a large language model capable of outputting a desired result by inputting a prompt.

[0012] Also, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0013] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. Also, the processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] FIG. 1 is a diagram for explaining positive information and false positive information. In this specification, a technique for predicting whether a claim obtained from a certain operator will go bad or the creditworthiness of the operator is high using data from past credit reviews will be described.

[0015] "Credit review" means reviewing the creditworthiness of an operator such as its financial strength and repayment ability. Credit review includes the review in factoring.

[0016] A "case" refers to a claim acquired from any creditor or the original creditor from whom the claim is transferred. When the case is a claim, the case may be, for example, a claim purchased by a factoring operator, a claim acquired by a certain operator, etc. When the case is a creditor, the creditor is a subject that transfers the claim to a factoring operator, a subject that transfers the claim to a certain operator, etc.

[0017] The cases approved in the credit review are finally classified into those that go bad or those that are refunded. Generally, there are few cases that go bad. Therefore, it is relatively difficult to obtain a learning model for predicting whether the creditworthiness of a claim or operator that goes bad is high from only the approved cases, from the perspective of the number of data. In this specification, a learning model for predicting whether the creditworthiness of a claim or operator that goes bad is high is obtained using the cases rejected in the credit review. Specifically, in the credit review, among the rejected cases, if they had been approved in the credit review, classify whether the case would result in going bad or being refunded. Among the classified cases, a case that was rejected in the credit review and, if approved in the credit review, is predicted to go bad is referred to as positive. Also, among the classified cases, a case that was rejected in the credit review and, if approved in the credit review, is predicted to be refunded without going bad is referred to as false positive. The data classified as positive and the data classified as false positive are used as labels for the training data in machine learning.

[0018] Positive information is information associated with cases classified as positive. "Positive information" refers to information indicating that, assuming a certain claim or a certain operator has passed the credit review, it has been determined that a bad debt has occurred for the claim or the claim acquired from the operator.

[0019] "False positive information" refers to information associated with cases classified as false positives. "False positive information" is information indicating that, assuming a certain debt or a certain operator has passed the credit review, no default has occurred for the debt associated with the credit review or the debt obtained from the operator.

[0020] 2. System Configuration of Information Processing System 1 First, the system configuration of the information processing system 1 according to Embodiment 1 will be described with reference to FIG. 2.

[0021] FIG. 2 is a diagram showing an example of the system configuration of the information processing system 1 according to Embodiment 1. As shown in FIG. 2, the information processing system 1 includes a server device 2, a client device 3, and a network N. The server device 2 is configured to be communicable with the client device 3 via the network N. Thereby, the server device 2 and the client device 3 can transmit or receive various information to and from each other. Note that the server device 2 and the client device 3 are examples of information processing devices and are not limited to this embodiment. The client device 3 may be any of a PC (Personal Computer), a tablet computer, a smartphone, etc. Note that there may be a plurality of server devices 2 and client devices 3.

[0022] 3. Hardware Configuration Next, the hardware configuration of the server device 2 according to Embodiment 1 will be described with reference to FIG. 3, and the hardware configuration of the client device 3 according to Embodiment 1 will be described with reference to FIG. 4.

[0023] 3.1. Hardware Configuration of Server Device 2 FIG. 3 is a diagram showing an example of the hardware configuration of the server device 2 according to Embodiment 1. As shown in FIG. 3, the server device 2 includes a processor 21, a storage unit 22, and a communication unit 23, and these components are electrically connected via a communication bus inside the server device 2. The server device 2 executes the processing according to the embodiment.

[0024] The processor 21 performs processing and control of the overall operations related to the server device 2. The processor 21 is, for example, a Central Processing Unit (CPU). By reading a predetermined program stored in the storage unit 22 and executing processing based on the program, various functions related to the server device 2, for example, the processing shown in FIG. 6 described later, are realized. Note that the processor 21 is not limited to being single, and may be implemented to have a plurality of processors 21 for each function. Also, combinations thereof may be used.

[0025] The storage unit 22 stores various information defined by the foregoing description. This may be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs and the like related to the server device 2 executed by the processor 21, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the operation of the program. The storage unit 22 stores various programs, variables, and data used by the processor 21 when executing processing based on the program related to the server device 2. The storage unit 22 is an example of a storage medium.

[0026] The communication unit 23 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may include wireless LAN network communication, mobile communication such as LTE / 3G / 4G / 5G, BLUETOOTH (registered trademark) communication, etc. as required. That is, it is more preferable to implement it as a collection of these plural communication means. That is, the server device 2 may communicate various information from the outside via the communication unit 23.

[0027] 3.2. Hardware Configuration of the Client Device 3 FIG. 4 is a diagram showing an example of the hardware configuration of the client device 3 according to Embodiment 1. As shown in FIG. 4, the client device 3 includes a processor 31, a storage unit 32, a communication unit 33, an input unit 34, and an output unit 35, and these components are electrically connected via a communication bus inside the client device 3. The client device 3 executes the processing according to the embodiment. For the processor 31, the storage unit 32, and the communication unit 33 of the client device 3, refer to the processor 21, the storage unit 22, and the communication unit 23 of the server device 2.

[0028] The input unit 34 may be included in the housing of the client device 3 or may be externally attached. For example, the input unit 34 may be integrated with the output unit 35 and implemented as a touch panel. In the case of a touch panel, the user can input a tap operation, a swipe operation, etc. Of course, instead of the touch panel, a switch button, a mouse, a QWERTY keyboard, etc. may be adopted. That is, the input unit 34 receives an input based on an operation made by the user. The input is transferred to the processor 31 via the communication bus as a command signal, and the processor 31 can execute predetermined control or calculation as necessary.

[0029] The output unit 35 can function as a display unit of the client device 3. The output unit 35 may be included in the housing of the client device 3 or may be externally attached, for example. The output unit 35 displays a screen of a graphical user interface (GUI) operable by the user. This is preferably implemented by selectively using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the client device 3.

[0030] 4. System Configuration of the Information Processing System 1 In this section, while showing FIG. 5, the functional configuration of the processor 21 of this embodiment will be described. FIG. 5 is an example of a block diagram showing the functions realized by the processor 21 of the server device 2. The processor 21 of the server device 2, which is an example of the information processing system 1, includes an information transmission / reception unit 210, a learning unit 211, an output control unit 212, a determination unit 213, and a display control unit 214. As described above, the information processing by software stored in the storage unit 22 is specifically realized by the processor 21, which is an example of hardware, and can be executed as each functional unit included in the processor 21.

[0031] The information transmission / reception unit 210 receives, accepts, or acquires various information from the client device 3 via the network N and the communication unit 23. The information transmission / reception unit 210 transmits various information to the client device 3 via the communication unit 23 and the network N. The information transmission / reception unit 210 executes, for example, an acquisition step.

[0032] The learning unit 211 acquires a bad debt estimation model based on teacher data. The learning unit 211 executes, for example, a learning step.

[0033] The output control unit 212 controls the output of data using the bad debt estimation model. The output control unit 212 executes, for example, an output control step.

[0034] The determination unit 213 determines whether bad debt has occurred in the creditor's rights or whether the creditworthiness of the business operator is high. The determination unit 213 executes, for example, a determination step.

[0035] The display control unit 214 is configured to control the screen data to be displayed on the output unit 35 of each information processing device. The display control unit 214 executes, for example, a display control step. Note that the screen data may be the visual information itself generated in a form visible to the user, such as a screen, an image, an icon, or text, or may be rendering information for causing various terminals to display visual information such as a screen, an image, an icon, or text.

[0036] The details of the information transmission / reception unit 210, the information transmission / reception unit 210, the learning unit 211, the output control unit 212, the determination unit 213, and the display control unit 214 will be described later.

[0037] 5. Information Processing of the Information Processing System 1 Subsequently, an example of preferable information processing executed by the information processing system 1 of the present embodiment will be described.

[0038] Note that, in this specification, various data transmitted and received via the network N, the communication unit 23, and the communication unit 33 may be stored in the storage unit 22 and the storage unit 32, respectively.

[0039] Also, in this specification, a part of the configuration used for information processing related to the network N, the communication unit 23, the communication unit 33, and the input unit 34 may be omitted from the description. For example, the case where the processor 31 receives a predetermined input via an operation on the input unit 34 by the user may be simply described as the processor 31 receiving a predetermined input from the user. Also, the case where the processor 21 transmits and receives information to and from the client device 3 via the communication unit 23, the network N, and the communication unit 33 may be simply described as the processor 21 transmitting information to the client device 3, or simply as the processor 21 receiving information from the client device 3 and omitted from the description. The same applies to the case where the processor 31 transmits and receives information to and from the server device 2 via the communication unit 33, the network N, and the communication unit 23.

[0040] 5.1. Outline of Information Processing In this section, the information processing method by the above-described information processing system 1 will be described. FIG. 6 is a diagram showing an example of an activity indicating the flow of information processing executed by the information processing system 1 according to Embodiment 1. In FIG. 6, the processes of A1 to A6 are processes for acquiring the credit risk estimation model 5, and the processes of A7 to A13 are processes of prediction using the credit risk estimation model 5.

[0041] In A1, the processor 31 acquires learning review information 4 that serves as teacher data. The learning review information 4 is information regarding an operator or a creditor that is the subject of a credit review. The learning review information 4 will be described later with reference to FIG. 7. In A2, the processor 31 receives an instruction to start machine learning from the user. When receiving an instruction to start machine learning from the user, the processor 31 transmits the learning review information 4 that serves as teacher data and an instruction for machine learning to the server device 2. In A3, the information transmission / reception unit 210 receives the learning review information 4 that serves as teacher data and an instruction for machine learning from the client device 3. In A4, the learning unit 211 acquires a bankruptcy prediction model 5 using the learning review information 4 as a feature amount. The learning unit 211 acquires the bankruptcy prediction model 5. The acquisition of the bankruptcy prediction model 5 by machine learning will be described later with reference to FIG. 8. In A5, the display control unit 214 transmits screen data including the fact that the bankruptcy prediction model 5 has been acquired to the client device 3. In A6, the processor 31 receives screen data including the fact that the bankruptcy prediction model 5 has been acquired from the server device 2. Thereafter, the processor 31 causes the output unit 35 to display the screen data including the fact that the bankruptcy prediction model 5 has been acquired. For example, the processor 31 causes the output unit 35 to display information indicating that the machine learning has been completed and the bankruptcy prediction model 5 has been acquired, such as "Machine learning has been completed, and the prediction model has been acquired", based on the screen data.

[0042] The above processes A1 to A6 are processes related to the acquisition of the bankruptcy prediction model 5. According to the configurations from A1 to A6, it is possible to acquire a bankruptcy prediction model 5 capable of determining whether a company will go bankrupt. Note that in FIG. 7, the processes A1 to A13 are described as if they are a series of processes, but the information processing system 1 may execute the processes for acquiring the bankruptcy prediction model 5 from A1 to A6 and the processes related to prediction using the bankruptcy prediction model 5 from A7 to A13 at different timings as not being a series of processes. For example, when the bankruptcy prediction model 5 has already been acquired, the information processing system 1 may omit the processes A1 to A6 and execute only the processes A7 to A13.

[0043] In A7, the processor 31 acquires the prediction review information 6 of the debt to be predicted. The processor 31 receives an instruction for prediction using the default estimation model 5 from the user. The prediction review information 6 is information regarding the business operator or debt that is the target of the prediction of whether it will go bankrupt. In A8, when receiving an instruction for prediction from the user, the processor 31 transmits the prediction review information 6 and the instruction for prediction to the server device 2. In A9, the information transmission / reception unit 210 acquires the prediction review information 6 by receiving the prediction review information 6 and the instruction for prediction from the client device 3. In A10, the output control unit 212 outputs the default information 7 based on the default estimation model 5 and the prediction review information 6. The default information 7 is information indicating whether the debt will go bankrupt. The output of the default information 7 using the default estimation model 5 will be described later with reference to FIG. 9. In A11, the display control unit 214 generates screen data including the default information 7 as the display content. The information transmission / reception unit 210 transmits the screen data including the default information 7 as the display content to the client device 3. In A12, the processor 31 receives the screen data including the default information 7 as the display content from the server device 2. In A13, the processor 31 causes the output unit 35 to display information regarding the default information 7 based on the screen data including the default information 7 as the display content. The output default information 7 will be described later with reference to FIG. 10.

[0044] As described above, according to the present disclosure, it is possible to provide a technology capable of predicting whether a debt may go bankrupt.

[0045] 5.2. Details of Information Processing Next, with reference to FIGS. 7 to 10, the detailed part of the information processing outlined above will be described. First, with reference to FIG. 7, the learning review information 4 serving as teacher data will be described.

[0046] FIG. 7 is a diagram showing an example of learning review information 4. The learning review information 4 is data used as teacher data for obtaining the default estimation model 5. The learning review information 4 is information on a business operator or a creditor that is the subject of credit review. The learning review information 4 is information on a business operator or a creditor that did not pass the credit review, and includes either positive information or false positive information as a label. In FIG. 7, information on three business operators, "A", "B", and "C", is illustrated.

[0047] The learning review information 4 is prepared by a user who operates the client device 3. For example, the processor 31 of the client device 3 accesses a database in which pre-processed data is stored, and obtains pre-processed data on one or more business operators or one or more creditors. The database only needs to be able to obtain information on a business operator or a creditor. For example, it includes databases provided by financial business operators such as banks and Fintech business operators, databases provided by business operators that conduct credit investigations of companies such as Teikoku Databank, and the like. The pre-processed data obtained here is information before being converted into the learning review information 4. Note that the pre-processed data may include at least one of the amount information 40, the number information 41, the time information 42, and the determination information 43. Also, the pre-processed data may be data that can obtain at least one of the amount information 40, the number information 41, the time information 42, and the determination information 43 by applying a predetermined conditional expression. The learning review information 4 is obtained by adding positive / false positive information 44 to information including at least one of the amount information 40, the number information 41, the time information 42, and the determination information 43. The information processing for generating the learning review information 4 from the above-described pre-processed data may be performed in the server device 2.

[0048] The learning review information 4 includes the amount information 40. The amount information 40 is information on the amounts related to the business operator or information derived from the amounts related to the business operator. The information on the amounts related to the business operator may include any numerical values obtained from financial statements such as cash flow statements, profit and loss statements, and balance sheets. The information on the amounts related to the business operator may include the information on the amounts used in the business operator's final tax return. The information on the amounts related to the business operator may include the amounts borrowed by the business operator (including, for example, loans from financial institutions and officer loans) and the amounts repaid. The information on the amounts related to the business operator may include the information on the amounts procured. The information on the amounts related to the business operator may include the information on the business operator's balance and the amounts that can be derived from the business operator's balance. Also, the information derived from the amounts related to the business operator includes financial indicators. The information derived from the amounts related to the business operator may include, in addition to financial indicators, for example, statistical values (average values, median values, maximum values, minimum values, etc.) calculated from the information on the amounts related to the business operator for any period. It may be information on any value calculated from the information on the amounts related to the business operator described above. Specifically, for example, the amount information 40 may include at least one of the following. · Information indicating the operating profit rate of the business operator in the most recently completed accounting period (not limited to this, for example, information indicating a ratio such as "7.4%") · Information indicating the accounts receivable turnover rate of the business operator in the most recently completed accounting period (not limited to this, for example, a value that can be derived from an equation such as "accounts receivable turnover period = accounts receivable at the end of the previous period / (annual sales of the previous period / 12)", and information indicating the number of times such as "3.5 times". Also, instead of the accounts receivable turnover period, the sales receivables turnover rate may be used.) · Information indicating the compensation amount of the representative officer of the business operator in the most recently completed accounting period (not limited to this, for example, information indicating an amount such as "28,000,000 yen") · Information showing the growth rate of the remuneration of the representative officers of the business operator in the most recent completed accounting period compared to the remuneration of the representative officers in the accounting period of the previous year from the most recent completed accounting period (not limited to this, for example, a value obtained by dividing the value in the most recent completed accounting period by the value in the accounting period of the previous year from the most recent completed accounting period, and information indicating a ratio such as "130%") · Information showing the difference between the total assets and the total liabilities (not limited to this, for example, information indicating an amount such as "2,000,000 yen") · Information showing the annual business volume of the business operator in the most recent completed accounting period (not limited to this, for example, information indicating an amount such as "10,000,000 yen") · Information showing the annual business volume of the business operator in the accounting period of the previous year from the most recent completed accounting period (not limited to this, for example, information indicating an amount such as "8,000,000 yen") · Information showing the growth rate of the annual business volume of the business operator comparing the annual business volume of the business operator in the most recent completed accounting period with the annual business volume of the business operator in the accounting period of the previous year from the most recent completed accounting period (not limited to this, obtained by dividing the annual business volume of the business operator in the most recent completed accounting period by the annual business volume of the business operator in the accounting period of the previous year from the most recent completed accounting period, and information indicating a ratio such as "125%") · Information showing the value obtained by dividing the amount of accounts payable in the most recent completed accounting period by the annual business volume (not limited to this, for example, information indicating a ratio such as "10.5") · Information showing the outstanding borrowing of the business operator from non-banks (not limited to this, for example, information indicating an amount such as "20,000,000 yen") · Information showing the procurement amount of the business operator by factoring most recently (not limited to this, for example, information indicating an amount such as "5,000,000 yen") · Information showing the borrowing amount of the business operator in the most recent completed accounting period (not limited to this, for example, information indicating an amount such as "5,000,000 yen") · Information indicating the borrower's monthly sales multiple of borrowings during the most recently ended accounting period (which is not limited to this, but is a value that can be derived from equations such as "borrower's monthly sales multiple of borrowings = borrowings ÷ (annual sales ÷ 12)", and for example, information indicating a ratio such as "2.4", etc.) Note that the "most recently ended accounting period" is the accounting period corresponding to the previous period, based on the point in time when the lender uses the bad debt estimation model 5 to predict whether the borrower will go bankrupt. Thus, using the acquirable amount information 40 as a feature quantity, it is possible to obtain a bad debt estimation model 5 that can predict whether the creditor's rights may become bad debts or whether the borrower has a high creditworthiness.

[0049] The learning review information 4 includes numerical information 41. The numerical information 41 is information regarding some kind of number related to the borrower. For example, the numerical information 41 is information indicating the number of borrowers narrowed down from a specific perspective that have transactions with a certain borrower, or information indicating a number related to the transactions of a certain borrower. Specifically, for example, the numerical information 41 may include at least one of the following. · Information indicating the average number of details on a monthly basis up to the month before the review (which is not limited to this, but for example, the number of "deposits" and "withdrawals" of a bank account, the number of transactions (number of lines) recorded in a passbook, etc., and for example, information indicating a number of times such as "110 times") · Information indicating the number of non - banks used by the borrower (which is not limited to this, but for example, information indicating the number of borrowers such as "6 companies") · Information indicating the number of factoring companies used by the borrower (which is not limited to this, but for example, information indicating the number of borrowers such as "5 companies") · Information in which the level of risk provided by a borrower engaged in the business of credit investigation is shown numerically (which is not limited to this, but for example, information indicating the level of risk of the borrower such as "level 5", information indicating the number of events or actions defined as risks for the borrower such as "11 cases", etc.) Thus, using the acquirable numerical information 41 as a feature quantity, it is possible to obtain a bad debt estimation model 5 that can predict whether the creditor's rights may become bad debts or whether the borrower has a high creditworthiness.

[0050] The learning review information 4 includes time information 42. The time information 42 is information obtained by combining the application date of the review and other timing information. The other timing information may be any information that can identify a certain timing. For example, it includes information such as the establishment date when the business operator was established, the date of a transaction such as a deposit or withdrawal to / from the business operator's account, and the desired date regarding borrowing or procurement input by the business operator. Specifically, for example, the time information 42 may include at least one of the following. · Information indicating how many years since establishment at the time of application for the review (not limited to this, for example, information indicating the number of years such as "5 years") · Information indicating the number of days from the application date of the review to the desired date of procurement (not limited to this, for example, information indicating the number of days such as "30 days") · Information indicating the number of days from the application date of the review to the date of the most recent borrowing from a non-bank (not limited to this, for example, information indicating the number of days such as "30 days") · Information indicating the number of days from the application date of the review to the date of the most recent deposit from a factoring business operator (not limited to this, for example, information indicating the number of days such as "30 days") · Information indicating the number of days from the application date of the review to the date of borrowing from a bank (not limited to this, for example, information indicating the number of days such as "30 days") Note that in the above examples, there is no need to be limited to the number of years or days, and any unit of time such as year, month, week, day, hour, etc. may be used. Thereby, using the obtainable time information 42 as a feature quantity, it is possible to obtain a bad debt estimation model 5 that can predict whether a creditor's right may become a bad debt or whether the creditworthiness of the business operator is high.

[0051] The learning review information 4 includes determination information 43. The determination information 43 may include information regarding the business viability of the business operator, information regarding any relationship between the business operator and a bank, information regarding any relationship between the business operator and a listed company (which may be for each market segment), and information regarding any relationship between the business operator and an unlisted company. The information regarding the business viability of the business operator may be information regarding the delay, arrears, non-payment, etc. of the business operator's payments. Hereinafter, the information recorded as the determination information 43 may be in any form that can identify whether it is applicable. For example, it may be represented by "TRUE" or "FALSE", a circle or a cross, "1" or "0", etc. Specifically, for example, the determination information 43 may include at least one of the following. · Information indicating whether it can be considered that the business operator has a repayment delay of debts (this information may be information indicating that there is a transaction in which the payment date is recorded after the repayment date. Also, this information may be information determined based on the number of repayment delays or the total amount of repayment delays). · Information indicating whether it can be considered that the business operator has a payment delay of accounts payable (this information may be information indicating that there is a transaction in which the actual payment date is recorded after the scheduled payment date of the accounts payable. This information may be information determined based on the number of payment delays or the total amount of payment delays). · Information indicating whether it can be considered that the business operator has a repayment arrears to a non-bank (this information may be information indicating whether there is a transaction in which the payment date is recorded after the repayment date to the non-bank). · Information indicating whether it can be considered that there is no delay in the payment of social insurance by the business operator (this information may be information indicating whether there is a transaction in which the actual payment date is recorded after the scheduled payment date of the social insurance). · Information indicating whether it can be considered that the business operator has a large amount of officer loans (this information may be information determined based on the amount of the loans or the number of loans). · Information indicating whether the claim is not a claim not subject to purchase (Claims not subject to purchase include claims related to anti-social forces, claims with undetermined amounts or payment dates, claims that have already exceeded the payment deadline (arrears claims), etc.) · Information indicating whether the claim can be regarded as a claim at the stage of billing where the provision of services has been completed (This information may be determined by the examiner in the credit review.) · Information indicating whether the claim can be regarded as a claim for a subsidy or grant with an undetermined amount of receipt (This information may be determined by the examiner in the credit review.) · Information indicating whether it is possible to confirm capital contributions from investors related to the business operator at the time of filing the review application (This information may be determined by the examiner in the credit review.) · Information indicating whether the use of the business operator's funds can be regarded as specific at the time of filing the review application (Whether the use of the business operator's funds is specific may be determined by using an algorithm for natural language processing. Also, this information may be determined by the examiner in the credit review.) · Information indicating whether it can be considered that there is a continuous transaction between the business operator and the debtor of the claim subject to purchase (Whether it can be considered that there is a continuous transaction may be determined by the number of transactions or the amount of transactions. Also, this information may be determined by the examiner in the credit review.) · Information indicating whether it is possible to confirm unpaid corporate tax for the year before last at the time of the previous year's settlement · Information indicating whether it is possible to confirm unpaid social insurance premiums for the year before last at the time of the previous year's settlement · Information indicating that a large amount of funds transfer is taking place between related companies (Whether a large amount of funds transfer is taking place between related companies may be determined by the number of transactions or the amount of transactions. This information may be determined by the examiner in the credit review.) · Information indicating that there are many transactions in cash on hand and the actual situation of cash inflows and outflows cannot be grasped (Whether there are many transactions in cash on hand and the actual situation of cash inflows and outflows cannot be grasped may be determined by the number of transactions or the amount of transactions. This information may be determined by the examiner in the credit review.) · Information indicating whether an operator can be considered to have changed the factoring operator it uses · Information indicating whether a history of bankruptcy or civil rehabilitation can be confirmed for the representative of the operator · Information indicating the determination result of the operator in a predetermined indicator representing the ease of bankruptcy (the predetermined indicator representing the ease of bankruptcy is, for example, an indicator defined by an operator that conducts credit rating, grading, etc. of the operator.) · Information indicating whether the operator has a homepage · Information indicating whether there has been a transfer of claims by subrogation to the operator in the past · Information indicating whether a trial balance can be considered to have been submitted by the operator (For example, by determining whether a balance sheet or monthly trend statement has been submitted by the operator, it may be considered that a trial balance has been submitted.) Thereby, by using the acquirable determination information 43 as a feature quantity, it is possible to obtain a bad debt estimation model 5 that can predict whether a claim may go bad or whether the creditworthiness of the operator is high.

[0052] Positive false positive information 44 is information indicating whether a case (here, a claim) is positive or false positive. The positive false positive information 44 may be mechanically assigned based on the amount information 40, quantity information 41, time information 42, and determination information 43 using rule-based or machine learning, etc., or may be assigned by a user with rich experience in credit examination. In the example of FIG. 7, the positive false positive information 44 is represented by "positive" or "false positive", but it may be represented by a circle or a cross, "1" or "0", etc., and is not limited thereto.

[0053] FIG. 8 is a diagram showing an example for explaining information processing related to the acquisition of the bad debt estimation model 5. FIG. 8 includes learning review information 4 and the bad debt estimation model 5.

[0054] The bad debt estimation model 5 is a learning model obtained by using the information included in the learning review information 4 as feature quantities. The bad debt estimation model 5 is constructed by any machine learning algorithm. The explanatory variables as the feature quantities of the bad debt estimation model 5 are amount information, quantity information, time information, and judgment information. Also, the target variables as the feature quantities of the bad debt estimation model 5 are positive information and false positive information. Thereby, it is possible to obtain a learning model that can be used to determine the risk of a claim or a business operator subject to credit review without using data of cases that have gone bad.

[0055] FIG. 9 is a diagram showing an example for explaining the information processing for outputting the bad debt information 7 from the bad debt estimation model 5. FIG. 9 includes prediction review information 6, the bad debt estimation model 5, and the bad debt information 7.

[0056] The prediction review information 6 is information regarding a business operator or a claim that is the target of prediction of going bad. The prediction review information 6 is prepared by a user who uses the client device 3. The prediction review information 6 includes at least one of the amount information 60, quantity information 61, time information 62, and judgment information 63 of the business operator to be predicted.

[0057] The bad debt estimation model 5 in FIG. 9 is a learning model learned to output the bad debt information 7 as output data in response to the input of the prediction review information 6 as input data.

[0058] The bad debt information 7 is information indicating whether the claim will go bad. The bad debt information 7 includes bad debt probability information 70 and bad debt occurrence information 71 as shown in FIG. 10.

[0059] FIG. 10 is a diagram showing an example of the bad debt information 7. The bad debt information 7 may be data in a format in which bad debt probability information 70 and bad debt occurrence information 71 are added to the prediction review information 6. The bad debt information 7 includes amount information 60, quantity information 61, time information 62, determination information 63, bad debt probability information 70, and bad debt occurrence information 71. In the example of FIG. 10, the prediction review information 6 includes one each of the amount information 60, quantity information 61, time information 62, and determination information 63, but is not limited thereto, and may not include any of the amount information 60, quantity information 61, time information 62, and determination information 63, or there may be a plurality of any of the information. In FIG. 10, information regarding the business operator "Ding" is illustrated.

[0060] The bad debt probability information 70 includes information on the probability of bad debt occurring for the creditor's rights. The bad debt probability information 70 includes information on the probability of whether the creditor's rights will become bad debt. The format of the output probability may be any format such as 0 to 100% or 0 to 1. The output control unit 212 outputs the bad debt probability information 70 based on the prediction review information 6 and the bad debt estimation model 5. By referring to the bad debt probability information 70, the probability of whether the creditor's rights will become bad debt can be confirmed, so it can be used as a reference for reviewing the creditworthiness such as the repayment ability of the business operator in the credit review.

[0061] In addition, the bad debt probability information 70 includes information indicating whether the claim will become a bad debt. In the example of FIG. 10, the bad debt occurrence information 71 is represented by "positive" or "false positive", but it may be represented by a circle or a cross, "1" or "0", etc., and is not limited thereto. When the probability of bad debt occurring in the claim indicated by the bad debt probability information 70 output by the output control unit 212 is equal to or higher than a threshold value (for example, when the probability is represented by 0 to 100%, 60% or higher, etc.), the determination unit 213 outputs information indicating that the claim is highly likely to become a bad debt. Further, when the probability of bad debt occurring in the claim indicated by the bad debt probability information 70 output by the output control unit 212 is less than the threshold value (for example, when the probability is represented by 0 to 100%, less than 60%, etc.), the determination unit 213 outputs information indicating that the claim is less likely to become a bad debt. As a result, it is possible to obtain a result of predicting whether a claim will become a bad debt, and thus it can be used as a reference for examining the creditworthiness such as the repayment ability of an operator in credit examination.

[0062] [Embodiment 2] 6. Details of Information Processing In Section 6, the details of the information processing according to Embodiment 2 will be described. In Embodiment 2, descriptions overlapping with those in Embodiment 1 will be omitted as appropriate.

[0063] FIG. 11 is a diagram for explaining safe destination information and dangerous destination information. The learning review information 4 includes either one of the safe destination information and the dangerous destination information as a label 80.

[0064] The safe destination information is information including, as a safe destination, an operator who is considered not to have a bad debt occur for the claim when it is assumed that the claim is acquired from a certain operator. That is, the safe destination information is information including an operator corresponding to false positive information and an operator who can be considered not to have a delay or arrears in the determination information 43.

[0065] The information on the risk target is information that includes, as the risk target, the business operator for whom the non-performing loan of the claim may occur when assuming the acquisition of a claim from a certain business operator. That is, the information on the risk target is information that includes the business operator corresponding to the positive information and the business operator that can be regarded as having a delay or arrears in the determination information 43.

[0066] By constructing the non-performing loan estimation model 5 using the learning review information 4 including the label 80, the objective variable as a feature quantity of the non-performing loan estimation model 5 includes, in addition to the positive information and the false positive information, the safe target information and the risk target information. By using such a non-performing loan estimation model 5, a more comprehensive credit judgment can be realized.

[0067] FIG. 12 is a diagram showing an example of the learning review information 4. The learning review information 4 includes the amount information 45. The amount information 45 is information on the amount related to the business operator or information derived from the amount related to the business operator. The information on the amount related to the business operator may include any numerical value obtained from financial statements such as a cash flow statement, an income statement, and a balance sheet. The information on the amount related to the business operator may include information on the balance of the account owned by the business operator. Here, an "account" is a mechanism for managing the inflow and outflow of money. An account is provided by a bank, the post office, a securities company, etc., and can include various types of accounts in addition to a regular account and a current account. Specifically, the amount information 45 may include at least one of the following, for example. · Information indicating the financial status of the business operator (but not limited to this, for example, information indicating revenue and sales data and showing a ratio such as "150%" as the sales growth compared to the previous year) · Information indicating the balance of the business operator's account (but not limited to this, for example, information showing an amount such as "100,000,000 yen")

[0068] Information indicating the financial status is information indicating the financial performance of an operator at a certain point in time. Information indicating the financial status may include, in addition to revenue and sales data, for example, expense data, profit figures, asset information, liabilities, share data, cash flow statements, investment data, budgets and forecasts, tax records, credit information, market data, bank transaction statements and records, financial ratios, and other information. Information indicating the financial status is not stored in the database described in Embodiment 1 and usually exists in paper form. Therefore, in Embodiment 2, OCR or the like is used to read the paper medium, and information indicating the financial status is handled as electronic data.

[0069] Information indicating the account balance is information calculated from the balance information at a certain point in time included in the pre - processing data. More specifically, information indicating the account balance is, for example, information showing the balance at predetermined timings in a time series. The predetermined timings may be timings such as annually, monthly, weekly, daily, hourly, etc. Also, the predetermined timing may be when a transaction related to the account occurs or is completed. Information indicating the account balance includes any value calculated from the account balance. Any value includes statistical values, values defined for this information processing, and the like. In the embodiment, an average value is used as information indicating the account balance, but it is not limited thereto. For example, any statistical value such as an average value, median, minimum value, maximum value, mode, variance, standard deviation, skewness, kurtosis, etc. may be used. Also, information indicating the account balance may include information obtained from records of deposits or withdrawals from the account.

[0070] The explanatory variable as a feature of the bad debt estimation model 5 further includes the amount information 45. Thereby, a bad debt estimation model 5 capable of predicting whether a claim may become uncollectible or whether the operator has a high creditworthiness can be obtained by using the acquirable amount information 45 as a feature.

[0071] FIG. 13 shows an example of the credit risk information 7 output from the credit risk estimation model 5 by inputting the prediction review information 6 into the credit risk estimation model 5. The prediction review information 6 may further include the amount information 65 of the business operator to be predicted. The amount information 65 is information corresponding to the amount information 45. The credit risk information 7 may be data in a format in which credit risk probability information 70, credit risk occurrence information 71, and credit risk occurrence information 72 are added to the prediction review information 6. The credit risk information 7 includes amount information 60, number information 61, time information 62, determination information 63, credit risk probability information 70, credit risk occurrence information 71, and credit risk occurrence information 72. In the example of FIG. 13, the credit risk occurrence information 72 is represented by "safe destination" or "dangerous destination", but it may be represented by a circle or a cross, "1" or "0", etc., and is not limited thereto.

[0072] According to such an aspect, since the available information is used, the man-hour of manual review can be reduced and real-time review can be realized.

[0073] [Modification Example] Hereinafter, a modification example of the present embodiment will be described. The following modification examples can be combined as appropriate.

[0074] The program is a program that causes one or more computers to execute each functional unit (step). Further, the information processing system 1 includes one or more computers that execute the program. Regarding the information processing system 1 according to the above-described embodiment, it may be a program that causes a computer to function as the processor 21 of the information processing system 1. Further, it may be an information processing method executed by the information processing system 1 (or the processor 21 of the server device 2).

[0075] In the embodiment, the credit risk probability information 70 and the credit risk probability information 70 are output, but in the modification example, information indicating the degree of risk of acquiring a claim from a business operator and information indicating whether or not it is a risk to acquire a claim from a business operator may be output.

[0076] At least one of the devices included in the information processing system 1 may be installed outside Japan. For example, the server device 2 may be installed outside Japan, and each terminal device may be installed within Japan. Similarly, a user may access the server device 2 installed within Japan using their terminal device from outside Japan. According to such an aspect, it is possible to provide a more convenient experience for the user in various management forms.

[0077] The server device 2 may be in an on-premises form or a cloud form. As the cloud-form server device 2, for example, it may provide the above functions and processes in the form of SaaS (Software as a Service), cloud computing, etc.

[0078] In the above embodiment, the server device 2 performs various storage and controls. However, instead of the server device 2, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like.

[0079] In the above embodiment, the description has been made assuming that information processing is executed by at least two devices, the server device 2 and the client device 3. However, in a modification, information processing may be executed only by the client device 3.

[0080] [Others] Furthermore, it may be provided in each of the aspects described below.

[0081] (1) A program for causing an information processing system to execute the following steps: In an acquisition step, prediction review information is acquired, and the prediction review information is information regarding a business operator or a claim that is a target of prediction of bankruptcy. In an output control step, bankruptcy information is output based on the prediction review information and a bankruptcy estimation model, and the bankruptcy information is information indicating whether the claim will go bankrupt. The bankruptcy estimation model is a learning model obtained by performing machine learning using information included in learning review information as feature amounts, and the learning review information is information regarding a business operator or a claim that was the target of credit review.

[0082] (2) In the program according to (1) above, the learning review information is information on a business operator or a claim that did not pass the credit review, and includes either positive information or false positive information as a label. The positive information is information indicating that when it is assumed that the credit review was passed, it was determined that bankruptcy of the claim associated with the credit review occurred. The false positive information is information indicating that when it is assumed that the credit review was passed, it was determined that bankruptcy of the claim associated with the credit review did not occur.

[0083] (3) In the program according to (1) or (2) above, the prediction review information and the learning review information include amount information, and the amount information includes information indicating the business operator's operating profit rate in the most recently ended accounting period, information indicating the business operator's accounts receivable turnover rate in the most recently ended accounting period, information indicating the amount of remuneration of the representative officer of the business operator in the most recently ended accounting period, information indicating the growth rate of the amount of remuneration of the representative officer of the business operator obtained by comparing the amount of remuneration of the representative officer of the business operator in the most recently ended accounting period with the amount of remuneration of the representative officer in the accounting period of the previous year before the most recently ended accounting period, and information indicating the difference between the total assets and the total liabilities, and includes at least one of them.

[0084] (4) In the program according to any one of (1) to (3) above, the prediction review information and the learning review information include amount information, and the amount information includes information indicating the annual sales of the business operator in the accounting period that has most recently ended, information indicating the annual sales of the business operator in the accounting period of the year before the accounting period that has most recently ended, information indicating the growth rate of the annual sales of the business operator obtained by comparing the annual sales of the business operator in the accounting period that has most recently ended with the annual sales of the business operator in the accounting period of the year before the accounting period that has most recently ended, and information indicating the value obtained by dividing the amount of accounts payable in the accounting period that has most recently ended by the annual sales. The program includes at least one of these.

[0085] (5) In the program according to any one of (1) to (4) above, the prediction review information and the learning review information include amount information, and the amount information includes information indicating the outstanding balance of the business operator's borrowings from non-banks, information indicating the amount of funds procured by the business operator through factoring most recently, information indicating the amount of the business operator's borrowings in the accounting period that has most recently ended, and information indicating the monthly sales multiple of the business operator's borrowings in the accounting period that has most recently ended. The program includes at least one of these.

[0086] (6) In the program according to any one of (1) to (5) above, the prediction review information and the learning review information include numerical information, and the numerical information includes information indicating the average number of details per month up to the month before the review, information indicating the number of non-banks used by the business operator, information indicating the number of factoring operators used by the business operator, and information indicating the level of risk provided by business operators engaged in the business of credit investigation as a numerical value. The program includes at least one of these.

[0087] (7) In the program according to any one of (1) to (6) above, the prediction review information and the learning review information include time information, and the time information includes information indicating the number of years since establishment at the time of application for review, information indicating the number of days from the application date of review to the desired date of procurement, information indicating the number of days from the application date of review to the most recent borrowing date from a non-bank, information indicating the number of days from the application date of review to the deposit date from the most recent factoring company, and information indicating the number of days from the application date of review to the borrowing date from a bank, and includes at least one of them.

[0088] (8) In the program according to any one of (1) to (7) above, the prediction review information and the learning review information include determination information, and the determination information includes information indicating whether it can be considered that the business operator has a repayment delay of debt, information indicating whether it can be considered that the business operator has a repayment delay to a non-bank, information indicating whether it can be considered that there is no delay in the payment of social insurance of the business operator, information indicating whether it can be considered that the business operator has a payment delay of accounts payable, and information indicating whether it can be considered that the business operator has a large amount of officer's loan, and includes at least one of them.

[0089] (9) In the program according to any one of (1) to (8) above, the prediction review information and the learning review information include determination information, and the determination information includes information indicating whether the claim is not a claim not subject to purchase, information indicating whether the claim can be considered as a claim at the stage of billing with the service provision completed, information indicating whether the claim can be considered as a claim for a subsidy or grant with the amount to be received undetermined, information indicating whether the investment from the related party of the business operator can be confirmed at the time of application for review, and information indicating whether the use of funds of the business operator can be considered specific at the time of application for review, and includes at least one of them.

[0090] (10) In the program according to any one of (1) to (9) above, the prediction review information and the learning review information include determination information, and the determination information includes information indicating whether a business operator can be regarded as having continuous transactions with the debtor of the claim to be purchased, information indicating whether the business operator can be regarded as having continuous transactions, information indicating whether unpaid corporate tax for the year before last can be confirmed at the time of the previous year's settlement, information indicating whether unpaid social insurance premiums for the year before last can be confirmed at the time of the previous year's settlement, information indicating whether an examiner determines that there are a large number of fund transactions with an affiliated company, and information indicating whether an examiner determines that there are many cash transactions and the actual situation of cash inflows and outflows cannot be grasped, and includes at least one of them.

[0091] (11) In the program according to any one of (1) to (10) above, the prediction review information and the learning review information include determination information, and the determination information includes information indicating whether a business operator can be regarded as having changed the factoring business operator it uses, information indicating whether a bankruptcy history or a civil rehabilitation history can be confirmed for the representative of the business operator, information indicating the determination result of the business operator in a predetermined index representing the ease of bankruptcy, information indicating whether the business operator has a homepage, information indicating whether there has been a transfer of claim by subrogation to the business operator in the past, and information indicating whether a trial balance can be regarded as having been submitted by the business operator, and includes at least one of them.

[0092] (12) In the program according to any one of (1) to (11) above, the learning review information includes either safety destination information or danger destination information as a label. The safety destination information is information including the business operator corresponding to the false positive information described in (2) above and the business operator that can be regarded as having no delay or arrears in the determination information described in (8) above. The danger destination information is information including the business operator corresponding to the positive information described in (2) above and the business operator that can be regarded as having a delay or arrears in the determination information described in (8) above.

[0093] (13) In the program according to any one of (1) to (12) above, the prediction review information and the learning review information include amount information, and the amount information includes at least one of information indicating the financial state of the business operator and information indicating the balance of the business operator's account.

[0094] (14) In the program according to any one of (1) to (13) above, the bad debt information includes information on the probability that the claim will become a bad debt.

[0095] (15) In the program according to any one of (1) to (14) above, the information processing system further executes a determination step, the bad debt information includes information indicating whether the claim will become a bad debt, and in the determination step, when the probability that the claim will become a bad debt indicated by the bad debt information output in the output control step is equal to or greater than a threshold value, information indicating that the claim is likely to become a bad debt is output, and when the probability that the claim will become a bad debt indicated by the bad debt information output in the output control step is less than the threshold value, information indicating that the claim is unlikely to become a bad debt is output.

[0096] (16) An information processing method executed by an information processing system, the method comprising each step of the program according to any one of (1) to (15) above.

[0097] (17) An information processing system comprising one or more processors that execute the program according to any one of (1) to (15) above. Of course, this is not all-inclusive.

[0098] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. Such embodiments and their modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalent scope thereof.

Explanation of Signs

[0099] 1: Information processing system 2: Server device 3: Client device 4: Learning review information 5: Default estimation model 6: Prediction review information 7: Default information 21: Processor 22: Memory unit 23: Communication unit 31: Processor 32: Memory unit 33: Communication unit 34: Input unit 35: Output unit 40: Amount information 41: Numerical information 42: Time information 43: Judgment information 44: Positive false positive information 45: Amount information 60: Amount information 61: Numerical information 62: Time information 63: Judgment information 65: Amount information 70: Default probability information 71: Default occurrence information 72: Default occurrence information 80: Label 210: Information transmission / reception unit 211: Learning unit 212: Output control unit 213: Judgment unit 214: Represents the control unit N: Network

Claims

1. A program for causing an information processing system to execute the following steps: In the acquisition step, predicted screening information is acquired, The prediction screening information is information about a business entity or a claim that is the subject of a prediction of whether the claim will become uncollectible, In the output control step, bad debt information is output based on the prediction screening information and the bad debt estimation model, and the bad debt information is information indicating whether the receivable is bad debt, The bad debt estimation model is a learning model obtained by performing machine learning using information included in the learning review information as a feature, The learning screening information is information about a business operator or a claim that was the subject of a credit screening. program.

2. The program according to claim 1, The learning screening information is information on businesses or loans that have not passed a credit screening, and includes either positive information or false positive information as a label; The positive information is information indicating that, assuming that the credit screening had been passed, a default would have occurred on the receivables linked to the credit screening, The false positive information is information indicating that, if the credit screening had been passed, it would have been determined that there would have been no default on the receivables linked to the credit screening. program.

3. The program according to claim 1, The prediction review information and the learning review information include amount information, The amount information is Information showing the operator's operating profit margin for the most recently completed accounting period; and Information showing the business's accounts receivable turnover rate for the most recently completed accounting period; and Information showing the amount of executive compensation for the representative of the business for the most recently completed accounting period; and Information showing the growth rate of the amount of compensation for the representative executive officer of the business enterprise, comparing the amount of compensation for the representative executive officer of the business enterprise for the most recently completed accounting period with the amount of compensation for the representative executive officer of the business enterprise for the accounting period of the year prior to the most recently completed accounting period; and information indicating the difference between total assets and total liabilities. program.

4. The program according to claim 1, The prediction review information and the learning review information include amount information, The amount information is Information showing the business's annual turnover for the most recently completed accounting period; Information showing the annual turnover of the business for the accounting period preceding the most recently ended accounting period; Information showing the growth rate of the business's annual turnover, comparing the business's annual turnover for the most recently completed accounting period with the business's annual turnover for the accounting period of the year prior to the most recently completed accounting period; and information indicating the amount of accounts payable for the most recently completed accounting period divided by annual sales. program.

5. The program according to claim 1, The prediction review information and the learning review information include amount information, The amount information is Information showing the outstanding loan balance of the business from non-banks; Information showing the amount of the business's recent procurement through factoring; Information showing the amount of borrowings of the business for the most recently ended accounting period; and information indicating the business's monthly sales ratio for the most recently completed accounting period; program.

6. The program according to claim 1, The prediction assessment information and the learning assessment information include numerical information, The numerical information is: Information showing the average number of statements by month up to the month prior to the review; Information showing the number of non-banks used by businesses; Information showing the number of factoring companies used by the business; and information indicating the level of risk as a numerical value provided by a business that conducts credit investigations. program.

7. The program according to claim 1, The prediction assessment information and the learning assessment information include time information, The time information is Information indicating how many years the company has been in business at the time of application for the review, Information indicating the number of days between the application date for review and the desired procurement date; Information showing the number of days between the application date and the most recent borrowing date from a non-bank, Information showing the number of days between the application date and the most recent payment date from the factoring company, and and information indicating the number of days from the application date to the date of borrowing from the bank. program.

8. The program according to claim 1, The prediction assessment information and the learning assessment information include judgment information, The determination information is Information indicating whether the business is considered to have arrears on its debts; Information indicating whether the business is considered to have arrears on repayments to non-banks; Information showing whether the employer is considered to have no overdue social insurance payments, and Information indicating whether the business is considered to have late payments of accounts payable; and information indicating whether the business is deemed to have significant director borrowings; program.

9. The program according to claim 1, The prediction assessment information and the learning assessment information include judgment information, The determination information is Information indicating whether the claim is an exempt claim; and Information indicating whether the receivable is considered a receivable that is at the stage of completed service and billing; Information indicating whether the claim is considered to be a grant or subsidy claim with the amount of the grant pending; Information indicating whether the investment from the investment stakeholders can be confirmed at the time of application for review, and information indicating whether the business operator's use of funds can be considered specific at the time of application for the review. program.

10. The program according to claim 1, The prediction assessment information and the learning assessment information include judgment information, The determination information is From information indicating whether the business operator can be considered to have a continuing transaction with the debtor of the receivables to be purchased, information indicating whether the business operator can be considered to have a continuing transaction with the debtor of the receivables to be purchased, Information showing whether unpaid corporation tax for the year before last can be confirmed at the time of closing the previous fiscal year, and Information showing whether unpaid social insurance premiums from the year before last can be confirmed at the time of the previous fiscal year's accounting, and Information indicating whether the examiner believes that significant financial transactions are occurring between related companies; and information indicating whether the examiner judges that the actual status of deposits and withdrawals cannot be grasped because there are many transactions using cash. program.

11. The program according to claim 1, The prediction assessment information and the learning assessment information include judgment information, The determination information is Information indicating whether the business is considered to have changed the factoring business it uses; and Information showing whether the representative of the business has a history of bankruptcy or civil rehabilitation; Information showing the assessment result of a business operator in a predetermined index representing the likelihood of bankruptcy; Information indicating whether the business has a website; Information indicating whether the business operator has had a subrogation of claims in the past; and and information indicating whether a trial balance is deemed to have been submitted by the business operator; program.

12. The program according to claim 1, The learning review information includes one of safe destination information and dangerous destination information as a label, The safe destination information is information including a business entity corresponding to the false positive information described in claim 2 and a business entity that is deemed to have no delay or arrears in the determination information described in claim 8, The risk destination information is information including a business entity corresponding to the positive information as described in claim 2 and a business entity that is deemed to have a delay or arrears in the determination information as described in claim 8. program.

13. The program according to claim 1, The prediction review information and the learning review information include amount information, The amount information is Information showing the financial condition of the business; and information indicating the balance of the business's account; program.

14. The program according to claim 1, The bad debt information includes information on the probability that the receivable will become bad debt. program.

15. The program according to claim 1, The information processing system further executes a determining step, The bad debt information includes information indicating whether the receivable is bad debt, In the determination step, outputting information indicating that the receivable is highly likely to become a default when the probability of the receivable being a default indicated by the bad debt information outputted in the output control step is equal to or greater than a threshold value; outputting information indicating that the probability of the receivable becoming a default is low when the probability of the receivable becoming a default indicated by the bad debt information outputted in the output control step is less than the threshold value; program.

16. An information processing method executed by an information processing system, comprising: The program includes steps according to any one of claims 1 to 15. Information processing methods.

17. An information processing system, A computer-readable storage device comprising: one or more processors that execute the program according to any one of claims 1 to 15; Information processing system.

Images