Credit assessment method

Abstract

The aim is to provide a credit assessment method that improves the accuracy of credit assessment for companies with potential repayment ability by taking into account not only the basic features of company information but also auxiliary features including diversity information. [Solution] The credit determination method of the present invention is characterized by the following steps: the computer obtains at least a plurality of basic features as company information and a plurality of auxiliary features as company diversity information, which are input elements for calculating the default probability, entered by the operator; and the computer calculates the default probability by multiplying each basic feature and each auxiliary feature by a regression coefficient and performing an inverse logit transformation.

Description

Technical Field

[0001] The present invention relates to a credit judgment method for assisting in the credit judgment of customers.

Background Art

[0002] Patent Document 1 discloses an invention related to a credit system aimed at providing a highly accurate credit system. In the credit system of Patent Document 1, it determines whether to start a transaction with a company analyzed by a financial information-based credit analysis device.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Thus, according to Patent Document 1, since it is a credit model using a financial information-based credit analysis device, small-scale and financially weak companies cannot receive sufficient credit transactions.

[0005] However, even among such companies, there are companies with potentially high repayment ability. In a conventional credit model that makes credit judgments only based on basic company information, it was not possible to conduct credit transactions with such companies.

[0006] In view of this point, the present invention has been made, and by taking into account not only the basic feature quantities of company information but also auxiliary feature quantities including diversity information, it aims to provide a credit judgment method that improves the credit accuracy for companies with potentially repayment ability.

Means for Solving the Problems

[0007] One embodiment of the credit assessment method of the present invention is a credit assessment method performed by a computer to support a customer's credit assessment, characterized in that the computer obtains, based on information input by an operator, at least a plurality of basic features as company information and a plurality of auxiliary features as company diversity information, as input elements for calculating the default probability; and the computer calculates the default probability by multiplying each basic feature and each auxiliary feature by a regression coefficient and performing an inverse logit transformation. [Effects of the Invention]

[0008] According to the credit assessment method of the present invention, it is possible to improve the accuracy of credit assessment for companies that have the potential ability to repay, and to make decisions quickly. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a block diagram of the credit decision system (information processing device) in this embodiment. [Figure 2] Figure 2 is a flowchart of the credit assessment method in this embodiment. [Figure 3] Figure 3 is a table showing an example of features and regression coefficients used to calculate the default probability. [Figure 4] Figure 4 is a step-by-step diagram showing the process of acquiring features. [Modes for carrying out the invention]

[0010] The embodiments of the present invention will be described in detail below, but the following description is merely an example (representative example) of the embodiments described herein, and the present invention is not limited to these contents unless it exceeds the gist of the invention.

[0011] <Background leading to the credit assessment method of this embodiment> Current credit scoring models determine creditworthiness based on a company's current financial situation. In other words, they calculate default rates based on past performance. As a result, small and medium-sized enterprises (SMEs) with limited financial resources often receive low credit ratings and are unable to obtain sufficient credit.

[0012] Incidentally, among small and medium-sized enterprises, startups, and venture companies, there are many excellent companies that, despite having limited financial resources at present, are expected to grow in the future. If such companies can receive sufficient credit, their businesses will expand, which in turn will contribute to the development of Japan's industries. However, under the current credit scoring model, potentially high-quality companies were unable to receive sufficient credit, hindering their business expansion.

[0013] Therefore, as a result of diligent research, the inventors have developed a credit assessment method that allows credit transactions to be made with companies that are expected to have a high repayment capacity, either potentially or in the future, by focusing not on current or short-term evaluations, but on whether there are elements that can contribute to the growth and improvement of the competitiveness of the organization.

[0014] In other words, the credit assessment method in this embodiment is characterized by improving credit accuracy for companies with potential repayment ability by taking into account not only basic (qualitative) features of company information but also auxiliary features including diversity information when determining the default probability as a predicted value indicating the possibility of default in the future.

[0015] <Regarding the credit decision system (credit decision device) in this embodiment> Figure 1 is a block diagram of the credit decision system (information processing device) in this embodiment. The credit decision system 1 shown in Figure 1 is composed of an input unit 3, a calculation unit 4, a storage unit 5, and a display unit 6. Although the credit decision system 1 is divided into multiple functional units, this is for the convenience of explanation and does not need to be strictly divided; the multiple functional units may operate as an integrated functional unit.

[0016] The input unit 3 inputs the feature amounts necessary for calculating the default probability. The input values of the feature amounts are, for example, "0: no, 1: yes".

[0017] The calculation unit 4 calculates the default probability based on the feature amounts input from the input unit 3. The default probability represents the probability of falling into the default (default in debt repayment) state in percentage (%).

[0018] The storage unit 5 stores the feature amounts input from the input unit 3 and the regression coefficient a. The regression coefficient can also be referred to as an odds ratio, etc. Further, the regression coefficient can be updated periodically or randomly by re-learning considering economic conditions, etc. The regression coefficient is such that the larger the positive value, the higher the probability of default, and the larger the negative value, the lower the probability of default. The display unit 6 displays on the screen the default probability calculated by the calculation unit 4, the corporate information for credit judgment, etc. In the input unit 3, a plurality of basic feature amounts as company information and a plurality of auxiliary feature amounts as the diversity information of the company are input.

[0019] The company information includes at least any one of at least the governance information readable from the company register transcript, the company scale information readable from the company website, and the growth information readable from the company publicity of the company register transcript or the company website. Note that the company information is not limited to these.

[0020] The governance information includes at least any one of the number of directors, the presence or absence of an owner company, the tenure of directors, the number of director departures, the location, the presence or absence of family management, the presence or absence of auditors and accounting auditors, and the presence or absence of a board of directors. Note that the governance information is not limited to these. Further, the governance information can also be obtained from, for example, the welfare pension insurance and health insurance applicable business establishment search system. The company scale information includes at least any one of the number of regular employees, the number of stores, and the capital amount. Note that the company scale information is not limited to these.

[0021] Growth information includes at least one of the following: the status of issuance of preferred stock / stock options, the frequency of social media activity, the growth rate of the number of employees and / or stores, and the frequency of press releases. However, growth information is not limited to these.

[0022] In addition, information such as whether or not an official gazette announcement has been made, target values ​​that can be gleaned from IR reports, whether or not ESG activities are being conducted, whether or not CSR activities are being conducted, business segments, new business development status, ROE, compliance information (such as whether or not the company is associated with anti-social forces, history of legal violations, and negative reputation), social insurance office information (such as whether or not health checkups are conducted), and the details of receivables (such as infrastructure / rent, entertainment, procurement, loan repayment, equipment / development investment, and outsourcing fees) can be obtained.

[0023] Diversity information includes at least one of the following: the percentage of women on the board of directors, the gender ratio of employees, the percentage of non-Japanese nationals, the age ratio, the employment rate of people with disabilities, the percentage of women in management positions, the use of teleworking, and the existence of parental leave systems. However, diversity information is not limited to these.

[0024] Diversity information can be gleaned from sources such as a company's website, registration documents, and social media. For example, the percentage of female directors can be determined from the names listed on the company's website.

[0025] Here, the information that can be gleaned from a company's website includes not only its own website but also the websites of other companies. For example, job search websites can be cited as examples of other companies' websites.

[0026] As shown in Figure 1, the operator can input information that forms the basis of multiple basic features as company information and multiple auxiliary features as company diversity information from the input unit 7 of the credit assessment system 1. Alternatively, the operator can directly input the basic and auxiliary features. That is, the operator can access the credit assessment system 1 from a terminal device that can communicate with the credit assessment system 1 and input multiple basic features as company information and multiple auxiliary features as company diversity information from the terminal device.

[0027] Furthermore, the credit assessment results from the credit assessment system 1 can be confirmed on the contract terminal device 2. The contract terminal device 2 is envisioned to be a terminal device of a credit institution such as a financial institution or credit company.

[0028] <Regarding the credit assessment method in this embodiment> Next, the credit assessment method in this embodiment will be explained using the flowchart in Figure 2. Figure 3 is a table showing an example of features and regression coefficients for calculating the default probability.

[0029] In step ST1 of Figure 2, several basic features are obtained as company information. For this acquisition, you can input either a numerical value of 0 or 1, for example, as shown in Figure 3, "0: No, 1: Yes". The operator can input basic features, or the computer can acquire features based on the information entered by the operator. In other words, the operator can select the appropriate answer from multiple options displayed on the screen, and the credit scoring system 1 can automatically convert this into features.

[0030] While there is no requirement to limit company information, it is preferable to include at least one of the following: governance information that can be read from the company registration certificate, company size information that can be read from the company's website, or growth potential information that can be read from the company registration certificate or the company's public relations materials on the website.

[0031] For example, as shown in Figure 3, there are input fields such as "Is there an official gazette announcement?", "Has it been established for more than 10 years?", "Does it have multiple businesses?", "Is its capital stock 100 million yen or more?", "Is there a shareholder register administrator?", "Is it a family business?", "Does it issue stock options?", and "Does it have a board of directors?", and you enter "0: No, 1: Yes" for each input field.

[0032] In step ST2 shown in FIG. 2, the credit judgment system 1 determines whether all necessary basic feature quantities have been acquired. If all have been acquired, the process proceeds to step ST3; if not, the process returns to step ST1. However, if there are items that cannot be acquired immediately, the acquisition can be postponed and the process can proceed to step ST3.

[0033] Also, the basic feature quantities necessary for credit judgment can be arbitrarily determined, and can be reduced or increased. The necessary basic feature quantities can determine specific input items, or can be the number of input items. That is, for example, “Is there an official gazette announcement?”, “Is it 10 years or more since establishment?”, “Is the capital 100 million or more?”, “Is there a shareholder register administrator?”, “Is it issuing stock options?”, “Is it installing a board of directors?” described in FIG. 3 can be set as essential input items, and “Are there multiple businesses?”, “Is it family-owned?” can be set as optional input items, and control is performed so that the process cannot proceed to step ST3 if the essential input items have not been input. Or, although there are 8 input items described in FIG. 3, for example, input of 5 or more items can be made essential and controlled numerically.

[0034] Also, for example, when all 8 items shown in FIG. 3 are used as essential basic feature quantities, if there is an item that cannot be input anyway, it may be possible to select “0: No” or, in addition to “0: No, 1: Yes”, select “Unknown”. At this time, “Unknown” is within the range of “0 < a < 1”, and for example, according to the regression coefficient, the input value of the feature quantity of the input item can be given a width.

[0035] In step ST3 of FIG. 3, a plurality of auxiliary feature quantities as the company's diversity information are acquired.

[0036] Although not limiting the diversity information, it preferably includes at least any one of the female ratio of directors, the male-female ratio of employees, the nationality ratio other than Japanese, the age ratio, and the employment ratio of disabled persons, the female ratio of management positions, the presence or absence of utilization of telecommuting, and the presence or absence of a parental leave system.

[0037] For example, as shown in Figure 3, there are input fields such as "Does the percentage of women exceed 25%?", "Is there a teleworking system in place and being utilized?", and "Is there a parental leave system in place and being utilized?", and you enter "0: No, 1: Yes" for each input field.

[0038] Furthermore, as shown in Figure 4, the input screen includes input fields such as "Number of Directors," "Number of Female Directors," "Years Since Establishment," "Family-Owned Business," "Number of Employees," and "Number of Female Employees," and the operator enters specific numerical values ​​into each input field.

[0039] On the computer side, as a backend process, the calculation unit 4 shown in Figure 1 calculates whether the percentage of female directors exceeds 25% based on the input "number of directors" and "number of female directors". If it is 25% or more, it obtains the feature "1: Yes", and if it is 25% or less, it obtains the feature "0: No".

[0040] Furthermore, on the computer side, as part of the backend processing, the calculation unit 4 shown in Figure 1 acquires a "1: Yes" feature if it has been more than 10 years since its establishment, and a "0: No" feature if it has been less than 10 years since its establishment, based on the input "Years since establishment".

[0041] Furthermore, on the computer side, as a backend process, the calculation unit 4 shown in Figure 1 calculates whether "the percentage of female employees exceeds 25%" based on the input "number of employees" and "number of female employees". If it is 25% or more, it obtains the feature "1: Yes", and if it is 25% or less, it obtains the feature "0: No".

[0042] Incidentally, in the case of startups and venture companies, there are many items that do not correspond to the basic feature input fields or are unknown, making it difficult to make accurate credit assessments. For example, features such as "Has it been established for more than 10 years?" and "Is its capital of 100 million yen or more?" as shown in Figure 3 are unlikely to apply, and the input value for these features would be "0: No".

[0043] Startups and venture companies often lack sufficient financial track records. Therefore, traditional credit assessment methods make it difficult to evaluate their future potential. It is impossible to determine business continuity or the feasibility of business plans based on financial statements whose reliability is uncertain.

[0044] Therefore, auxiliary features representing diversity information are set as input items, and the focus is on whether there are elements that can contribute to organizational growth and improved competitiveness, thereby evaluating the potential for long-term overall organizational value improvement. Furthermore, in this embodiment, the default probability is calculated by taking into account not only quantitative information but also qualitative information.

[0045] In step ST4 of Figure 2, the credit assessment system 1 determines whether all the necessary diversity information has been entered. If all the necessary diversity information has been obtained, it proceeds to step ST5; if there is any missing diversity information, it returns to step ST3.

[0046] The auxiliary features necessary for credit assessment can be arbitrarily determined and can be reduced or increased. The necessary auxiliary features can be defined as specific input items, or they can be defined as the number of input items. For example, among the following, the percentage of female directors, the male-female ratio of employees, the percentage of non-Japanese nationals, the age ratio, the employment rate of people with disabilities, the percentage of female managers, the use of teleworking, and the existence of a parental leave system, the percentage of female directors, the male-female ratio of employees, the age ratio, the percentage of female managers, the use of teleworking, and the existence of a parental leave system can be designated as essential diversity information, while the percentage of non-Japanese nationals and the employment rate of people with disabilities can be designated as selective diversity information.

[0047] It can sometimes be difficult to obtain diversity information from a company's website or registration documents. In such cases, information can be obtained from other companies' websites, such as job search sites, or from social media.

[0048] Also, if there are items that cannot be input into the essential diversity information, you may select "0: No" or, in addition to "0: No, 1: Yes", you may also be able to select "Unknown". At this time, "Unknown" is within the range of "0 < a < 1". For example, according to the regression coefficient, the input value of the feature quantity of the input item can have a width.

[0049] Since the importance of diversity information changes depending on the era, industry type, etc., it is desirable to periodically review (re-learn) input items and regression coefficients, etc., to improve the credit judgment accuracy by the credit judgment system 1.

[0050] And in step ST5 shown in FIG. 2, the default probability is calculated. The regression coefficient a required to calculate the default probability is stored in advance in the storage unit of FIG. 1. The regression coefficient is a predetermined numerical value and indicates the accuracy of the default prediction value. It is calculated by machine learning based on a large number of corporate data. In the arithmetic unit 4, using the input feature quantity and the regression coefficient associated with each feature quantity, the default probability is calculated based on the following (Equation 1).

[0051] inv_logit(a1x1+a2x2+···a n x n +b) (Equation 1) (Here, a1, a2…a n (n is an integer of 1 or more) indicates the regression coefficient, x1, x2…x n (n is an integer of 1 or more) indicates the feature quantity, and b indicates the intercept).

[0052] (Equation 1) is expressed as the probability obtained by taking the inverse logit of the feature quantity (input value) × regression coefficient + intercept. Note that the intercept b is used subsidiarily to improve the accuracy of the default prediction value and is set individually according to each credit diagnosis model.

[0053] In conventional credit assessments that focus primarily on financials, the market average default probability is 0.9-1.1%, whereas in credit assessments using the method of this embodiment, which incorporates diversity information and qualitative information, the default probability is 0.09%, which is about one-tenth of that of conventional credit assessments.

[0054] As a result, even companies that previously failed credit checks can now pass the credit check using this embodiment and receive speedy credit transactions. [Explanation of symbols]

[0055] 1: Credit assessment system 2: Contract terminal device 3: Input section 4: Arithmetic section 5: Storage section 6:Display section 7: Input section

Claims

1. A credit assessment method performed by a computer to support customer credit decisions, The computer, based on the information entered by the operator, takes the step of obtaining at least several basic features as company information and several auxiliary features as company diversity information, which serve as input elements for calculating the default probability. The computer calculates the default probability by multiplying each basic feature and each auxiliary feature by a regression coefficient and performing an inverse logit transform. A credit assessment method characterized by having the following features.

2. The credit assessment method according to claim 1, wherein the diversity information includes at least one of the following: the percentage of female directors, the male-female ratio of employees, the percentage of non-Japanese nationals, the age ratio, the employment rate of persons with disabilities, the percentage of female managers, whether or not teleworking is utilized, and whether or not a parental leave system is in place.

3. The credit assessment method according to claim 1, wherein the aforementioned company information includes at least one of the following: governance information that can be read from the company register, company size information that can be read from the company's website, and growth potential information that can be read from the company register or the company's public relations materials on the website.

4. The credit assessment method according to claim 3, wherein the governance information includes at least one of the following: the number of directors, whether or not it is an owner-managed company, the length of time directors have served, the number of directors who have left office, the location, whether or not it is a family-owned business, whether or not there are auditors / outsourced auditors, and whether or not there is a board of directors.

5. The credit assessment method according to claim 3, wherein the company size information includes at least one of the number of full-time employees, the number of stores, and the capital.

6. The credit assessment method according to claim 3, wherein the growth information includes at least one of the following: the status of issuance of preferred stocks / stock options, the frequency of SNS postings, the growth rate of the number of employees and / or the number of stores, and the frequency of press releases.

7. The default probability is given by the credit determination method according to claim 1, as shown in formula 1 below. (Math 1) inv_logit(a 1 x 1 +a 2 x 2 + ··· a n x n +b) (Equation 1) (Here, a 1 , a 2 … a n (n is an integer greater than or equal to 1) represents a regression coefficient, x 1 , x 2 … x n (n is an integer greater than or equal to 1) represents a feature amount, and b represents an intercept).

Images