KR20200111518A - System for Debt Repayment Capability Evaluation Of Corporation Including Evaluation Model Based On AI Using Commerce Data - Google Patents

Abstract

The present invention relates to a corporate debt repayment capability evaluation system including an AI-based evaluation model using commerce data. With the present invention, debt repayment capability evaluation can be performed using non-financial data including financial information and public procurement information as well as financial data acquired based on financial statements of a target enterprise. The system includes: a data acquisition unit acquiring commerce data acquired based on financial data acquired based on financial statements of a target enterprise, non-financial data other than the financial data, and bond information of the target enterprise; a calculation unit dividing a main prediction period from an evaluation time point to a prediction time point following the evaluation time point into sub prediction periods and calculating a debt repayment capability evaluation result of the target enterprise by inputting the financial data, the non-financial data, and the commerce data to debt repayment capability evaluation models generated by sub prediction period; and a final calculation unit calculating a final debt repayment capability evaluation result of the target enterprise by using the debt repayment capability evaluation result of the target enterprise.

Description

System for Debt Repayment Capability Evaluation Of Corporation Including Evaluation Model Based On AI Using Commerce Data}

The present invention relates to credit ratings, and more specifically, to credit ratings of companies.

In business-to-business transactions, evaluation of the debt repayment ability of the relevant company is required in advance in order to prevent damages due to arrears or default of debts of the customer company or the investment partner company (hereinafter referred to as'company').

Therefore, a credit rating system has been proposed to objectively evaluate a company's debt repayment ability by objectively quantifying the possibility of a company's default or the size of its creditworthiness.

A general credit rating system evaluates a company's debt repayment ability by using financial data generated based on financial statements. However, the credit rating system can evaluate only the financial data up to before the financial statements are prepared, and the financial data generated after the financial statements are prepared cannot be reflected in the evaluation. There is a problem that it cannot be accurately evaluated.

In addition, since the credit rating system evaluates the debt repayment ability at the time of evaluation, there is a problem in that it cannot be known even if there is a possibility that a problem may occur in the debt repayment ability at some point after the evaluation point.

The present invention is to solve the above-described problems, and commercial data capable of evaluating debt repayment ability using non-financial data including financial information and public procurement information as well as financial data obtained based on the financial statements of a target company. Its technical task is to provide a company's debt repayment ability evaluation system including an AI-based evaluation model using.

In addition, the present invention provides a company's debt repayment capability evaluation system including an AI-based evaluation model using commercial data capable of evaluating the debt repayment capability using the commercial data of the target company obtained based on the company's bond information. This is the technical task.

In addition, the present invention uses a plurality of debt repayment capability evaluation models that evaluate the debt repayment capability for each predetermined forecast period, and uses a commercial transaction capable of calculating the possibility of at least one of arrears, insolvent, and default of a target company for each forecast period. Its technical task is to provide a system for evaluating a company's debt repayment ability including an AI-based evaluation model using data.

In addition, in the present invention, each debt repayment capability evaluation model learns the financial data and non-financial data of the insolvent companies generated in the expected insolvent period corresponding to each forecast period among the financial data and non-financial data of the insolvent company in which bankruptcy or delinquency occurred. Its technical task is to provide a company's debt repayment ability evaluation system including an AI-based evaluation model using commercial data.

In addition, the present invention is a company that includes an AI-based evaluation model using commercial data capable of evaluating the debt repayment ability of a target company by using a plurality of debt repayment ability evaluation models in which commercial data including corporate bond information is learned. Its technical task is to provide a system for evaluating the debt repayment capability of the company.

In addition, the present invention generates derived data correlated with debt repayment ability from financial and non-financial data of insolvent companies, and AI-based evaluation using commercial data that can additionally learn derived data in each debt repayment ability evaluation model. Its technical task is to provide a system for evaluating the debt repayment ability of a company including a model.

The debt repayment capability evaluation system of a company including an AI-based evaluation model using commercial data according to an aspect of the present invention for achieving the above object is financial data obtained based on the financial statements of the target company, the financial data. A data acquisition unit for acquiring commercial data acquired based on non-financial data and bond information of a target company; The main forecasting period from the evaluation point to the forecasting point after the evaluation point is divided into a plurality of sub-prediction periods, and the financial data, the non-financial data, and the commercial transaction are applied to a plurality of debt repayment ability evaluation models generated for each sub-prediction period. A calculation unit for inputting data and calculating a result of evaluating the debt repayment capability of the target company; And a final calculation unit that calculates a final debt repayment ability evaluation result of the target company by using the debt repayment ability evaluation result of the target company.

A company's debt repayment ability evaluation system including an AI-based evaluation model using commercial data according to another aspect of the present invention to achieve the above object is data for acquiring commercial transaction data obtained based on the bond information of the target company. Acquisition unit; The main forecasting period from the evaluation point to the forecasting point after the evaluation point is divided into a plurality of sub-prediction periods, and the transaction data is input to a plurality of debt repayment capacity evaluation models generated for each sub-prediction period, and the respective debt repayment capabilities A calculation unit that calculates a result of evaluating the debt repayment ability of the target company for each evaluation model; And a final calculation unit that calculates a final debt repayment ability evaluation result of the target company by using at least one evaluation result among the debt repayment ability evaluation results calculated for each debt repayment ability evaluation model.

According to the present invention, it is possible to evaluate the debt repayment ability using non-financial data as well as the financial data of the target company, so even if changes occur in the target company after the financial statements are prepared, this can be reflected, so that the debt repayment ability can be accurately calculated. There is an effect.

In addition, according to the present invention, it is possible to evaluate the debt repayment ability by using the commercial transaction data of the target company obtained based on the corporate bond information, so that the delinquency of the transaction corresponds to a preliminary sign of bankruptcy or insolvency. By using commercial data containing information, there is an effect that it is possible to first check whether the target company is bankrupt or insolvent.

According to the present invention, the probability of occurrence of at least one of delinquency, insolvent, and default of a target company can be calculated for each forecast period by using a plurality of debt repayment capability evaluation models that evaluate debt repayment capability for each predetermined forecast period. However, there is an effect that it is possible to evaluate not only the debt repayment ability of the target company at the time of evaluation, but also the debt repayment ability of the target company at the time after the time of evaluation.

In addition, according to the present invention, since the probability of occurrence of at least one of delinquency, insolvent, and default of the target company can be calculated for each prediction period, the first prediction period of any one of a plurality of prediction periods in which the entire prediction period is divided If the debt repayment ability is abnormal but the debt repayment ability is normal in other forecast periods, it is possible to prevent the determination of the debt repayment ability in the first forecast period to be normal by evaluating the debt repayment capacity for each forecast period rather than the entire forecast period. It works.

According to the present invention, since the probability of occurrence of at least one of delinquency, insolvent, and default of the target company can be calculated for each predetermined forecast period, the target company can seek a response to the target company before the delinquency or default occurs. It has the effect of minimizing economic losses by getting opportunities.

In addition, according to the present invention, each debt repayment capability evaluation model is learned from the financial data and non-financial data of the insolvent companies generated during the expected period of insolvency corresponding to each forecast period among the financial data and non-financial data of insolvent companies in which bankruptcy or delinquency occurred. Therefore, each debt repayment capability evaluation model learns the financial and non-financial data of insolvent companies generated in different insolvency periods, so that it is possible to accurately evaluate the debt repayment capability for each forecast period.

In addition, according to the present invention, since it is possible to evaluate the debt repayment ability of a target company by using a plurality of debt repayment ability evaluation models in which commercial data including corporate bond information is learned, the results of the debt repayment ability evaluation model and debt repayment There is an effect that the accuracy of the debt repayment ability can be improved by comparing the results of the capability evaluation model.

In addition, according to the present invention, since derived data is generated from financial data and non-financial data of insolvent companies to learn each debt repayment capability evaluation model, there is an effect that the degree of matching of each debt repayment capability evaluation model is improved.

1 is a diagram schematically showing the configuration of a debt repayment capability evaluation system of a company including an AI-based evaluation model using commercial transaction data according to an embodiment of the present invention.
2 is a diagram showing the configuration of a debt repayment ability evaluation system 100 according to an embodiment of the present invention
3A is a diagram illustrating that a first calculator according to an embodiment of the present invention uses a probability distribution to calculate a grade for an insolvency probability.
3B is a diagram showing a composition ratio for each grade according to an embodiment of the present invention.
4 is a diagram showing a configuration of a second calculation unit according to an embodiment of the present invention.
5A is a diagram illustrating an example of a table generated by a table generation unit.
5B is a diagram showing an example of a debt repayment capability level.
6 is a diagram illustrating that a modeling unit according to an embodiment of the present invention generates a plurality of first debt repayment capability evaluation models and a plurality of second debt repayment capability evaluation models.
7 is a diagram showing an example of a modeling unit verifying a debt repayment capability evaluation model.
8A is a diagram illustrating that four first models according to an embodiment of the present invention calculate an insolvency probability for each prediction period.
8B is a diagram illustrating that a first model according to an embodiment of the present invention calculates an insolvency probability for each prediction period.

The meaning of the terms described in this specification should be understood as follows.

Singular expressions should be understood as including plural expressions unless clearly defined differently in context, and terms such as “first” and “second” are used to distinguish one element from other elements, The scope of rights should not be limited by these terms.

It is to be understood that terms such as "comprise" or "have" do not preclude the presence or addition of one or more other features or numbers, steps, actions, components, parts, or combinations thereof.

The term “at least one” is to be understood as including all possible combinations from one or more related items. For example, the meaning of “at least one of the first item, the second item, and the third item” means 2 among the first item, the second item, and the third item, as well as the first item, the second item, and the third item. It means a combination of all items that can be presented from more than one.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically showing the configuration of a debt repayment ability evaluation system (hereinafter referred to as'debt repayment ability evaluation system') including an AI-based evaluation model using commercial transaction data according to an embodiment of the present invention. .

The user terminal 10 receives identification information on a company (hereinafter referred to as a “target company”) to be evaluated for debt repayment capability from the user and transmits it to the debt repayment capability evaluation system 100. In this case, the identification information may include a business operator number, a business name, and the like.

The user terminal 10 may include a mobile terminal, a tablet PC, and a computer.

The debt repayment capability evaluation system 100 evaluates the debt repayment capability of the target company according to the request of the user terminal 10. Specifically, the debt repayment ability evaluation system 100 is based on financial data obtained based on the financial statements of the target company, non-financial data including financial information, public procurement information, etc. The obtained commercial transaction data may be analyzed for each predetermined forecast period using a plurality of first debt repayment capability evaluation models and a plurality of second debt repayment capability evaluation models to evaluate the debt repayment capability of the target company.

Hereinafter, the debt repayment capability evaluation system 100 will be described in more detail with reference to FIG. 2.

2 is a diagram showing the configuration of a debt repayment ability evaluation system 100 according to an embodiment of the present invention. As shown in Fig. 2, the debt repayment ability evaluation system 100 includes a data acquisition unit 210, a derivative data generation unit 220, a calculation unit 225, a final calculation unit 243, a database 245, and It includes a modeling unit 250, and a debt repayment capability evaluation model 255.

The data acquisition unit 210 is obtained based on financial data obtained based on the financial statements of the target company and non-financial data including financial information, public procurement information, etc. in addition to the financial data of the target company and the target company's bond information. Acquire commerce data. In one embodiment, when the identification information of the target company is received from the user terminal 10, the data acquisition unit 210 transmits the received identification information of the target company to the external server 20 from the external server 20. It is possible to obtain financial data, non-financial data, and commerce data of the target company.

In one embodiment, the financial data acquired by the data acquisition unit 210 may include at least one of financial statement information, financial ratio information, financial model information, and borrowing information. At this time, the financial statement information includes at least one of financial position information, income statement information, and cash flow information, and the financial ratio information includes general financial ratio information. The financial model information includes at least one of financial model input variable information and financial issue information, and the borrowing information includes information on calculating borrowing capacity.

The non-financial data acquired by the data acquisition unit 210 may include financial information, public procurement information, human resource information, and penalty information. In this case, the company information may include a company overview, and the financial information may include credit information. Public procurement information may include at least one of bidding information and contract information. Human resource information may include at least one of national pension information and job posting information. The penalty information may include at least one of information on disposition of fraudulent disposition and disposition of construction license.

The commercial transaction data acquired by the data acquisition unit 210 may include at least one of information on accounts receivable of a target company and information on collection records of a target company.

The derivative data generation unit 220 generates derived data that is correlated with the debt repayment capability from the financial data and non-financial data of the target company obtained by the data acquisition unit 210.

In one embodiment, the derivative data is the ratio of the latest month's debt to sales, the amount of the guarantee of the corporate debt to the equity capital, the amount of the guarantee of the corporate debt to the real capital, the ratio of the 3-month credit contribution to the operating profit, the ratio of the end of the previous month to the equity capital, and monthly Borrowing capacity analysis, monthly debt dependence, average number of credit loans in the last 3 months, average deposit amount in the last 3 months, rate of exhaustion of 1 financial sector loan limit for the last 3 months, monthly interest expense, proportion of policy funds, bill discount proportion, checking loan availability, Overdraft transaction amount, payment guarantee ratio, share of collateral, current month's entry rate, current month's resignation rate, current month's employee number increase and decrease rate, previous month's notice amount increase or decrease rate, average notified amount, 3 month resignation rate, 6 month resignation rate, 3 month employment rate , 6-month entry rate, 3-month employee increase/decrease rate, 6-month employee increase/decrease rate, 3 months 1 person average notification amount increase/decrease rate, 6 months 1 person average notification amount increase/decrease rate.

The derivative data generation unit 220 may generate derivative data that is correlated with the debt repayment ability from the commercial transaction data. In one embodiment, the derived data generated from the commercial transaction data is the number of times of collection of bonds, number of times of collection of bonds after the period of fulfillment of bonds, rate of collection of bonds, rate of collection of bonds after the period of fulfillment of bonds, bond delinquency period, whether or not bonds are overdue, It may include at least one of the receivable collection type, the number of divisions, and the required period.

The derivative data generation unit 220 generates derived data from financial data, non-financial data, and commercial transaction data of the target company and transmits the generated data to the calculation unit 225.

The calculation unit 225 divides the main prediction period from the evaluation time to a predetermined prediction time after the evaluation time into a plurality of sub-prediction periods, and the plurality of debt repayment ability evaluation models 255 generated for each sub-prediction period. By inputting financial and non-financial data, the result of evaluating the debt repayment ability of the target company is calculated. In addition, the calculation unit 225 may input financial data, non-financial data, and commercial data into a plurality of debt repayment capability evaluation models 255 generated for each sub-prediction period to calculate the debt repayment capability evaluation result of the target company. have.

To this end, the calculation unit 225 may include a first calculation unit 230 and a second calculation unit 240. Hereinafter, for convenience of explanation, the first calculation unit 230 includes a plurality of first debt repayment ability evaluation models 260 and a plurality of second debt repayment ability evaluation models included in the plurality of debt repayment ability evaluation models 255. It is explained that the target company's debt repayment ability is evaluated through (280). In addition, a common function of the first debt repayment ability evaluation model 260 and the second debt repayment ability evaluation model 280 will be described as a debt repayment ability evaluation model 255.

The first calculation unit 230 calculates the first debt repayment capability evaluation result and the second debt repayment capability evaluation result of the target company. Specifically, the first calculation unit 230 divides the main prediction period from the evaluation time to a predetermined prediction time after the evaluation time into a plurality of sub prediction periods. The first calculation unit 230 inputs the financial data and non-financial data of the target company into the plurality of first debt repayment capability evaluation models 260 generated for each sub-prediction period, and the target company for each first debt repayment capability evaluation model. The first debt repayment ability evaluation result of In addition, the first calculation unit 230 inputs the financial data, non-financial data, and commercial data of the target company into the plurality of second debt repayment capability evaluation models 280 generated for each sub-prediction period to repay each second debt. For each capability evaluation model 280, the second debt repayment capability evaluation result of the target company is calculated. In this case, the time point of evaluation means the time point at which the debt repayment ability is evaluated.

In the above-described embodiment, it has been described that the first calculation unit 230 uses only financial data, non-financial data, and commercial transaction data, but the first calculation unit 230 uses the derivative data generation unit 220 to provide financial data, Non-financial data and derivative data generated from commercial transaction data may be additionally used to calculate the result of evaluating the debt repayment capability of the target company.

In one embodiment, the first calculation unit 230 includes financial data of the target company in a plurality of first debt repayment ability evaluation models 260 that evaluate the debt repayment ability for each sub-prediction period in which a predetermined main prediction period is divided. And non-financial data are input to calculate a first target rating indicating the probability of occurrence of insolvency events of the target company for each sub-prediction period. In addition, the first calculation unit 230 includes financial data, non-financial data of the target company, and a plurality of second debt repayment capability evaluation models 280 that evaluate the debt repayment capability for each sub-prediction period in which a predetermined main prediction period is divided. And, by inputting the commercial transaction data, a second target grade indicating the probability of occurrence of insolvency events of the target company for each sub-prediction period is calculated.

In one embodiment, the insolvency event may include at least one of short-term delinquency, public delinquency, financial delinquency, card delinquency, commerce delinquency, closed business, and unreceivable of accounts receivable.

In one embodiment, the first calculation unit 230 inputs the financial data and non-financial data of the target company into the plurality of first debt repayment capability evaluation models 260, and the first insolvency probability of the target company for each sub-prediction period. Is calculated, and the first insolvency probability calculated for each sub-prediction period is calculated as a first target grade according to a predetermined criterion. In addition, the first calculation unit 230 inputs the financial data, non-financial data, and commercial data of the target company into the plurality of second debt repayment capability evaluation models 280, and the second insolvency probability of the target company for each sub-prediction period. Is calculated, and the second insolvency probability calculated for each sub-prediction period is calculated as a second target grade according to a predetermined criterion.

In an embodiment, the first calculation unit 230 may calculate the insolvency probability calculated for each sub-prediction period as a target grade according to a section located on the reference insolvency probability distribution. At this time, the reference insolvency probability distribution means a probability distribution of a plurality of test insolvency probabilities calculated by inputting a plurality of test data to each of the first debt repayment ability evaluation model 260 and each second debt repayment ability evaluation model 280 do. On the reference insolvency probability distribution, sections of each grade may be set according to the composition ratio of each grade.

For example, as shown in FIGS. 3A and 3B, a grade may be set for each section according to a composition ratio for each grade on the reference insolvency probability distribution. Accordingly, the first calculator 230 may calculate a target grade according to a section in which the insolvency probability calculated for each sub-prediction period is located on the reference insolvency probability distribution.

In FIG. 3B, it is shown that there are seven grades, but this is only an example, and there may be six or less grades and eight or more grades may exist.

The reason why the first calculation unit 230 according to the present invention calculates the insolvency probability calculated by each debt repayment capability evaluation model 255 as a grade, is that each debt repayment capability evaluation model 255 is Since it was created by learning the generated financial data, non-financial data, commercial data, and derivative data of the generated insolvent company, it was not possible to determine the superiority between each insolvency probability, so the insolvency probability calculated in each debt repayment ability evaluation model (255) was used as the target grade. This is to calculate as one result value by converting and determining the superiority between target grades.

In one embodiment, the first calculation unit 230 may determine the enterprise type of the target company according to the classification criteria, and select a plurality of first debt repayment ability evaluation models 260 according to the determined enterprise type of the target company. have. At this time, the classification criteria may include the type of business, the size of the company, whether or not a company has external audit. According to this embodiment, by inputting the financial data, non-financial data, and derivative data of the target company into the plurality of first debt repayment ability evaluation models 260 selected according to the type of the target company in the first calculation unit 230 The target grade for each sub-prediction period can be calculated.

For example, when it is determined that the target company is an externally audited company, the first calculation unit 230 may add financial data, non-financial data, and derivative data of the target company to the plurality of first debt repayment ability evaluation models 260 for the externally audited company. By inputting, you can calculate the target grade for each prediction period.

In addition, the first calculation unit 230 may determine the enterprise type of the target company according to the classification criteria, and may select a plurality of second debt repayment capability evaluation models 280 according to the determined enterprise type of the target company. At this time, the classification criteria may include the type of business, the size of the company, whether or not a company has external audit. In the case of this embodiment, the first calculation unit 230 includes financial data, non-financial data, commercial data, and derivative data of the target company in a plurality of second debt repayment capability evaluation models 280 selected according to the company type of the target company. By inputting, the target grade for each sub-prediction period can be calculated.

For example, when it is determined that the target company is an externally audited company, the first calculation unit 230 may add financial data, non-financial data, and derivative data of the target company to the plurality of second debt repayment ability evaluation models 280 for the externally audited company. By inputting, you can calculate the target grade for each prediction period.

The second calculation unit 240 uses at least one first result value among the first debt repayment capability evaluation results calculated by the first debt repayment capability evaluation model 260 by the first calculation unit 230 to the target company's debt. It is calculated from the evaluation result of repayment ability. In addition, the second calculation unit 240 determines at least one second result value of the second debt repayment capability evaluation results calculated for each second debt repayment capability evaluation model 280 by the first calculation unit 230 It is calculated as the result of evaluating the debt repayment ability of the target company of

In one embodiment, the second calculation unit 240 is the median value of the first debt repayment ability evaluation results, the lowest evaluation result among the first debt repayment ability evaluation results, and the highest among the first debt repayment ability evaluation results. The first result selected from among the high evaluation results can be calculated as the result of evaluating the debt repayment ability of the target company. In addition, the second calculation unit 240 is the median value of the second debt repayment ability evaluation results, the lowest evaluation result among the second debt repayment ability evaluation results, and the highest evaluation result among the second debt repayment ability evaluation results. The selected second result can be calculated as the result of evaluating the debt repayment ability of the target company.

In one embodiment, the second calculation unit 240 calculates a target debt repayment capability level of the target company using a plurality of target grades calculated by the first calculation unit 230. Specifically, the second calculation unit 230 may calculate the target debt repayment capability level of the target company by using the final grade, which is one of a plurality of target grades calculated for each sub-prediction period.

In one embodiment, the second calculation unit 240 includes the first debt repayment ability evaluation model 260 according to a distance on the time axis from the evaluation point to a reference point included in each sub-prediction period of the plurality of debt repayment ability evaluation models. ) Using a table in which the priorities of a plurality of grades are recorded, the target debt repayment capability level of the target company can be calculated.

In addition, the second calculation unit 240 is a second debt repayment capability evaluation model (the second debt repayment capability evaluation model) according to the distance on the time axis from the evaluation point to the reference time included in each sub-prediction period of the plurality of second debt repayment capability evaluation models 280 280) A target debt repayment capability level of a target company can be calculated using a table in which the priorities of a plurality of stars are recorded. In this case, the time point of evaluation means the time point at which the debt repayment ability is evaluated. The reference point may include the start point or end point of each prediction period.

To this end, the second calculation unit 240 is a table generation unit 410, a table storage 420, a rating selection unit 430, a level determination unit 440 and a score calculation unit 450 as shown in FIG. ) Can be included.

The table generation unit 410 generates a table in which the priorities of a plurality of grades for each debt repayment ability evaluation model 255 are recorded.

For example, when there are n debt repayment ability evaluation models 255 and m grades, the table generator 410 may generate a table having n*m fields. In this case, the priority of the grade for each debt repayment capability evaluation model may be recorded in each field. Also, the table generator 410 may generate a table having n*m fields when there are n second debt repayment capability evaluation models 280 and m grades. In this case, the priority of the rating for each second debt repayment capability evaluation model may be recorded in each field.

For example, as illustrated in FIG. 5A, when four first to fourth models exist and seven grades exist, the table generator 410 may generate a table having 28 fields.

In one embodiment, the table generation unit 410 is in the field of each table according to the distance on the time axis from the evaluation point to the reference point of the prediction period of each debt repayment ability evaluation model 255 ( 255) Priority of a plurality of grades according to priority of a plurality of grades may be recorded.

In one embodiment, the table generator 410 has a higher priority as the distance on the time axis from the evaluation point to the reference point of each prediction period is shorter for the same grades of the different debt repayment ability evaluation models 255 on the table. It can be recorded, and different grades of the same debt repayment ability evaluation model 255 can be recorded with higher priority as the grade is higher. In this case, the higher the grade, the poorer the debt repayment ability may mean. In contrast to the above-described embodiment, on the contrary, when a lower grade means that the debt repayment ability is poor, the table generator 410 prioritizes different grades of the same debt repayment ability evaluation model 255 as the lower grade. Can be recorded high.

For example, as shown in FIG. 5A, when the distance on the time axis from the evaluation point to the reference point of the prediction period is sequentially increased in the first to fourth models, the table generator 410 has priority among the same grades. It can be recorded sequentially lower in the 1st model to the 4th model. In addition, when the higher the grade means that the debt repayment ability is poor, the table generation unit 410 may record the higher priority as the grade increases between different grades. In FIG. 5A, the smaller the priority value is, the higher the priority is. However, this is only an example, and the higher the priority value, the higher the priority.

In an embodiment, the table generator 410 may set a debt repayment capability level for each group by grouping a plurality of grades for each debt repayment capability evaluation model on the table into at least one group.

As an example, the table generation unit 410 groups some of the plurality of ratings of the debt repayment ability evaluation model 255 on the table among the same grades of different debt repayment ability evaluation models 255, and the other grades are the same. It is possible to group between different successive grades of the debt repayment ability evaluation model 260. Accordingly, the table generator 410 may set the debt repayment capability level for the grouped groups.

For example, as illustrated in FIG. 5A, the table generator 410 may group the first to fourth models into a first group and set the first group to the first level. The table generator 410 may group the first to fourth models of the second grade into a second group and set the second group to a second level. The table generator 410 may group the 3rd grades of the first to fourth models into a third group and set the third group to a 3rd level. The table generator 410 may group the first to fourth models into a fourth group between the fourth grades and set the fourth group to a fourth level. The table generator 410 may group the seventh grades of the first to fourth models into a seventh group and set the seventh group to a seventh level.

In addition, the table generator 410 may group the 5th to 6th grades of the first model into the 6B group and set the 6B group to the 6B level. The table generator 410 may group the 5th to 6th grades of the second model into the 6A group and set the 6A group to the 6A level. The table generator 410 may group the 5th to 6th grades of the third model into the 5B group and set the 5B group to the 5B level. The table generator 410 may group the 5th to 6th grades of the fourth model into the 5A group and set the 5A group to the 5A level.

As shown in FIG. 5B, the level set by the table generator 410 may mean that the debt repayment ability of the target company is lowered in ascending order. Levels 1 and 2 can mean that the target company's debt repayment ability is normal, levels 3 and 4 mean that the target company's debt repayment ability needs to be observed, and levels 5 to 7 have problems with the debt repayment ability. It can mean there is.

At this time, the 5A level can mean that the target company has a high probability of occurrence of insolvent events within 9 to 12 months from the time of evaluation, and the 5B level indicates that the target company has a high probability of occurrence of insolvency events within 6 to 9 months from the time of evaluation. Can mean that. In addition, level 6A may mean that the target company has a high probability of occurrence of insolvent events within 3 to 6 months from the time of evaluation, and level 6B means that the target company has a high probability of occurrence of insolvency events within 3 months from the time of evaluation. I can. Level 7 can mean that the target company has already had a bad event.

The table generation unit 410 stores the generated table in the table storage 420.

In the above-described embodiment, it has been described that the table generation unit 410 is included in the second calculation unit 240, but the table generation unit 410 may be included in the debt repayment ability evaluation system 100 in a separate configuration.

The table storage 420 stores tables created by the table generation unit. The table storage 420 may be implemented in the form of a database.

The grade selection unit 430 may select a final grade with the highest priority matching each target grade among a plurality of target grades using a table stored in the table storage 420.

For example, as shown in FIG. 5A, the first calculation unit 230 uses 4 grades (priority: 13) of the first model, 3 grades (priority: 18) of the second model, and 5 When the grade (priority: 10) and the sixth grade (priority: 11) of the fourth model are calculated, the grade selection unit 430 selects the fifth grade (priority: 10) of the third model with the highest priority. It can be selected as the final grade.

The level determination unit 440 determines the final grade selected by the grade selection unit 430 as the target debt repayment capability level of the target company.

In one embodiment, the level determination unit 440 may determine the debt repayment capability level set in the group including the final grade as the target debt repayment capability level of the target company.

For example, as shown in FIG. 5A, when the 5th grade is selected as the final grade by the grade selection unit 430, the level determination unit 440 targets the 5B level set in the group including the field where the fifth grade is located. It can be determined by the company's target debt repayment capability level.

The level determination unit 440 transmits the determined debt repayment capability level to the user terminal 10.

The score calculation unit 450 may convert the target debt repayment capability level into a debt repayment capability score. In one embodiment, the score calculation unit 450 inputs the priority recorded in the field where the final grade selected by the grade selection unit 430 is located in a predetermined equation to determine the target debt repayment capability level of the target company. It can be converted into debt repayment ability points. As an example, the predetermined equation may be Equation 1 below.

In Equation 1, Y denotes a debt repayment ability score, and X denotes priority.

For example, as shown in FIG. 5A, when the 5th grade is selected by the grade selection unit 430, the score calculation unit 450 inputs 10, which is the priority recorded in the field where the 5th grade is located, into Equation 1 Thus, the debt repayment ability score can be calculated. Accordingly, the first calculation unit 450 may calculate a debt repayment ability score of 37 points.

The reason why the score calculation unit 450 according to the present invention calculates the debt repayment capability score is to provide the user with an accurate debt repayment capability by further subdividing the debt repayment capability level of the target company.

The score calculation unit 450 transmits the calculated debt repayment capability score to the user terminal 10.

Meanwhile, in the above-described embodiment, the second calculation unit 240 calculates a plurality of target grades as the target debt repayment ability level using a table in which the priorities are recorded, but in a modified embodiment, the second calculation unit 240 A plurality of target grades may be calculated as target debt repayment capability levels using weights for each grade.

Referring back to FIG. 2, when the second calculation unit 240 receives information on occurrence of a non-donation event from the data acquisition unit 210, the second calculation unit 240 may calculate the level of the debt repayment ability of the target company as a level representing the actual occurrence of the bad event. have. For example, as shown in FIG. 5B, the second calculation unit 240 may calculate a 7 level when a non-donation event occurs in the target company.

The final calculation unit 243 calculates the final debt repayment capability evaluation result of the target company by using the target company’s debt repayment capability evaluation result calculated by the calculation unit 225.

In one embodiment, the final calculation unit 243 includes the first debt repayment ability evaluation result and the second debt repayment ability evaluation model 280 calculated from the first debt repayment ability evaluation model 260 by the calculation unit 225. The final debt repayment ability evaluation result is calculated using the second debt repayment ability evaluation result calculated from ).

In one embodiment, the final calculation unit 243 compares the first result of the first debt repayment ability evaluation result and the second result of the second debt repayment ability evaluation result to calculate the final debt repayment ability evaluation result. I can.

For example, if the first result value and the second result value differ by less than a predetermined reference value, the final calculation unit 243 may calculate the first result value as a final debt repayment ability evaluation result. In addition, the final calculation unit 243 may calculate the second result value as the final debt repayment ability evaluation result when the first result value and the second result value differ by more than a predetermined reference value.

As described above, the present invention calculates the final debt repayment ability evaluation result using all of the plurality of second debt repayment ability evaluation models 280 learned differently from the plurality of first debt repayment ability evaluation models 260, There is an effect of improving the reliability and accuracy of the evaluation results.

Unlike the above-described embodiment, it has been described that the final calculation unit 243 calculates the final debt repayment ability evaluation result by using both the first debt repayment ability evaluation model 260 and the second debt repayment ability evaluation model 280. , In a modified embodiment, the final calculation unit 225 targets the debt repayment ability evaluation result of the target company calculated from either the first debt repayment ability evaluation model 260 or the second debt repayment ability evaluation model 280. It can also be calculated as the result of evaluating the final debt repayment capability of the company.

In the database 245, the modeling unit 240 stores financial data, non-financial data, and commercial data of companies (hereinafter referred to as'comparative companies') in order to generate the debt repayment ability evaluation model 260, and generates derivative data. The derivative data of the comparative company generated by the unit 220 is stored. At this time, the target company may be included in the comparative company.

In one embodiment, the database 245 may be stored by acquiring financial data, non-financial data, and commercial transaction data of comparative companies from the external server 20 by the data acquisition unit 210.

The modeling unit 250 generates a debt repayment ability evaluation model 255. In an embodiment, the modeling unit 250 may generate an AI-based debt repayment capability evaluation model 255 using a gradient boosting machine (GBM) algorithm. In this case, the GBM algorithm is an algorithm that generates a decision tree sequentially and corrects an error in the previous tree to derive a result.

Unlike the above-described embodiment, the modeling unit 250 may generate an AI-based debt repayment capability evaluation model 255 using a random forest algorithm, a deep neural network (DNN) algorithm, or the like.

In one embodiment, the modeling unit 250 generates a plurality of first debt repayment capability evaluation models 260 by learning financial data, non-financial data, and derivative data of a comparative company stored in the database 245.

In particular, the modeling unit 250 according to the present invention learns financial data, non-financial data, and derivative data of a non-performing company in which a non-performing event occurred among comparative companies, and evaluates the debt repayment ability of the target company by sub-prediction period. 1 A debt repayment ability evaluation model 260 is created. In this case, the insolvency event may include at least one of short-term overdue, public overdue, financial overdue, card overdue, and closed business.

In one embodiment, the modeling unit 250 learns not only financial data, non-financial data, and derivative data of a comparative company stored in the database 245, but also commercial data, and provides a plurality of second debt repayment capability evaluation models 280. Generate. When following this embodiment, the insolvency event may further include a delinquent transaction.

The reason why the modeling unit 250 according to the present invention generates the second debt repayment capability evaluation model 280 by learning the commercial transaction data is that the most important evidence in the progress of corporate insolvency is the delinquency of the transaction to the customer. Therefore, by learning the commercial transaction data including this information to generate a plurality of second debt repayment ability evaluation models 280, it is possible to more accurately evaluate the debt repayment ability of the target company.

In one embodiment, the modeling unit 250 includes financial data, non-financial data generated in the expected insolvent period corresponding to each sub-prediction period among financial data, non-financial data, and derivative data of a non-performing company in which a non-performing event occurred, and By learning the derived data, each first debt repayment ability evaluation model 260 may be generated. In addition, the modeling unit 250 generates each second debt repayment ability evaluation model 280 by learning the commercial transaction data generated during the expected insolvent period corresponding to each sub-prediction period among the commercial transaction data of the insolvent company where the insolvent event has occurred. can do.

Hereinafter, with reference to FIG. 6, it will be described in more detail that the modeling unit 250 generates a plurality of first debt repayment ability evaluation models 260 and a plurality of second debt repayment ability evaluation models 280.

6 is a diagram illustrating that the modeling unit 250 generates a plurality of first debt repayment ability evaluation models 260 and a plurality of second debt repayment ability evaluation models 280 according to an embodiment of the present invention. As shown in FIG. 6, the modeling unit 250 includes a first learning unit 610, a second learning unit 620, a third learning unit 630, and a fourth learning unit 640. In addition, the first debt repayment ability evaluation model 260 generated by the modeling unit 250 includes the 1-1 model 660, the 1-2 model 665, the 1-3 model 670, and 1-4 models 675 are included. In addition, the second debt repayment capability evaluation model 280 generated by the modeling unit 250 includes a 2-1 model 680, a 2-2 model 685, a 2-3 model 690, and It includes the 2-4th model 695.

In FIG. 6, the modeling unit 250 is shown to include four learning units 610-640, but there may be three or less learning units or five or more learning units. Accordingly, the number of four first models 660-675 and four second models 680-695 generated by the modeling unit 260 may be three or less, or five or more. For convenience of description, it will be described that there are four learning units 610-640, first models 660-675, and second models 680-695.

The first learning unit 610 generates the 1-1 model 660 by learning financial data, non-financial data, and derivative data of a non-performing company in which a non-performing event has occurred among comparative companies stored in the database 245. Specifically, the first learning unit 610 includes the financial data, non-financial data, and derivative data of the insolvent company where the insolvency event has occurred, from the insolvency point where the insolvency event occurs to the first insolvency point before the insolvency point. The 1-1 model 660 is generated by learning the financial data, non-financial data, and derivative data generated during the first insolvency expected period. In addition, the first learning unit 610 generates the 2-1 model 680 by learning the financial data, non-financial data, commercial data, and derivative data of the insolvent company generated during the first insolvency expected period.

For example, the first scheduled insolvency may mean three months before the insolvency. When following this example, the first learning unit 610 learns the financial data, non-financial data, and derivative data of the insolvent company generated 3 months ago from the insolvency point where the insolvent event occurred, and the 1-1 model 660 ) Can be created.

The second learning unit 620 generates a second model 665 by learning the financial data, non-financial data, and derivative data of the insolvent company in which the insolvent event has occurred among the comparison companies stored in the database 245. Specifically, the second learning unit 620 is for the second expected insolvent period from the first expected insolvency point to the second expected insolvent point before the first expected insolvency point among the financial data, non-financial data, and derivative data of the insolvent company. The generated financial data, non-financial data, and derivative data are learned to generate a 1-2 model 665. In addition, the second learning unit 620 generates a 2-2 model 685 by learning the financial data, non-financial data, commerce data, and derivative data of the insolvent company generated during the second insolvent period.

For example, the second scheduled insolvency may mean three months before the first scheduled insolvency. When following this example, the second learning unit 620 learns the financial data, non-financial data, and derivative data of the insolvent company generated between 3 months to 6 months before the occurrence of the insolvency event, (665) can be created.

The third learning unit 630 generates a 1-3 model 670 by learning financial data, non-financial data, and derivative data of a non-performing company in which an insolvent event has occurred among the comparison companies stored in the database 245. Specifically, the third learning unit 630 occurs during the third expected insolvency period from the second learning point to the third expected insolvency point before the second expected insolvency point among financial data, non-financial data, and derivative data of insolvent companies. The generated financial data, non-financial data, and derivative data are learned to generate a 1-3 model 670. In addition, the third learning unit 630 learns the financial data, non-financial data, commerce data, and derivative data of the insolvent company generated during the third insolvent period to generate the 2-3rd model 690.

For example, the third expected insolvency may mean three months before the second expected insolvency. When following this example, the third learning unit 630 learns the financial data, non-financial data, and derivative data of the insolvent company generated between 3 months and 6 months before the occurrence of the insolvent event, 670 can be created.

The fourth learning unit 640 generates a 1-4 model 675 by learning financial data, non-financial data, and derivative data of a non-performing company in which a non-performing event has occurred among the comparison companies stored in the database 245. Specifically, the fourth learning unit 640 is for the fourth expected insolvency period from the third expected insolvency point to the fourth expected insolvency point before the third expected insolvency point among financial data, non-financial data, and derivative data of the insolvent company. The generated financial data, non-financial data, and derived data are learned to generate a 1-4 model 675. In addition, the fourth learning unit 640 generates a 2-4 model 695 by learning financial data, non-financial data, commerce data, and derivative data of the insolvent company generated during the fourth insolvent period.

For example, the fourth expected insolvency may mean three months before the third expected insolvency. When following this example, the fourth learning unit 640 learns the financial data, non-financial data, and derivative data of the insolvent company generated between 9 months and 12 months before the occurrence of the insolvency event, (675) can be created.

Referring back to FIG. 2, in an embodiment, the modeling unit 250 includes a plurality of first debt repayment capability evaluation models 260 and a plurality of second debt repayment capability evaluations for each type of business of a bad company in which a bad event has occurred. Each of the models 280 can be generated. In this case, the enterprise type may be set as a classification criterion for classifying the enterprise. In one embodiment, the classification criteria may include a business type, a company size, whether or not an externally audited company. Here, the externally audited company means a company that is obligated to undergo accounting audits.

For example, when the classification criterion is the size of the company and whether it is an externally audited company, the modeling unit 250 generates a plurality of first debt repayment capacity evaluation models 260 for each type of enterprise classified according to the size of the comparative company and whether or not it is externally audited company can do. In this case, the type of enterprise may include externally audited enterprises, non-exclusively audited enterprises, small and medium-sized enterprises (hereinafter referred to as'small enterprises'), and individual entrepreneurs.

When following this example, the modeling unit 250 uses the financial data, non-financial data, and derivative data of a non-performing company corresponding to an externally audited company among a plurality of comparative companies, to generate a plurality of first debt repayment capability evaluation models 260. Can be generated. In addition, the modeling unit 250 may generate a plurality of first debt repayment ability evaluation models 260 using financial data, non-financial data, and derivative data of a non-performing company corresponding to a non-offset company among a plurality of insolvent companies. have. In addition, the modeling unit 250 may generate a plurality of first debt repayment capability evaluation models 260 by using financial data, non-financial data, and derivative data of a bad company corresponding to a small company among a plurality of bad companies. In addition, the modeling unit 250 may generate a plurality of first debt repayment ability evaluation models 260 by using financial data, non-financial data, and derivative data of a bad company corresponding to an individual business among a plurality of bad companies. .

According to this embodiment, the modeling unit 250 may generate k*l first debt repayment capability evaluation models 260 according to k enterprise types and l prediction periods. In addition, the modeling unit 250 may generate k*l second debt repayment capability evaluation models 280 according to k business types and l prediction periods.

For example, the first to fourth learning units 610-640 included in the modeling unit 250 learn from the financial data, non-financial data, and derivative data of the external audit enterprise in which the insolvency event has occurred, and You can create a model.

In addition, the first to fourth learning units 610 to 640 may learn the financial data, non-financial data, and derivative data of the non-instrumented company in which the insolvency event has occurred to generate the first to fourth non-instrued company models. .

In addition, the first to fourth learning units 610 to 640 may generate first to fourth small business models by learning from financial data, non-financial data, and derivative data of a small company in which an insolvent event has occurred.

In addition, the first to fourth learning units 610 to 640 may generate first to fourth private business models learned from financial data, non-financial data, and derivative data of an individual business operator in which an insolvency event has occurred.

The modeling unit 250 inputs test data into the generated first plurality of debt repayment ability evaluation models 260 and second plurality of debt repayment ability evaluation models 280 to verify whether the comparison company's actual insolvency probability and match. can do. In this case, the test data may include financial data, non-financial data, and derivative data of the comparative company. In one embodiment, the modeling unit 250 uses a plurality of first debt repayment capability evaluation models 260 and a plurality of second debt repayments using AUC (Area Under the ROC Curve) or KS statistics (Kolmogorov Smirnov Statistics). The capability evaluation model 280 may be verified. For example, as shown in FIG. 7, the modeling unit 250 may verify a plurality of debt repayment capability evaluation models 255.

According to this embodiment, the first to fourth learning units 660 to 675 included in the modeling unit 250 respectively verify the first model and the second model, or the modeling unit 250 A separate verification unit (not shown) for verifying the first debt repayment capability evaluation model 260 and the plurality of second debt repayment capability evaluation models 280 may be further included.

The plurality of debt repayment capability evaluation models 255 calculates the probability of insolvency at which insolvency events will occur in the target company for each predetermined sub-prediction period. To this end, the plurality of debt repayment ability evaluation models 255 includes a first debt repayment ability evaluation model 260 and a second debt repayment ability evaluation model 280.

The plurality of first debt repayment capability evaluation models 260 receive financial data and non-financial data of the target company by the calculation unit 225 and calculate the probability of insolvency at which insolvency events will occur in the target company for each predetermined sub-prediction period. do. Specifically, when the plurality of first debt repayment capability evaluation models 260 are inputted by the calculation unit 225 into the financial data and non-financial data of the target company, each debt repayment capability evaluation model is targeted for each predetermined sub-prediction period. Calculate the probability of insolvency at which insolvent events will occur in the company. In one embodiment, the plurality of first debt repayment ability evaluation models 260 additionally receive derivative data by the calculation unit 225, and calculate the insolvency probability that a non-performing event will occur in the target company for each sub-prediction period. Can do

In one embodiment, the sub-prediction period may be determined as at least one of daily, monthly, and quarterly. According to this embodiment, the plurality of first debt repayment capability evaluation models 260 may evaluate the debt repayment capability of the target company according to at least one sub-prediction period of daily, monthly, and quarterly.

In one embodiment, the sub prediction period may divide the main prediction period into quartiles. When following this embodiment, the plurality of first debt repayment ability evaluation models 260 may evaluate the debt repayment ability for each quintile.

In one embodiment, each first debt repayment ability evaluation model 260 divides the main prediction period into a plurality of sub prediction periods, and can be learned for each insolvency expected period of the insolvent company corresponding to each divided sub prediction period. have. Specifically, each first debt repayment capability evaluation model 260 is the financial data of the insolvent company generated during the expected insolvent period corresponding to each sub-prediction period among the financial data, non-financial data, and derivative data of the insolvent company where the insolvent event occurred. , Non-financial data, and derived data can be learned.

Hereinafter, a plurality of first debt repayment ability evaluation models 260 will be described in more detail with reference to FIG. 6.

As shown in FIG. 6, the plurality of debt repayment ability evaluation models 260 are the 1-1 model 660, the 1-2 model 665, the 1-3 model 670, and the 1-4 Model 675 may be included. As described above, the number of the four first models 660 to 675 may be three or less, and may be five or more.

When the financial data, non-financial data, and derivative data of the target company are input by the first calculation unit 230, the 1-1 model 660 is targeted during the first sub-prediction period from the time of evaluation to the time of the first sub-prediction. Calculate the probability of insolvency at which insolvent events will occur in the company. At this time, the first sub-prediction time point means a time point later than the evaluation time point.

For example, the first sub-prediction time may mean three months after the evaluation time. Following this example, the 1-1 model 660 may calculate a probability of insolvency at which insolvency events will occur in the target company from the time of evaluation to three months.

In one embodiment, the 1-1 model 660 is the first insolvency project from the insolvency point where the insolvency event is generated in the insolvent company by the first learning unit 610 to the first insolvency schedule before the insolvency point. Financial data, non-financial data, and derivative data of the insolvent company generated during the period may be learned.

Following this embodiment, the first expected insolvency period may correspond to the first sub-prediction period. For example, if the first sub-prediction period is 3 months from the time of evaluation, the first expected insolvency period is 3 months from the time of non-conduct.

In the 1-2 model 665, when financial data, non-financial data, and derivative data of the target company are input by the first calculation unit 230, the second sub-prediction from the first sub-prediction time to the second sub-prediction time Calculate the probability of insolvency at which insolvency events will occur in the target company during the period. In this case, the second sub-prediction time refers to a time later than the first sub-prediction time.

For example, the second sub-prediction time may mean three months after the first sub-prediction time. Following this example, the 1-2 model 665 may calculate a probability that an insolvent event will occur in the target company from 3 months to 6 months from the time point of evaluation.

In one embodiment, the 1-2 model 665 is performed by the second learning unit 620 during the second expected insolvency period from the first expected insolvency to the second expected insolvency before the first expected insolvency. The generated financial data, non-financial data, and derivative data of the insolvent company may be learned.

Following this embodiment, the second insolvency expected period may correspond to the second sub-prediction period. For example, if the second sub-prediction period is from 3 months to 6 months from the time of evaluation, the second expected period of insolvency is from 3 months to 6 months from the time of non-implementation.

When the financial data, non-financial data and derivative data of the target company are input by the first calculation unit 230, the 1-3 model 670 is a third sub-prediction from the second sub-prediction time to the third sub-prediction time. Calculate the probability of insolvency at which insolvency events will occur in the target company during the period. In this case, the third sub-prediction time point means a time point later than the second sub-prediction time point.

For example, the third sub-prediction time may mean three months after the second sub-prediction time. Following this example, the 1-3 models 670 can calculate the probability of occurrence of a bad event in the target company from 6 months to 9 months from the time of evaluation.

In one embodiment, the 1-3 models 670 are performed by the third learning unit 630 during the third expected insolvency period from the second expected insolvency to the third expected insolvency before the second expected insolvency. The generated financial data, non-financial data, and derivative data of the insolvent company may be learned.

Following this embodiment, the third expected insolvency period may correspond to the third sub-prediction period. For example, if the third sub-prediction period is from 6 months to 9 months from the time of evaluation, the third expected insolvency period is from 6 months to 9 months from the time of non-implementation.

When the financial data, non-financial data, and derivative data of the target company are input by the first calculation unit 230, the 1-4 model 675 is a fourth sub-prediction from the third sub-prediction to the fourth sub-prediction. Calculate the probability of insolvency at which insolvency events will occur in the target company during the period. In this case, the fourth sub-prediction time point means a time point later than the third sub-prediction time point.

For example, the fourth sub-prediction time may mean three months after the third sub-prediction time. Following this example, the model 1-4 675 may calculate a probability that an insolvent event will occur in the target company from 9 months to 12 months from the time point of evaluation.

In one embodiment, the model 1-4 675 is performed by the fourth learning unit 640 during the fourth expected insolvency period from the third expected insolvency to the fourth expected insolvency before the third expected insolvency. The generated financial data, non-financial data, and derivative data of the insolvent company may be learned.

Following this embodiment, the fourth expected period of insolvency may correspond to the fourth sub-prediction period. For example, if the fourth sub-prediction period is from 9 months to 12 months from the time of evaluation, the fourth expected period of insolvency is from 9 months to 12 months from the time of insolvency.

The first model 660-675 according to the present invention may calculate the insolvency probability of the target company in the first to fourth sub-prediction periods as shown in FIG. 8A. In a modified embodiment different from the above-described embodiment, one first model 660 may calculate the insolvency probability of the target company in the first to fourth sub-prediction periods, respectively, as shown in FIG. 8B. In addition, in another modified embodiment, one first model 660 may calculate the insolvency probability during the total prediction period of the first to fourth sub-prediction periods.

In one embodiment, the first models 660-675 may be generated for each type of company by the first to fourth learning units 610-640. In this case, the type of enterprise includes at least one of an externally audited enterprise, a non externally audited enterprise, a small enterprise, and an individual business entity.

According to this embodiment, there may be a plurality of first models 660 to 675, respectively, depending on the type of company.

For example, when the type of enterprise is an externally audited enterprise, a non-exclusively audited enterprise, a small enterprise, and an individual entrepreneur, the first model 660-675 may be a first to fourth externally audited enterprise model, and the first model 660-675 is It may be the 1st to 4th non-expansion company model. Further, the first models 660-675 may be first to fourth small business models, and the first to fourth models 660-675 may be first to fourth private business models. Following this example, four first models 660-675 may be generated by the learning units 610-640.

The plurality of second debt repayment capability evaluation models 280 receives financial data and non-financial data of the target company by the calculation unit 225 and calculates the probability of insolvency at which insolvency events will occur in the target company for each predetermined sub-forecast period do. Specifically, when the plurality of second debt repayment capability evaluation models 280 are inputted by the calculation unit 225 into the financial data and non-financial data of the target company, each second debt repayment capability evaluation model 280 is predetermined. Calculate the probability of insolvency at which insolvency events will occur in the target company for each sub-prediction period.

In particular, the plurality of second debt repayment capability evaluation models 280 inputs the commercial transaction data of the target company by the calculation unit 225, and thus calculates the insolvency probability that a non-performing event will occur in the target company for each predetermined sub-prediction period. I can.

In one embodiment, the plurality of second debt repayment capability evaluation models 280 additionally receive derivative data by the calculation unit 225, and calculate the insolvency probability that a non-performing event will occur in the target company for each sub-prediction period. Can do

In one embodiment, the sub-prediction period may be determined as at least one of daily, monthly, and quarterly. According to this embodiment, the plurality of second debt repayment capability evaluation models 280 may evaluate the debt repayment capability of the target company according to at least one sub-prediction period of daily, monthly, and quarterly.

In one embodiment, the sub prediction period may divide the main prediction period into quartiles. When following this embodiment, the plurality of second debt repayment ability evaluation models 280 may evaluate the debt repayment ability for each quintile.

In one embodiment, each second debt repayment capability evaluation model 280 divides the main prediction period into a plurality of sub prediction periods, and can be learned for each insolvency expected period of the insolvent company corresponding to each divided sub prediction period. have. Specifically, each second debt repayment capability evaluation model 280 is a method of insolvent corporations occurring during the expected insolvent period corresponding to each sub-prediction period among financial data, non-financial data, commercial data, and derivative data of insolvent companies in which the insolvency event occurred. Financial data, non-financial data, commerce data, and derivative data can be learned.

Hereinafter, a plurality of second debt repayment ability evaluation models 280 will be described in more detail with reference to FIG. 6.

As shown in FIG. 6, the plurality of second debt repayment ability evaluation models 280 are the 2-1 model 680, the 2-2 model 685, the 2-3 model 690, and the second -4 models 695 may be included. As described above, the number of four models 680-695 may be three or less, and may be five or more.

When the financial data, non-financial data, commercial transaction data, and derivative data of the target company are input by the first calculation unit 230, the 2-1 model 680 is a first sub-prediction from the time of evaluation to the time of the first sub-prediction. Calculate the probability of insolvency at which insolvency events will occur in the target company during the period. At this time, the first sub-prediction time point means a time point later than the evaluation time point.

For example, the first sub-prediction time may mean three months after the evaluation time. Following this example, the 2-1 model 680 can calculate the insolvency probability that the insolvency event will occur in the target company from the time of evaluation to 3 months.

In one embodiment, the 2-1 model 680 is the first insolvency project from the insolvency point where the insolvency event is generated in the insolvent company by the first learning unit 610 to the first insolvency scheduled time before the insolvency point. Financial data, non-financial data, commerce data, and derivative data of the insolvent company generated during the period may be learned.

Following this embodiment, the first expected insolvency period may correspond to the first sub-prediction period. For example, if the first sub-prediction period is 3 months from the time of evaluation, the first expected insolvency period is 3 months from the time of non-conduct.

When the financial data, non-financial data, commercial transaction data, and derivative data of the target company are input by the first calculation unit 230, the 2-2 model 685 is determined from the first sub-prediction time to the second sub-prediction time. 2 Calculate the probability of insolvency at which insolvency events will occur in the target company during the sub-prediction period. In this case, the second sub-prediction time refers to a time later than the first sub-prediction time.

For example, the second sub-prediction time may mean three months after the first sub-prediction time. Following this example, the 2-2 model 685 may calculate a probability that an insolvent event will occur in the target company from 3 months to 6 months from the time point of evaluation.

In one embodiment, the 2-2 model 685 is performed by the second learning unit 620 during the second expected insolvency period from the first expected insolvency to the second expected insolvency before the first expected insolvency. The generated financial data, non-financial data, commerce data, and derivative data of the insolvent company may be learned.

Following this embodiment, the second insolvency expected period may correspond to the second sub-prediction period. For example, if the second sub-prediction period is from 3 months to 6 months from the time of evaluation, the second expected period of insolvency is from 3 months to 6 months from the time of non-implementation.

When the financial data, non-financial data, commercial transaction data, and derivative data of the target company are input by the first calculation unit 230, the 2-3 model 690 is determined from the second sub-prediction time to the third sub-prediction time. 3 Calculate the probability of insolvency at which insolvency events will occur in the target company during the sub-forecast period. In this case, the third sub-prediction time point means a time point later than the second sub-prediction time point.

For example, the third sub-prediction time may mean three months after the second sub-prediction time. Following this example, the 2-3rd model 690 may calculate a probability that a bad event will occur in the target company from 6 months to 9 months from the time point of evaluation.

In one embodiment, the 2-3rd model 690 is performed by the third learning unit 630 during the third expected insolvency period from the second expected insolvency to the third expected insolvency before the second expected insolvency. The generated financial data, non-financial data, commerce data, and derivative data of the insolvent company may be learned.

Following this embodiment, the third expected insolvency period may correspond to the third sub-prediction period. For example, if the third sub-prediction period is from 6 months to 9 months from the time of evaluation, the third expected insolvency period is from 6 months to 9 months from the time of non-implementation.

In the 2-4 model 695, when financial data, non-financial data, commercial data, and derivative data of the target company are input by the first calculation unit 230, the third sub-prediction time to the fourth sub-prediction time 4 Calculate the probability of insolvency at which insolvency events will occur in the target company during the sub-prediction period. In this case, the fourth sub-prediction time point means a time point later than the third sub-prediction time point.

For example, the fourth sub-prediction time may mean three months after the third sub-prediction time. Following this example, the 2-4 model 695 can calculate the probability that a bad event will occur in the target company from 9 months to 12 months from the time point of evaluation.

In one embodiment, the 2-4 model 695 is performed by the fourth learning unit 640 during the fourth expected insolvency period from the third expected insolvency to the fourth expected insolvency before the third expected insolvency. The generated financial data, non-financial data, commerce data, and derivative data of the insolvent company may be learned.

Following this embodiment, the fourth expected period of insolvency may correspond to the fourth sub-prediction period. For example, if the fourth sub-prediction period is from 9 months to 12 months from the time of evaluation, the fourth expected period of insolvency is from 9 months to 12 months from the time of insolvency.

The second model 680-695 according to the present invention can calculate the insolvency probability of the target company in the first to fourth sub-prediction periods as shown in FIG. 8A. In a modified embodiment different from the above-described embodiment, one second model 680 may calculate the insolvency probability of the target company in the first to fourth sub-prediction periods, respectively, as shown in FIG. 8B. In addition, in another modified embodiment, one second model 680 may calculate the insolvency probability during the total prediction period of the first to fourth sub-prediction periods.

In an embodiment, the second model 680-695 may be generated for each company type by the first to fourth learning units 610-640. In this case, the type of enterprise includes at least one of an externally audited enterprise, a non externally audited enterprise, a small enterprise, and an individual business entity.

When following this embodiment, there may be a plurality of second models 680-695, respectively, depending on the type of company.

For example, when the type of enterprise is an externally audited enterprise, a non-exclusively audited enterprise, a small enterprise, and an individual business, the second model 680-695 may be the first to fourth externally audited enterprise models, and the second model 680-695 is It may be the 1st to 4th non-expansion company model. In addition, the second model 680-695 may be the first to fourth small business models, and the second model 680-695 may be the first to fourth private business models. Following this example, the four second models 680-695 may be generated by the learning units 610-640.

On the other hand, the debt repayment ability evaluation system 100 may further include a payment capacity evaluation unit 295.

The payment capacity evaluation unit (295) is a marginal borrowing inference model (not shown) generated by learning through correlation analysis between the borrowing information among the financial data of a company with financial statements and the credit contribution information among the non-financial data of the company, and appropriate borrowings. Using an inference model (not shown), the payment capacity of the target company can be calculated. At this time, marginal borrowings refer to borrowings that the target company can bear up to the limit in consideration of operating activities, assets, and industrial average, and appropriate borrowings refer to borrowings that the target company can bear in consideration of business activities. The payment capacity may refer to the range of marginal borrowings and appropriate borrowing amounts.

Referring back to FIG. 1, the external server 20 collects financial data and non-financial data on the target company based on the financial statements of the target company and transmits it to the debt repayment ability evaluation system 100. In addition, the external server 20 collects commerce data based on the bond information of the target company and transmits it to the debt repayment ability evaluation system 100.

In an embodiment, when a non-donation event occurs in the target company, the external server 20 may transmit information on the occurrence of the non-donation event to the second calculation unit 240 through the data acquisition unit 210.

Those skilled in the art to which the present invention pertains will appreciate that the above-described present invention can be implemented in other specific forms without changing the technical spirit or essential features thereof.

Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

100: Debt repayment ability evaluation system.
210: data acquisition unit 220: derived data generation unit
225: calculation unit 230: first calculation unit
240: second calculation unit 250: modeling unit
255: debt repayment ability evaluation model 260: first debt repayment ability evaluation model
280: second debt repayment ability evaluation model 295: payment capacity evaluation unit

Claims (14)

A data acquisition unit for acquiring financial data obtained based on the financial statements of the target company, non-financial data other than the financial data, and commercial transaction data acquired based on the bond information of the target company;
The main forecasting period from the evaluation point to the forecasting point after the evaluation point is divided into a plurality of sub-prediction periods, and the financial data, the non-financial data, and the commercial transaction are applied to a plurality of debt repayment ability evaluation models generated for each sub-prediction period. A calculation unit for inputting data and calculating a result of evaluating the debt repayment capability of the target company; And
Debt repayment of a company including an AI-based evaluation model using commercial data, characterized in that it comprises a final calculation unit that calculates the final debt repayment ability evaluation result of the target company using the debt repayment ability evaluation result of the target company Ability evaluation system. The method of claim 1,
The plurality of debt repayment ability evaluation models are generated as a plurality of different first debt repayment ability evaluation models by learning each of the financial data and the non-financial data for each expected insolvent period of a non-performing company corresponding to each sub-prediction period. A company's debt repayment ability evaluation system that includes an AI-based evaluation model using the featured commercial data. The method of claim 1,
The plurality of debt repayment ability evaluation models are generated as a plurality of different second debt repayment ability evaluation models by learning the transaction data of the insolvent company according to the expected insolvent period of the insolvent company corresponding to each of the sub prediction periods. A company's debt repayment ability evaluation system that includes an AI-based evaluation model using commerce data. The method of claim 1,
The commercial transaction data includes at least one of the sales receivable information of the target company and the collection performance information of the target company. A system for evaluating debt repayment capability of a company including an AI-based evaluation model using commercial data. The method of claim 1,
Each sub-prediction period is the main prediction period is divided into quartiles,
The plurality of debt repayment ability evaluation models are generated for each quintile, and each of the plurality of debt repayment ability evaluation models includes an AI-based evaluation model using commercial data, characterized in that the target company's debt repayment ability is evaluated. A system for evaluating the debt repayment ability of a company. The method of claim 1,
The debt repayment ability evaluation model uses a plurality of first debt repayment ability evaluation models and the commercial transaction data for calculating a first debt repayment ability evaluation result for each of the plurality of sub-prediction periods using the financial data and the non-financial data. And a plurality of second debt repayment ability evaluation models for calculating a second debt repayment ability evaluation result for each of the plurality of sub prediction periods,
The calculation unit calculates a first result selected from among a plurality of first debt repayment ability evaluation results and a second result selected from among a plurality of second debt repayment ability evaluation results as a result of evaluating the debt repayment ability of the target company. A company's debt repayment ability evaluation system that includes an AI-based evaluation model using the featured commercial data. The method of claim 6,
The first result value is a median value of the plurality of first debt repayment ability evaluation results, the lowest evaluation result among the plurality of first debt repayment ability evaluation results, and among the plurality of first debt repayment ability evaluation results. Is determined as one of the highest evaluation results,
The second result value is a median value of the plurality of second debt repayment ability evaluation results, the lowest evaluation result among the plurality of second debt repayment ability evaluation results, and among the plurality of second debt repayment ability evaluation results. A company's debt repayment ability evaluation system including an AI-based evaluation model using commercial data, which is determined as one of the highest evaluation results. The method of claim 6,
The plurality of first debt repayment ability evaluation results and the plurality of second debt repayment ability evaluation results are calculated as a plurality of grades,
The calculation unit
The first result according to the priority of a plurality of ratings for each first debt repayment ability evaluation model according to the distance on the time axis from the evaluation point to the reference point included in each sub-prediction period of the plurality of first debt repayment ability evaluation models Calculate the value,
The second result according to the priority of a plurality of grades for each second debt repayment ability evaluation model according to the distance on the time axis from the evaluation point to the reference point included in each sub-prediction period of the plurality of second debt repayment ability evaluation models. A company's debt repayment ability evaluation system including an AI-based evaluation model using commercial data, characterized in that calculating a value. The method of claim 6,
The final calculation unit
If the difference between the first result value and the second result value is less than a predetermined reference value, the first result value is calculated as the final debt repayment ability evaluation result of the target company, and if the difference is more than the reference value, the second result A company's debt repayment capability evaluation system including an AI-based evaluation model using commercial data, characterized in that the value is calculated as a result of the final debt repayment capability evaluation result of the target company. The method of claim 1,
The financial data includes at least one of financial statement information, financial ratio information, financial model information, and borrowing information of the target company, and the non-financial data includes company information, credit grant information, bidding information, contract information of the target company. , National pension information, employment announcement information, fraudulent disposition information, and a company's debt repayment ability evaluation system comprising an AI-based evaluation model using commercial data, characterized in that it includes at least one of the information on disposition of construction licenses. The method of claim 1,
Financial data, non-financial data, and commerce data, and derived data generated from the financial data, non-financial data, and commerce data, respectively, of the insolvent company where the insolvency event has occurred for each predetermined insolvency period corresponding to each of the sub-prediction periods A system for evaluating debt repayment ability of a company including an AI-based evaluation model using commercial data, characterized in that it further comprises a modeling unit that learns to generate the plurality of debt repayment ability evaluation models. The method of claim 11,
The insolvency event includes at least one of short-term delinquency, public delinquency, financial delinquency, card delinquency, commerce delinquency, closed business, and non-receivables of accounts receivable. Debt repayment ability evaluation system. The method of claim 1,
Further comprising a modeling unit for generating the plurality of debt repayment capability evaluation models,
The modeling unit generates each of the plurality of debt repayment capability evaluation models for each type of company,
The calculation unit selects the plurality of debt repayment ability evaluation models that match the type of the company to which the target company belongs, and calculates the debt repayment ability evaluation result of the target company. A system for evaluating the company's debt repayment ability, including. A data acquisition unit for acquiring commercial transaction data acquired based on the bond information of the target company;
The main forecasting period from the evaluation point to the forecasting point after the evaluation point is divided into a plurality of sub-prediction periods, and the transaction data is input to a plurality of debt repayment capacity evaluation models generated for each sub-prediction period, and the respective debt repayment capabilities A calculation unit that calculates a result of evaluating the debt repayment ability of the target company for each evaluation model; And
AI using commercial data, characterized in that it comprises a final calculation unit that calculates the final debt repayment ability evaluation result of the target company by using at least one evaluation result among the debt repayment ability evaluation results calculated for each debt repayment ability evaluation model. A system for evaluating a company's debt repayment ability, including a base evaluation model.

Images