Credit risk scoring model

By designing a credit risk scoring model in the risk management system of financial companies, using tree structure and multi-dimensional time series data matrix, the problem of inefficiency of financial companies in customer credit ratings is solved, and the accuracy and efficiency of credit risk ratings are achieved. promote.

CN118941375APending Publication Date: 2024-11-12珠海华发金融科技研究院有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410895510.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Financial companies face risks brought about by changes in customer credit in risk management, and it is difficult for existing technology to effectively identify and rated different customers, resulting in inefficient risk management and control.

Method used

Design a credit risk scoring model, including a score card management module based on a tree structure, a main ruler management module, a debt model configuration module and an industry model configuration module, which supports classification setting of score cards, main ruler, and models, and obtain and Process financial and non-financial indicator data to generate a multi-dimensional time series data matrix and establish a risk prediction model.

Benefits of technology

The accuracy and efficiency of credit risk ratings have been improved. Through the data accumulation and optimization of the information system, the diversified business needs of financial companies are met and the effectiveness of ratings has been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941375A_ABST
    Figure CN118941375A_ABST
Patent Text Reader

Abstract

The invention discloses a credit risk scoring model which comprises a scoring card management module, a main scale management module, a debt item model configuration module and an industry model configuration module. Classification of the score card management module comprises debt items, subjects and individuals, score cards are arranged under the debt item, subject and individual classification, and the score card design comprises index names, corresponding weights and permission configuration; the classification of the main scale management module comprises a debt item, a subject and an individual, a main scale is arranged under the classification of the debt item, the subject and the individual, and the design of the main scale comprises credit rating, risk description, risk weight and risk weight. According to the method, based on flexible tree structure design, through freely-extensible indexes and authority distribution, most business credit risk rating requirements of financial companies can be met, the companies can be assisted to realize online evaluation of a rating model, rating accuracy and rating efficiency are further improved, data are accumulated through an informatization system, and the evaluation efficiency of the financial companies is improved. And the scoring model is continuously optimized and perfected, and the rating effectiveness is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of risk control, and in particular to a credit risk scoring model. Background Art

[0002] With the development of financial group companies, the scale of credit business has expanded, the number of customers has increased, and the group projects may face many risks due to changes in customer credit. There is an urgent need to improve the group's risk management capabilities and levels. Based on the risk management information system that has been built by financial companies, it is necessary to further model the risk management items, use the information system to identify different customers, adapt different scoring models and scales, and efficiently and accurately rate customers to improve the risk management efficiency within the group. Summary of the invention

[0003] The purpose of the present invention is to provide a credit risk scoring model to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: a credit risk scoring model, comprising a scoring card management module, a main scale management module, a debt model configuration module and an industry model configuration module constructed based on a tree design;

[0005] The scorecard management module is classified into debt, subject, and individual. Scorecards are set under the debt, subject, and individual classifications. The scorecard design includes indicator names, corresponding weights, and authority configurations. The scorecard management module manages the scorecards according to the scorecard design.

[0006] The main scale management module classification includes debt, subject, and individual. The main scale is set under the debt, subject, and individual classification. The main scale design includes credit rating, risk description, risk weight, and risk weight; the main scale management module is used to define the credit rating and the score range corresponding to the scoring result;

[0007] The debt model configuration module classification includes debt investment, financial products, and private equity funds. The bottom layer of the debt investment, financial products, and private equity fund classifications is designed with a model name and a field for whether it is a default. The model name corresponds to a score card set by a score card management module. The debt model configuration module configures the debt model according to the score card management module.

[0008] The industry model configuration module is classified into the national standard industry classification, which meets the needs of different management and control granularity, designs the model name and whether the field is default. The model name corresponds to the score card set by the score card management module. The industry model configuration module configures the industry model according to the score card management module.

[0009] Preferably, the scorecard supports add, delete, modify and query operations.

[0010] Preferably, the setting of the scorecard is specifically as follows: obtaining a modeling sample, the modeling sample is a sample obtained by querying a data source based on a resampled sample, the resampled sample is a sample obtained by resampling an original sample, the data source is a data source that can reflect credit risk, the modeling sample, the original sample and the resampled sample are used to represent the object characteristics of the business object in the preset business; establishing a risk prediction model based on the modeling sample; and creating a credit risk scorecard based on the risk prediction model.

[0011] Preferably, the scorecard management module comprises an acquisition unit, which acquires data to be evaluated, and the data to be evaluated comprises data of multiple financial indicators and / or data of multiple non-financial indicators.

[0012] Preferably, the scoring card management module includes an evaluation unit, which inputs the data to be evaluated into a credit risk scoring model to obtain a risk value of the data to be evaluated.

[0013] Preferably, each financial indicator data and each non-financial indicator data carry time information, and a multi-dimensional time series data matrix is ​​generated according to the data of multiple financial indicators and the data of multiple non-financial indicators.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] Based on a flexible tree structure design, with its freely scalable indicators and authority allocation, it can meet the credit risk rating needs of most financial companies. It can assist companies in realizing online scoring models, thereby improving rating accuracy and efficiency, and accumulate data through information systems, continuously optimize and improve scoring models, and enhance rating effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 , the present invention provides a technical solution: a credit risk scoring model, including a scoring card management module, a main scale management module, a debt model configuration module and an industry model configuration module constructed based on a tree design;

[0019] The scorecard management module is classified into debt, subject, and individual. Scorecards are set under the debt, subject, and individual classifications. The scorecard design includes indicator names, corresponding weights, and authority configurations. The scorecard management module manages the scorecards according to the scorecard design.

[0020] The main scale management module classification includes debt, subject, and individual. The main scale is set under the debt, subject, and individual classification. The main scale design includes credit rating, risk description, risk weight, and risk weight; the main scale management module is used to define the credit rating and the score range corresponding to the scoring result;

[0021] The debt model configuration module classification includes debt investment, financial products, and private equity funds. The bottom layer of the debt investment, financial products, and private equity fund classifications is designed with a model name and a field for whether it is a default. The model name corresponds to a score card set by a score card management module. The debt model configuration module configures the debt model according to the score card management module.

[0022] The industry model configuration module is classified into the national standard industry classification, which meets the needs of different management and control granularity, designs the model name and whether the field is default. The model name corresponds to the score card set by the score card management module. The industry model configuration module configures the industry model according to the score card management module.

[0023] In the present invention, the scorecard supports add, delete, modify and query operations.

[0024] In the present invention, the setting of the scorecard is specifically as follows: obtaining a modeling sample, the modeling sample is a sample obtained by querying a data source based on a resampled sample, the resampled sample is a sample obtained by resampling an original sample, the data source is a data source that can reflect credit risk, the modeling sample, the original sample and the resampled sample are used to represent the object characteristics of the business object in the preset business; establishing a risk prediction model based on the modeling sample; and creating a credit risk scorecard based on the risk prediction model.

[0025] In the present invention, the scorecard management module comprises an acquisition unit, which acquires data to be evaluated, and the data to be evaluated comprises data of multiple financial indicators and / or data of multiple non-financial indicators.

[0026] In the present invention, the scoring card management module includes an evaluation unit, which inputs the data to be evaluated into the credit risk scoring model to obtain the risk value of the data to be evaluated.

[0027] In the present invention, each financial indicator data and each non-financial indicator data carry time information, and a multi-dimensional time series data matrix is ​​generated according to a plurality of financial indicator data and a plurality of non-financial indicator data.

[0028] The present invention forms a credit risk scoring model by designing four functional modules: score card management, main scale management, debt model configuration, and industry model configuration. It is also applied to rating practices of institutions, individuals, and projects by setting model parameters such as specific indicators, thresholds, and weights.

[0029] The scorecard management is designed in a tree structure, and the classification can include debt items, entities, individuals, etc.; each classification can be further subdivided. For example, under the debt category, you can design debt investment plans and financial products according to business needs, and further set scorecards for specific project types, using this scorecard as the bottom-level classification. The scorecard design includes the indicator name, corresponding weight, and permission configuration, all of which support operations such as adding, deleting, modifying, and checking, to achieve various scorecards covering the company's practical business.

[0030] The main scale management is designed in a tree structure. The classification may include debt items, entities, individuals, etc., corresponding to the classification of scorecard management. Under each classification, such as debt items, the main scales such as debt investment plan, financial product, and entity model are designed. The main scale design includes credit rating, risk description, risk weight (lower limit), risk weight (upper limit), etc., and defines the score range corresponding to the credit rating and its scoring results.

[0031] The debt model configuration is designed in a tree structure. The categories can include debt investment, financial products, private equity funds, etc., and can be flexibly classified according to the company's practical needs. At the bottom of the classification, the model name and the default field are designed. The model name corresponds to the scorecard set in the scorecard management.

[0032] The industry model configuration is designed in a tree structure, which is classified into national standard industry classifications and can be flexibly adjusted according to the company's practical needs. Under each classification of the tree structure, different control granularity needs are met. Design the model name and whether it is a default field. The model name corresponds to the scorecard that has been set in the scorecard management.

[0033] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the embodiments of the present invention have been shown and described, it is understood by ordinary technicians in the field that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A credit risk scoring model, Features: It includes the scorecard management module, main scale management module, debt model configuration module and industry model configuration module based on tree design; The scorecard management module is classified into debt, subject, and individual. Scorecards are set under the debt, subject, and individual classifications. The scorecard design includes indicator names, corresponding weights, and authority configurations. The scorecard management module manages the scorecards according to the scorecard design. The main scale management module is classified into debt, subject, and individual. The main scale is set under the debt, subject, and individual classification. The main scale design includes credit rating, risk description, and risk weight; the main scale management module is used to define the credit rating and the score range corresponding to the scoring result; The debt model configuration module classification includes debt investment, financial products, and private equity funds. The bottom layer of the debt investment, financial products, and private equity fund classifications is designed with a model name and a field for whether it is a default. The model name corresponds to a score card set by a score card management module. The debt model configuration module configures the debt model according to the score card management module. The industry model configuration module is classified into the national standard industry classification, which meets the needs of different management and control granularity, designs the model name and whether the field is default. The model name corresponds to the score card set by the score card management module. The industry model configuration module configures the industry model according to the score card management module.

2. A credit risk scoring model according to claim 1, Features: The scorecard supports add, delete, modify and query operations.

3. A credit risk scoring model according to claim 1, Features: The setting of the scorecard is specifically as follows: obtaining a modeling sample, the modeling sample is a sample obtained by querying a data source based on a resampled sample, the resampled sample is a sample obtained by resampling an original sample, the data source is a data source that can reflect credit risk, the modeling sample, the original sample and the resampled sample are used to represent the object characteristics of the business object in the preset business; establishing a risk prediction model based on the modeling sample; and creating a credit risk scorecard based on the risk prediction model.

4. A credit risk scoring model according to claim 1, Features: The scorecard management module includes an acquisition unit, which acquires data to be evaluated, and the data to be evaluated includes data of multiple financial indicators and / or data of multiple non-financial indicators.

5. A credit risk scoring model according to claim 1, Features: The scoring card management module includes an evaluation unit, which inputs the data to be evaluated into the credit risk scoring model to obtain the risk value of the data to be evaluated.

6. A credit risk scoring model according to claim 4, Features: The data of each financial indicator and the data of each non-financial indicator carry time information, and a multi-dimensional time series data matrix is ​​generated according to the data of multiple financial indicators and the data of multiple non-financial indicators.