Enterprise credit risk assessment method and system based on information cross validation

Abstract

The invention relates to the technical field of enterprise credit risk assessment, and discloses an enterprise credit risk assessment method and system based on information cross validation, and the method comprises the steps: constructing an iterative risk index combination according to a risk assessment index and a forward risk index combination, calculating the default rate confidence of the risk assessment index according to a default rate approximation value set, and calculating the default rate confidence of the risk assessment index; constructing a credit risk regression assessment model set according to the default rate confidence set, identifying the current index default rate of the current risk assessment index to obtain a current index default rate set, and performing information cross validation calculation according to the current index default rate set and a target risk regression assessment model. And obtaining an enterprise credit risk assessment value. According to the invention, the evaluation timeliness and the evaluation precision in the enterprise credit risk evaluation process can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise credit risk assessment, and in particular to an enterprise credit risk assessment method and system based on information cross-validation. Background Art

[0002] In the modern business environment, corporate credit risk directly impacts financial institutions' lending decisions, the security of supply chain collaboration, and the effectiveness of market regulation. However, traditional corporate credit risk assessment methods face numerous challenges.

[0003] Traditional corporate credit risk assessment relies on manual analysis, making it difficult to efficiently integrate multi-dimensional data. It also has long assessment cycles and is susceptible to subjective factors, making it unable to meet the needs of real-time risk monitoring. Existing corporate credit risk assessment methods often rely solely on single dimensions, such as financial indicators or administrative penalty records. They lack multi-dimensional validation of multi-source data, making it difficult to identify corporate-related risks and potential credit fraud. Consequently, current corporate credit risk assessment methods suffer from poor timeliness and low accuracy. Summary of the Invention

[0004] The present invention provides an enterprise credit risk assessment method and system based on information cross-validation, the main purpose of which is to improve the assessment timeliness and assessment accuracy in the enterprise credit risk assessment process.

[0005] To achieve the above objectives, the present invention provides a method for assessing corporate credit risk based on information cross-validation, comprising: Obtain multiple risk assessment indicator combinations, and sequentially extract risk assessment indicators from the risk assessment indicator combinations; Identifying a forward risk indicator combination of the risk assessment indicator, and constructing an iterative risk indicator combination based on the risk assessment indicator and the forward risk indicator combination, wherein the forward risk indicator combination refers to a combination of risk assessment indicators that precede the risk assessment indicator in the risk assessment indicator combination; Obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; Calculate the default rate approximation value of the risk assessment indicator according to the forward combination default rate and the iterative combination default rate, and obtain the default rate approximation value set; Calculating the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; A credit risk regression assessment model is constructed based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; Identifying a target risk regression assessment model corresponding to a pre-acquired current risk assessment indicator combination in a credit risk regression assessment model set; Extracting current risk assessment indicators in sequence from the current risk assessment indicator combination, identifying the current indicator default rate of the current risk assessment indicator, and obtaining a current indicator default rate set; Based on the current indicator default rate set and the target risk regression assessment model, information cross-validation calculation is performed to obtain the enterprise credit risk assessment value.

[0006] Optionally, obtaining multiple risk assessment indicator combinations includes: Extracting risk assessment items in sequence from a preset risk assessment item set, wherein the risk assessment items include: industry risk level, enterprise duration, administrative penalty record, judicial litigation status, equity structure stability, and tax credit rating; Setting a risk assessment indicator set according to the risk assessment project to obtain multiple risk assessment indicator sets, wherein the risk assessment indicator set includes: a high risk assessment indicator, a medium risk assessment indicator, and a low risk assessment indicator; The multiple risk assessment indicator sets are combined to obtain multiple risk assessment indicator combinations, wherein the number of risk assessment indicator combinations is .

[0007] Optionally, the step of respectively obtaining the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination includes: Determining whether the risk assessment indicator is a first risk assessment indicator preset in the risk assessment indicator combination, wherein the first risk assessment indicator refers to the first risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is the first risk assessment indicator in the risk assessment indicator combination, Then identify the comprehensive default rate of the pre-acquired current credit risk assessment data; Setting the forward combined default rate to the composite default rate; Taking the risk assessment indicator as an iterative risk indicator combination, identifying an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the iterative assessment enterprise set refers to a set of enterprises belonging to the iterative risk indicator combination; Identify the number of iteratively defaulted enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set, wherein the number of iteratively defaulted enterprises refers to the number of enterprises in the iteratively evaluated enterprise set that have defaulted, and the number of iteratively evaluated enterprises refers to the number of enterprises in the iteratively evaluated enterprise set; Calculating an iterative combination default rate based on the iterative number of defaulting enterprises and the iterative number of evaluated enterprises, wherein the iterative combination default rate refers to the ratio of the iterative number of defaulting enterprises to the iterative number of evaluated enterprises; If the risk assessment indicator is not the first risk assessment indicator in the risk assessment indicator combination, then identifying a forward assessment enterprise set belonging to the forward risk indicator combination and an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the forward assessment enterprise set refers to a set of enterprises belonging to the forward risk indicator combination; Identify the number of forward-defaulted enterprises and the number of forward-assessed enterprises corresponding to the forward-assessed enterprise set, wherein the number of forward-defaulted enterprises refers to the number of enterprises in the forward-assessed enterprise set that have defaulted, and the number of forward-assessed enterprises refers to the number of enterprises in the forward-assessed enterprise set; Identifying the number of iterative defaulting enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set; The forward combination default rate is calculated based on the forward number of defaulting enterprises and the forward number of assessed enterprises, and the iterative combination default rate is calculated based on the iterative number of defaulting enterprises and the iterative number of assessed enterprises, wherein the forward combination default rate refers to the ratio of the forward number of defaulting enterprises to the forward number of assessed enterprises.

[0008] Optionally, identifying the comprehensive default rate of the pre-acquired current credit risk assessment data includes: Identifying the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises in the current credit risk assessment data, wherein the number of comprehensively assessed enterprises refers to the number of enterprises that have undergone enterprise credit risk assessment in the current credit risk assessment data, and the number of comprehensively defaulted enterprises refers to the number of enterprises that have defaulted in the current credit risk assessment data; The comprehensive default rate is calculated based on the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises, wherein the comprehensive default rate refers to the ratio of the number of comprehensively defaulted enterprises to the number of comprehensively assessed enterprises.

[0009] Optionally, the step of calculating the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain a set of default rate approximation values includes: Determining whether the risk assessment indicator is a preset last risk assessment indicator in the risk assessment indicator combination, wherein the last risk assessment indicator refers to the last risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is not the last risk assessment indicator preset in the risk assessment indicator combination, then calculating a default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate, and returning to the above step of sequentially extracting risk assessment indicators from the risk assessment indicator combination, wherein the default rate approximation value refers to the absolute value of the difference between the forward combination default rate and the iterative combination default rate; If the risk assessment indicator is the last risk assessment indicator preset in the risk assessment indicator combination, the default rate approximation value of the risk assessment indicator is calculated based on the forward combination default rate and the iterative combination default rate, and the default rate approximation values are summarized to obtain a default rate approximation value set.

[0010] Optionally, calculating the default rate confidence level of the risk assessment indicator based on the default rate approximation value set to obtain the default rate confidence level set includes: The default rate confidence of the risk assessment indicator is calculated using a pre-built confidence formula to obtain a default rate confidence set, wherein the confidence formula is as follows: in, represents the confidence level of the default rate of the i-th risk assessment indicator, represents the default rate approximation value of the i-th risk assessment indicator, and I represents the number of risk assessment indicators in the risk assessment indicator combination.

[0011] Optionally, identifying the current indicator default rate of the current risk assessment indicator to obtain a current indicator default rate set includes: A currently assessed enterprise set belonging to the current risk assessment indicator in the current credit risk assessment data, wherein the currently assessed enterprise set refers to a collection of enterprises belonging to the current risk assessment indicator; Identify the number of currently defaulting enterprises and the number of currently assessed enterprises corresponding to the currently assessed enterprise set, wherein the number of currently defaulting enterprises refers to the number of enterprises in the currently assessed enterprise set that have defaulted, and the number of currently assessed enterprises refers to the number of enterprises in the currently assessed enterprise set; Calculating the current indicator default rate based on the current number of defaulting enterprises and the current number of assessed enterprises, wherein the current indicator default rate refers to the ratio of the current number of defaulting enterprises to the current number of assessed enterprises; The current indicator default rates corresponding to each current risk assessment indicator are collected to obtain a current indicator default rate set.

[0012] Optionally, performing information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value includes: Identifying a current default rate confidence set corresponding to the target risk regression assessment model; Using the current indicator default rate set as first cross information and the current default rate confidence level set as second cross information; The target risk regression assessment model is used to calculate an enterprise credit risk assessment value based on the first cross-information and the second cross-information.

[0013] Optionally, after performing information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model, the method further includes: Acquire a mapping risk assessment indicator combination set, and sequentially extract mapping risk assessment indicator combinations from the mapping risk assessment indicator combination set; Identifying, in the credit risk regression assessment model set, an associated risk regression assessment model corresponding to the mapped risk assessment indicator combination; Calculating a mapping indicator default rate set and a mapping default rate confidence set of the mapping risk assessment indicator combination using the current credit risk assessment data; Calculating a mapped credit risk assessment value based on the mapped indicator default rate set and the mapped default rate confidence level set using the associated risk regression assessment model; Calculating the mapped comprehensive default rate of the mapped risk assessment indicator combination using the current credit risk assessment data; Calculating a default assessment conversion coefficient between the mapped comprehensive default rate and the mapped credit risk assessment value to obtain a default assessment conversion coefficient set, wherein the default assessment conversion coefficient refers to a ratio of the mapped comprehensive default rate to the mapped risk assessment value; Calculate the default assessment conversion coefficient mean of the default assessment conversion coefficient set, and use the default assessment conversion coefficient mean as the default assessment conversion coefficient.

[0014] To achieve the above objectives, the present invention further provides an enterprise credit risk assessment system based on information cross-validation, comprising: A default rate confidence calculation module is used to obtain multiple groups of risk assessment indicator combinations, extract risk assessment indicators in the risk assessment indicator combinations in sequence; identify forward risk indicator combinations of the risk assessment indicators, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combinations, wherein the forward risk indicator combination refers to a combination of risk assessment indicators located before the risk assessment indicators in the risk assessment indicator combination; obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; calculate the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain a default rate approximation value set; calculate the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; The credit risk regression assessment model construction module is used to construct a credit risk regression assessment model based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; A target risk regression assessment model identification module is used to identify the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination in the credit risk regression assessment model set; The enterprise credit risk assessment value calculation module is used to extract the current risk assessment indicators in the current risk assessment indicator combination in sequence, identify the current indicator default rate of the current risk assessment indicator, and obtain the current indicator default rate set; perform information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value.

[0015] In order to solve the above problem, the present invention further provides an electronic device, comprising: A memory storing at least one instruction; and a processor executing the instruction stored in the memory to implement the above-mentioned enterprise credit risk assessment method based on information cross-validation.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned enterprise credit risk assessment method based on information cross-validation.

[0017] In order to solve the problems described in the background technology, the present invention calculates the enterprise credit risk assessment value through a credit risk regression assessment model. Since the credit risk regression assessment model is constructed by a default rate confidence set, it is necessary to first calculate the default rate confidence set. Since the default rate confidence is calculated by a default rate approximation value set, and the default rate approximation value set represents the absolute value of the difference between the forward combination default rate of each forward risk indicator combination and the iterative risk indicator combination and the iterative combination default rate, it is necessary to first obtain multiple groups of risk assessment indicator combinations, and extract risk assessment indicators in the risk assessment indicator combination in sequence. In order to obtain each forward risk indicator combination and the iterative risk indicator combination, it is necessary to identify the forward risk indicator combination of the risk assessment indicators in sequence, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combination. Then, the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination can be obtained respectively, and then the forward combination default rate and the iterative combination default rate can be extracted based on the forward combination default rate. The default rate approximation value of the risk assessment indicator is calculated by the approximate rate of the approximate rate of the risk assessment indicator, and the default rate approximation value set is obtained. Since the default rate confidence refers to the default rate approximation value ratio of the risk assessment indicator, the default rate confidence of the risk assessment indicator can be calculated according to the default rate approximation value set to obtain the default rate confidence set. Finally, a credit risk regression assessment model is constructed according to the default rate confidence set to obtain a credit risk regression assessment model set. Since each risk assessment indicator combination corresponds to a credit risk regression assessment model, the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination is identified in the credit risk regression assessment model set. At this time, the current risk assessment indicator can be extracted in the current risk assessment indicator combination in sequence, and the current indicator default rate of the current risk assessment indicator is identified to obtain the current indicator default rate set. Finally, information cross-validation calculation is performed according to the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value. Therefore, the present invention can improve the assessment timeliness and assessment accuracy in the enterprise credit risk assessment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a method for assessing corporate credit risk based on information cross-validation provided by one embodiment of the present invention; Figure 2 A functional module diagram of an enterprise credit risk assessment system based on information cross-validation provided by one embodiment of the present invention; Figure 3 A schematic structural diagram of an electronic device for implementing the enterprise credit risk assessment method based on information cross-validation provided by an embodiment of the present invention.

[0019] Description of reference numerals: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0020] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0022] The present application provides a method for assessing corporate credit risk based on information cross-validation. The method can be performed by at least one of a server, a terminal, or other electronic device capable of executing the method provided by the present application. In other words, the method can be performed by software or hardware installed on a terminal or server device, where the software can be a blockchain platform. The server can include, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0023] Reference Figure 1 FIG. 1 is a flow chart of a method for assessing corporate credit risk based on information cross-validation according to an embodiment of the present invention. In this embodiment, the method for assessing corporate credit risk based on information cross-validation includes: S1. Obtain multiple risk assessment indicator combinations, and extract risk assessment indicators from the risk assessment indicator combinations in sequence.

[0024] It can be explained that the multiple sets of risk assessment indicator combinations refer to the combination of multiple sets of risk assessment indicators, and the risk assessment indicators refer to indicators used to assess corporate credit risks. The risk assessment indicator combinations can be: high-risk industries, long corporate survival time, no administrative penalties, ordinary litigation, stable equity structure, and high tax credit; high-risk industries, short corporate survival time, minor administrative penalties, no litigation, general equity structure, and low tax credit; low-risk industries, medium corporate survival time, minor administrative penalties, ordinary litigation, stable equity structure, and general tax credit, etc.

[0025] In an embodiment of the present invention, obtaining multiple risk assessment indicator combinations includes: Extracting risk assessment items in sequence from a preset risk assessment item set, wherein the risk assessment items include: industry risk level, enterprise duration, administrative penalty record, judicial litigation status, equity structure stability, and tax credit rating; Setting a risk assessment indicator set according to the risk assessment project to obtain multiple risk assessment indicator sets, wherein the risk assessment indicator set includes: a high risk assessment indicator, a medium risk assessment indicator, and a low risk assessment indicator; The multiple risk assessment indicator sets are combined to obtain multiple risk assessment indicator combinations, wherein the number of risk assessment indicator combinations is .

[0026] It can be understood that the risk assessment project refers to the assessment project to which the risk assessment indicator belongs, and the risk assessment indicator set refers to a set of risk assessment indicators set according to the risk assessment project. The high-risk assessment indicator refers to an indicator with a higher corporate credit risk, the medium-risk assessment indicator refers to an indicator with a general corporate credit risk, and the low-risk assessment indicator refers to an indicator with a lower corporate credit risk. For example, when the risk assessment item is the industry risk level, the high-risk assessment indicator, the medium-risk assessment indicator and the low-risk assessment indicator can be high-risk industries (for example, real estate industry, financial industry), medium-risk industries (for example, retail industry, manufacturing industry) and low-risk industries (for example, medical industry, public utilities industry), respectively; when the risk assessment item is the enterprise survival time, the high-risk assessment indicator, the medium-risk assessment indicator and the low-risk assessment indicator can be long enterprise survival time (for example, more than 10 years), medium enterprise survival time (for example, 3-10 years) and short enterprise survival time (for example, less than 3 years), respectively; when the risk assessment item is the administrative penalty record, the high-risk assessment indicator, the medium-risk assessment indicator and the low-risk assessment indicator can be serious administrative penalties, minor administrative penalties and no administrative penalties, respectively.

[0027] Furthermore, the risk assessment indicator combination refers to the risk assessment indicator combination obtained by combining the risk assessment indicators of each risk assessment project. For example, the risk assessment indicator combination can be high-risk industry, long enterprise survival time, no administrative penalties, ordinary litigation, stable equity structure, and high tax credit. Since each risk assessment project has 3 risk assessment indicators, and there are 6 risk assessment projects, the number of risk assessment indicator combinations is .

[0028] S2. Identify the forward risk indicator combination of the risk assessment indicators, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combination.

[0029] In detail, the forward risk indicator combination refers to a combination of risk assessment indicators that are located in front of the risk assessment indicators in the risk assessment indicator combination. For example: when the risk assessment indicator is no administrative penalty, the forward risk indicator combination can be high-risk industry and long enterprise survival time; when the risk assessment indicator is stable equity structure, the forward risk indicator combination can be high-risk industry, long enterprise survival time, no administrative penalty, and ordinary litigation. The iterative risk indicator combination refers to the indicator combination of the risk assessment indicator and the forward risk indicator combination. For example: when the risk assessment indicator is no administrative penalty, the forward risk indicator combination can be high-risk industry and long enterprise survival time, and the iterative risk indicator combination can be high-risk industry, long enterprise survival time, and no administrative penalty.

[0030] S3. Obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively.

[0031] Furthermore, the forward combination default rate refers to the default rate of enterprises belonging to the forward risk indicator combination. The default rate refers to the proportion of enterprises that default. For example, if the number of enterprises in high-risk industries with long enterprise life spans that have defaulted on loan contracts with banks is 100 in the current credit risk assessment data, and the total number of enterprises in high-risk industries with long enterprise life spans is 1,000, then the forward combination default rate is 10%. The current credit risk assessment data refers to the currently recorded credit risk performance data of each enterprise in different industries. The credit risk performance data includes the specific risk assessment indicator set corresponding to the risk assessment project set for each enterprise. The iterative combination default rate refers to the default rate of the enterprises belonging to the iterative risk indicator combination.

[0032] In the embodiment of the present invention, the step of respectively obtaining the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination includes: Determining whether the risk assessment indicator is a first risk assessment indicator preset in the risk assessment indicator combination, wherein the first risk assessment indicator refers to the first risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is the first risk assessment indicator in the risk assessment indicator combination, identifying the comprehensive default rate of the pre-acquired current credit risk assessment data; Setting the forward combined default rate to the composite default rate; Taking the risk assessment indicator as an iterative risk indicator combination, identifying an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the iterative assessment enterprise set refers to a set of enterprises belonging to the iterative risk indicator combination; Identify the number of iteratively defaulted enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set, wherein the number of iteratively defaulted enterprises refers to the number of enterprises in the iteratively evaluated enterprise set that have defaulted, and the number of iteratively evaluated enterprises refers to the number of enterprises in the iteratively evaluated enterprise set; Calculating an iterative combination default rate based on the iterative number of defaulting enterprises and the iterative number of evaluated enterprises, wherein the iterative combination default rate refers to the ratio of the iterative number of defaulting enterprises to the iterative number of evaluated enterprises; If the risk assessment indicator is not the first risk assessment indicator in the risk assessment indicator combination, then identifying a forward assessment enterprise set belonging to the forward risk indicator combination and an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the forward assessment enterprise set refers to a set of enterprises belonging to the forward risk indicator combination; Identify the number of forward-defaulted enterprises and the number of forward-assessed enterprises corresponding to the forward-assessed enterprise set, wherein the number of forward-defaulted enterprises refers to the number of enterprises in the forward-assessed enterprise set that have defaulted, and the number of forward-assessed enterprises refers to the number of enterprises in the forward-assessed enterprise set; Identifying the number of iterative defaulting enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set; The forward combination default rate is calculated based on the forward number of defaulting enterprises and the forward number of assessed enterprises, and the iterative combination default rate is calculated based on the iterative number of defaulting enterprises and the iterative number of assessed enterprises, wherein the forward combination default rate refers to the ratio of the forward number of defaulting enterprises to the forward number of assessed enterprises.

[0033] It is understood that the comprehensive default rate refers to the percentage of enterprises experiencing default within the current credit risk assessment data. When the iterative risk indicator combination is high-risk industry, long enterprise duration, and no administrative penalties, the iteratively assessed enterprise set refers to the set of enterprises within the current credit risk assessment data that fall within these categories. The iterative combination default rate refers to the percentage of enterprises within the iteratively assessed enterprise set that have experienced default.

[0034] It is understood that when the forward risk indicator combination is high-risk industry and long enterprise life, the forward assessment enterprise set refers to the set of enterprises belonging to high-risk industries and long enterprise life in the current credit risk assessment data. The forward combination default rate represents the proportion of enterprises in the forward assessment enterprise set that have defaulted, and the iterative combination default rate represents the proportion of enterprises in the iterative assessment enterprise set that have defaulted.

[0035] Furthermore, the identifying of the comprehensive default rate of the pre-acquired current credit risk assessment data includes: Identifying the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises in the current credit risk assessment data, wherein the number of comprehensively assessed enterprises refers to the number of enterprises that have undergone enterprise credit risk assessment in the current credit risk assessment data, and the number of comprehensively defaulted enterprises refers to the number of enterprises that have defaulted in the current credit risk assessment data; The comprehensive default rate is calculated based on the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises, wherein the comprehensive default rate refers to the ratio of the number of comprehensively defaulted enterprises to the number of comprehensively assessed enterprises.

[0036] S4. Calculate the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain a default rate approximation value set.

[0037] It is understood that the default rate approximation value refers to the value by which the iterative combination default rate approaches the target default rate corresponding to the risk assessment indicator combination compared to the forward combination default rate. For example, if the target default rate corresponding to the risk assessment indicator combination is 20%, the forward combination default rate is 32%, and the iterative combination default rate is 30%, then the default rate approximation value is 2%. The target default rate refers to the default ratio of enterprises belonging to the risk assessment indicator combination. For example, if the number of enterprises belonging to the risk assessment indicator combination in the current credit risk assessment data is 500, and 100 of them default, then the target default rate is 20%.

[0038] In the embodiment of the present invention, the method of calculating the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain the default rate approximation value set includes: Determining whether the risk assessment indicator is a preset last risk assessment indicator in the risk assessment indicator combination, wherein the last risk assessment indicator refers to the last risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is not the last risk assessment indicator preset in the risk assessment indicator combination, then calculating a default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate, and returning to the above step of sequentially extracting risk assessment indicators from the risk assessment indicator combination, wherein the default rate approximation value refers to the absolute value of the difference between the forward combination default rate and the iterative combination default rate; If the risk assessment indicator is the last risk assessment indicator preset in the risk assessment indicator combination, the default rate approximation value of the risk assessment indicator is calculated based on the forward combination default rate and the iterative combination default rate, and the default rate approximation values are summarized to obtain a default rate approximation value set.

[0039] It can be understood that when the risk assessment indicator is the last risk assessment indicator, it indicates that the default rate approximation value calculated by the forward combination default rate and the iterative combination default rate is the last default rate approximation value. Therefore, the default rate approximation values can be summarized to obtain a default rate approximation value set.

[0040] S5. Calculate the default rate confidence level of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence level set.

[0041] Furthermore, the default rate confidence refers to the percentage of the default rate approximation value of the risk assessment indicator. For example, when the default rate approximation value set is 18%, 6%, 7%, 5%, 3%, and 2%, the default rate confidence of each risk assessment indicator is respectively 、 、 、 、 、 The default rate confidence set refers to the default rate confidence set of each risk assessment indicator.

[0042] In the embodiment of the present invention, the step of calculating the default rate confidence level of the risk assessment indicator based on the default rate approximation value set to obtain the default rate confidence level set includes: The default rate confidence of the risk assessment indicator is calculated using a pre-built confidence formula to obtain a default rate confidence set, wherein the confidence formula is as follows: in, represents the confidence level of the default rate of the i-th risk assessment indicator, represents the default rate approximation value of the i-th risk assessment indicator, and I represents the number of risk assessment indicators in the risk assessment indicator combination.

[0043] S6. Construct a credit risk regression assessment model based on the default rate confidence set to obtain a credit risk regression assessment model set.

[0044] It is understood that the credit risk regression assessment model refers to a credit risk model used to assess the credit risk of an enterprise belonging to a specific risk assessment indicator combination. The credit risk regression assessment model set refers to a collection of credit risk regression assessment models corresponding to each risk assessment indicator combination.

[0045] In detail, the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, Represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination.

[0046] S7. Identify the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination in the credit risk regression assessment model set.

[0047] It can be explained that the current risk assessment indicator combination refers to the risk assessment indicator combination of the enterprise that currently needs to undergo enterprise credit assessment. The target risk regression assessment model refers to the credit risk regression assessment model corresponding to the current risk assessment indicator combination.

[0048] S8. Extract the current risk assessment indicators in the current risk assessment indicator combination in sequence, identify the current indicator default rate of the current risk assessment indicator, and obtain a current indicator default rate set.

[0049] It is explained that the current risk assessment indicator refers to the risk assessment indicator in the current risk assessment indicator combination. The current indicator default rate refers to the proportion of enterprises that have defaulted among all enterprises belonging to the current risk assessment indicator in the current credit risk assessment data. For example, if there are 1,000 enterprises belonging to the current risk assessment indicator, among which 10 have defaulted, the current indicator default rate is 1%.

[0050] In the embodiment of the present invention, the identifying the current indicator default rate of the current risk assessment indicator to obtain the current indicator default rate set includes: A currently assessed enterprise set belonging to the current risk assessment indicator in the current credit risk assessment data, wherein the currently assessed enterprise set refers to a collection of enterprises belonging to the current risk assessment indicator; Identify the number of currently defaulting enterprises and the number of currently assessed enterprises corresponding to the currently assessed enterprise set, wherein the number of currently defaulting enterprises refers to the number of enterprises in the currently assessed enterprise set that have defaulted, and the number of currently assessed enterprises refers to the number of enterprises in the currently assessed enterprise set; Calculating the current indicator default rate based on the current number of defaulting enterprises and the current number of assessed enterprises, wherein the current indicator default rate refers to the ratio of the current number of defaulting enterprises to the current number of assessed enterprises; The current indicator default rates corresponding to each current risk assessment indicator are collected to obtain a current indicator default rate set.

[0051] S9. Perform information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value.

[0052] It is understood that the information cross-validation calculation refers to performing an information cross-validation calculation on the current indicator default rate set and the current default confidence level set to calculate the credit risk of the enterprise currently requiring credit risk assessment. The current indicator default rate refers to the overall default rate of the current risk assessment indicator, while the current default confidence level refers to the degree of impact of the current risk assessment indicator on the default rate of the enterprises belonging to the current risk assessment indicator combination. Therefore, the two belong to different measurement dimensions and therefore constitute information cross-validation of different dimensions.

[0053] In the embodiment of the present invention, the information cross-validation calculation is performed based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value, including: Identifying a current default rate confidence set corresponding to the target risk regression assessment model; Using the current indicator default rate set as first cross information and the current default rate confidence level set as second cross information; The target risk regression assessment model is used to calculate an enterprise credit risk assessment value based on the first cross-information and the second cross-information.

[0054] It is understandable that the current default rate confidence set refers to each default rate confidence set in the target risk regression assessment model, for example: 、 、 、 、 、 The first cross-information refers to the credit risk assessment information of the first dimension, and the second cross-information refers to the credit risk assessment information of the second dimension.

[0055] In an embodiment of the present invention, after performing information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model, the method further includes: Acquire a mapping risk assessment indicator combination set, and sequentially extract mapping risk assessment indicator combinations from the mapping risk assessment indicator combination set; Identifying, in the credit risk regression assessment model set, an associated risk regression assessment model corresponding to the mapped risk assessment indicator combination; Calculating a mapping indicator default rate set and a mapping default rate confidence set of the mapping risk assessment indicator combination using the current credit risk assessment data; Calculating a mapped credit risk assessment value based on the mapped indicator default rate set and the mapped default rate confidence level set using the associated risk regression assessment model; Calculating the mapped comprehensive default rate of the mapped risk assessment indicator combination using the current credit risk assessment data; Calculating a default assessment conversion coefficient between the mapped comprehensive default rate and the mapped credit risk assessment value to obtain a default assessment conversion coefficient set, wherein the default assessment conversion coefficient refers to a ratio of the mapped comprehensive default rate to the mapped risk assessment value; Calculate the default assessment conversion coefficient mean of the default assessment conversion coefficient set, and use the default assessment conversion coefficient mean as the default assessment conversion coefficient.

[0056] It is understood that the mapped risk assessment indicator combination set refers to the set of risk assessment indicator combinations used to perform the mapping calculation between an enterprise's credit risk assessment value and default rate. The mapped risk assessment indicator combination refers to the risk assessment indicator combination used to perform the mapping calculation between an enterprise's credit risk assessment value and default rate. The associated risk regression assessment model refers to the credit risk regression assessment model corresponding to the mapped risk assessment indicator combination. The mapped indicator default rate set refers to the set of comprehensive default rates for each mapped risk assessment indicator in the mapped risk assessment indicator combination. The mapped default rate confidence set refers to the set of default rate confidence levels for each mapped risk assessment indicator in the mapped risk assessment indicator combination. The mapped credit risk assessment value refers to the enterprise credit risk assessment value corresponding to the mapped risk assessment indicator combination. The mapped comprehensive default rate refers to the percentage of enterprises that have defaulted among all enterprises belonging to the mapped risk assessment indicator combination in the current credit risk assessment data. The default assessment conversion coefficient mean refers to the average value of the default assessment conversion coefficient set. The default assessment conversion coefficient refers to the conversion coefficient between an enterprise's credit risk assessment value and its assessed default rate. After the enterprise credit risk assessment value is calculated, the user does not know the risk level corresponding to the enterprise credit risk assessment value. Therefore, the mapped comprehensive default rate can be used to convert the mapped credit risk assessment value into a default probability.

[0057] In order to solve the problems described in the background technology, the present invention calculates the enterprise credit risk assessment value through a credit risk regression assessment model. Since the credit risk regression assessment model is constructed by a default rate confidence set, it is necessary to first calculate the default rate confidence set. Since the default rate confidence is calculated by a default rate approximation value set, and the default rate approximation value set represents the absolute value of the difference between the forward combination default rate of each forward risk indicator combination and the iterative risk indicator combination and the iterative combination default rate, it is necessary to first obtain multiple groups of risk assessment indicator combinations, and extract risk assessment indicators in the risk assessment indicator combination in sequence. In order to obtain each forward risk indicator combination and the iterative risk indicator combination, it is necessary to identify the forward risk indicator combination of the risk assessment indicators in sequence, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combination. Then, the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination can be obtained respectively, and then the forward combination default rate and the iterative combination default rate can be extracted based on the forward combination default rate. The default rate approximation value of the risk assessment indicator is calculated by the approximate rate of the approximate rate of the risk assessment indicator, and the default rate approximation value set is obtained. Since the default rate confidence refers to the default rate approximation value ratio of the risk assessment indicator, the default rate confidence of the risk assessment indicator can be calculated according to the default rate approximation value set to obtain the default rate confidence set. Finally, a credit risk regression assessment model is constructed according to the default rate confidence set to obtain a credit risk regression assessment model set. Since each risk assessment indicator combination corresponds to a credit risk regression assessment model, the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination is identified in the credit risk regression assessment model set. At this time, the current risk assessment indicator can be extracted in the current risk assessment indicator combination in sequence, and the current indicator default rate of the current risk assessment indicator is identified to obtain the current indicator default rate set. Finally, information cross-validation calculation is performed according to the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value. Therefore, the present invention can improve the assessment timeliness and assessment accuracy in the enterprise credit risk assessment process.

[0058] like Figure 2 , which is a functional module diagram of an enterprise credit risk assessment system based on information cross-validation provided by one embodiment of the present invention.

[0059] The enterprise credit risk assessment system 100 based on information cross-validation described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the enterprise credit risk assessment system 100 based on information cross-validation can include a default rate confidence calculation module 101, a credit risk regression assessment model construction module 102, a target risk regression assessment model identification module 103, and an enterprise credit risk assessment value calculation module 104. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.

[0060] The default rate confidence calculation module 101 is used to obtain multiple groups of risk assessment indicator combinations, extract risk assessment indicators in the risk assessment indicator combinations in sequence; identify forward risk indicator combinations of the risk assessment indicators, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combinations, wherein the forward risk indicator combination refers to a combination of risk assessment indicators located before the risk assessment indicators in the risk assessment indicator combination; obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; calculate the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain a default rate approximation value set; calculate the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; The credit risk regression assessment model construction module 102 is used to construct a credit risk regression assessment model based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; The target risk regression assessment model identification module 103 is used to identify the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination in the credit risk regression assessment model set; The enterprise credit risk assessment value calculation module 104 is used to sequentially extract current risk assessment indicators from the current risk assessment indicator combination, identify the current indicator default rate of the current risk assessment indicator, and obtain a current indicator default rate set; perform information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value.

[0061] In detail, each module in the enterprise credit risk assessment system 100 based on information cross-validation in the embodiment of the present invention adopts the same method as above when in use. Figure 1 The technical means are the same as the enterprise credit risk assessment method based on information cross-validation described in , and can produce the same technical effects, so I will not go into details here.

[0062] like Figure 3FIG. 1 is a schematic diagram of the structure of an electronic device for implementing an enterprise credit risk assessment method based on information cross-validation provided by an embodiment of the present invention.

[0063] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an enterprise credit risk assessment method program based on information cross-validation.

[0064] The memory 11 includes at least one type of readable storage medium, including flash memory, a removable hard drive, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a removable hard drive of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in removable hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of a corporate credit risk assessment method based on information cross-validation, but also to temporarily store data that has been output or is about to be output.

[0065] In some embodiments, the processor 10 may be comprised of an integrated circuit, such as a single packaged integrated circuit or a combination of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (control unit) of the electronic device, connecting the various components of the electronic device using various interfaces and circuits. It executes programs or modules stored in the memory 11 (e.g., a program for an enterprise credit risk assessment method based on information cross-validation) and accesses data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0066] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0067] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0068] For example, although not shown, the electronic device 1 may further include a power supply (e.g., a battery) to power various components. Preferably, the power supply may be logically connected to the at least one processor 10 via a power management device, thereby enabling functions such as charge management, discharge management, and power consumption management via the power management device. The power supply may further include any components such as one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0069] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0070] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, and is used to display information processed by the electronic device 1 and to display a visual user interface.

[0071] The enterprise credit risk assessment method program based on information cross-validation stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following: Obtain multiple risk assessment indicator combinations, and sequentially extract risk assessment indicators from the risk assessment indicator combinations; Identifying a forward risk indicator combination of the risk assessment indicator, and constructing an iterative risk indicator combination based on the risk assessment indicator and the forward risk indicator combination, wherein the forward risk indicator combination refers to a combination of risk assessment indicators that precede the risk assessment indicator in the risk assessment indicator combination; Obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; Calculate the default rate approximation value of the risk assessment indicator according to the forward combination default rate and the iterative combination default rate, and obtain the default rate approximation value set; Calculating the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; A credit risk regression assessment model is constructed based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; Identifying a target risk regression assessment model corresponding to a pre-acquired current risk assessment indicator combination in a credit risk regression assessment model set; Extracting current risk assessment indicators in sequence from the current risk assessment indicator combination, identifying the current indicator default rate of the current risk assessment indicator, and obtaining a current indicator default rate set; Based on the current indicator default rate set and the target risk regression assessment model, information cross-validation calculation is performed to obtain the enterprise credit risk assessment value.

[0072] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0073] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0074] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement: Obtain multiple risk assessment indicator combinations, and sequentially extract risk assessment indicators from the risk assessment indicator combinations; Identifying a forward risk indicator combination of the risk assessment indicator, and constructing an iterative risk indicator combination based on the risk assessment indicator and the forward risk indicator combination, wherein the forward risk indicator combination refers to a combination of risk assessment indicators that precede the risk assessment indicator in the risk assessment indicator combination; Obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; Calculate the default rate approximation value of the risk assessment indicator according to the forward combination default rate and the iterative combination default rate, and obtain the default rate approximation value set; Calculating the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; A credit risk regression assessment model is constructed based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; Identifying a target risk regression assessment model corresponding to a pre-acquired current risk assessment indicator combination in a credit risk regression assessment model set; Extracting current risk assessment indicators in sequence from the current risk assessment indicator combination, identifying the current indicator default rate of the current risk assessment indicator, and obtaining a current indicator default rate set; Based on the current indicator default rate set and the target risk regression assessment model, information cross-validation calculation is performed to obtain the enterprise credit risk assessment value.

[0075] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0076] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0077] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0078] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for assessing corporate credit risk based on information cross-validation, characterized in that: The method comprises: Obtain multiple risk assessment indicator combinations, and sequentially extract risk assessment indicators from the risk assessment indicator combinations; Identifying a forward risk indicator combination of the risk assessment indicator, and constructing an iterative risk indicator combination based on the risk assessment indicator and the forward risk indicator combination, wherein the forward risk indicator combination refers to a combination of risk assessment indicators that precede the risk assessment indicator in the risk assessment indicator combination; Obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; Calculate the default rate approximation value of the risk assessment indicator according to the forward combination default rate and the iterative combination default rate, and obtain the default rate approximation value set; Calculating the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; A credit risk regression assessment model is constructed based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; Identifying a target risk regression assessment model corresponding to a pre-acquired current risk assessment indicator combination in a credit risk regression assessment model set; Extracting current risk assessment indicators in sequence from the current risk assessment indicator combination, identifying the current indicator default rate of the current risk assessment indicator, and obtaining a current indicator default rate set; Based on the current indicator default rate set and the target risk regression assessment model, information cross-validation calculation is performed to obtain the enterprise credit risk assessment value.

2. The enterprise credit risk assessment method based on information cross-validation according to claim 1, characterized in that: The obtaining of multiple risk assessment indicator combinations includes: Extracting risk assessment items in sequence from a preset risk assessment item set, wherein the risk assessment items include: industry risk level, enterprise duration, administrative penalty record, judicial litigation status, equity structure stability, and tax credit rating; Setting a risk assessment indicator set according to the risk assessment project to obtain multiple risk assessment indicator sets, wherein the risk assessment indicator set includes: a high risk assessment indicator, a medium risk assessment indicator, and a low risk assessment indicator; The multiple risk assessment indicator sets are combined to obtain multiple risk assessment indicator combinations, wherein the number of risk assessment indicator combinations is .

3. The enterprise credit risk assessment method based on information cross-validation according to claim 2, characterized in that: The step of respectively obtaining the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination includes: Determining whether the risk assessment indicator is a first risk assessment indicator preset in the risk assessment indicator combination, wherein the first risk assessment indicator refers to the first risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is the first risk assessment indicator in the risk assessment indicator combination, identifying the comprehensive default rate of the pre-acquired current credit risk assessment data; Setting the forward combined default rate to the composite default rate; Taking the risk assessment indicator as an iterative risk indicator combination, identifying an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the iterative assessment enterprise set refers to a set of enterprises belonging to the iterative risk indicator combination; Identify the number of iteratively defaulted enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set, wherein the number of iteratively defaulted enterprises refers to the number of enterprises in the iteratively evaluated enterprise set that have defaulted, and the number of iteratively evaluated enterprises refers to the number of enterprises in the iteratively evaluated enterprise set; Calculating an iterative combination default rate based on the iterative number of defaulting enterprises and the iterative number of evaluated enterprises, wherein the iterative combination default rate refers to the ratio of the iterative number of defaulting enterprises to the iterative number of evaluated enterprises; If the risk assessment indicator is not the first risk assessment indicator in the risk assessment indicator combination, then identifying a forward assessment enterprise set belonging to the forward risk indicator combination and an iterative assessment enterprise set belonging to the iterative risk indicator combination in the current credit risk assessment data, wherein the forward assessment enterprise set refers to a set of enterprises belonging to the forward risk indicator combination; Identify the number of forward-defaulted enterprises and the number of forward-assessed enterprises corresponding to the forward-assessed enterprise set, wherein the number of forward-defaulted enterprises refers to the number of enterprises in the forward-assessed enterprise set that have defaulted, and the number of forward-assessed enterprises refers to the number of enterprises in the forward-assessed enterprise set; Identifying the number of iterative defaulting enterprises and the number of iteratively evaluated enterprises corresponding to the iteratively evaluated enterprise set; The forward combination default rate is calculated based on the forward number of defaulting enterprises and the forward number of assessed enterprises, and the iterative combination default rate is calculated based on the iterative number of defaulting enterprises and the iterative number of assessed enterprises, wherein the forward combination default rate refers to the ratio of the forward number of defaulting enterprises to the forward number of assessed enterprises.

4. The enterprise credit risk assessment method based on information cross-validation according to claim 3, characterized in that: The identifying of the comprehensive default rate of the pre-acquired current credit risk assessment data includes: Identifying the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises in the current credit risk assessment data, wherein the number of comprehensively assessed enterprises refers to the number of enterprises that have undergone enterprise credit risk assessment in the current credit risk assessment data, and the number of comprehensively defaulted enterprises refers to the number of enterprises that have defaulted in the current credit risk assessment data; The comprehensive default rate is calculated based on the number of comprehensively assessed enterprises and the number of comprehensively defaulted enterprises, wherein the comprehensive default rate refers to the ratio of the number of comprehensively defaulted enterprises to the number of comprehensively assessed enterprises.

5. The enterprise credit risk assessment method based on information cross-validation according to claim 4, characterized in that: The default rate approximation value of the risk assessment indicator is calculated based on the forward combination default rate and the iterative combination default rate to obtain a default rate approximation value set, including: Determining whether the risk assessment indicator is a preset last risk assessment indicator in the risk assessment indicator combination, wherein the last risk assessment indicator refers to the last risk assessment indicator in the risk assessment indicator combination; If the risk assessment indicator is not the last risk assessment indicator preset in the risk assessment indicator combination, then calculating a default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate, and returning to the above step of sequentially extracting risk assessment indicators from the risk assessment indicator combination, wherein the default rate approximation value refers to the absolute value of the difference between the forward combination default rate and the iterative combination default rate; If the risk assessment indicator is the last risk assessment indicator preset in the risk assessment indicator combination, the default rate approximation value of the risk assessment indicator is calculated based on the forward combination default rate and the iterative combination default rate, and the default rate approximation values are summarized to obtain a default rate approximation value set.

6. The enterprise credit risk assessment method based on information cross-validation according to claim 5, characterized in that: The default rate confidence level of the risk assessment indicator is calculated based on the default rate approximation value set to obtain the default rate confidence level set, including: The default rate confidence of the risk assessment indicator is calculated using a pre-built confidence formula to obtain a default rate confidence set, wherein the confidence formula is as follows: in, represents the confidence level of the default rate of the i-th risk assessment indicator, represents the default rate approximation value of the i-th risk assessment indicator, and I represents the number of risk assessment indicators in the risk assessment indicator combination.

7. The enterprise credit risk assessment method based on information cross-validation according to claim 6, characterized in that: The identifying of the current indicator default rate of the current risk assessment indicator to obtain a current indicator default rate set includes: A currently assessed enterprise set belonging to the current risk assessment indicator in the current credit risk assessment data, wherein the currently assessed enterprise set refers to a collection of enterprises belonging to the current risk assessment indicator; Identify the number of currently defaulting enterprises and the number of currently assessed enterprises corresponding to the currently assessed enterprise set, wherein the number of currently defaulting enterprises refers to the number of enterprises in the currently assessed enterprise set that have defaulted, and the number of currently assessed enterprises refers to the number of enterprises in the currently assessed enterprise set; Calculating the current indicator default rate based on the current number of defaulting enterprises and the current number of assessed enterprises, wherein the current indicator default rate refers to the ratio of the current number of defaulting enterprises to the current number of assessed enterprises; The current indicator default rates corresponding to each current risk assessment indicator are collected to obtain a current indicator default rate set.

8. The enterprise credit risk assessment method based on information cross-validation according to claim 7, characterized in that: The information cross-validation calculation is performed based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value, including: Identifying a current default rate confidence set corresponding to the target risk regression assessment model; Using the current indicator default rate set as first cross information and the current default rate confidence level set as second cross information; The target risk regression assessment model is used to calculate an enterprise credit risk assessment value based on the first cross-information and the second cross-information.

9. The enterprise credit risk assessment method based on information cross-validation according to claim 8, characterized in that: After performing information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model, the method further includes: Acquire a mapping risk assessment indicator combination set, and sequentially extract mapping risk assessment indicator combinations from the mapping risk assessment indicator combination set; Identifying, in the credit risk regression assessment model set, an associated risk regression assessment model corresponding to the mapped risk assessment indicator combination; Calculating a mapping indicator default rate set and a mapping default rate confidence set of the mapping risk assessment indicator combination using the current credit risk assessment data; Calculating a mapped credit risk assessment value based on the mapped indicator default rate set and the mapped default rate confidence level set using the associated risk regression assessment model; Calculating the mapped comprehensive default rate of the mapped risk assessment indicator combination using the current credit risk assessment data; Calculating a default assessment conversion coefficient between the mapped comprehensive default rate and the mapped credit risk assessment value to obtain a default assessment conversion coefficient set, wherein the default assessment conversion coefficient refers to a ratio of the mapped comprehensive default rate to the mapped risk assessment value; Calculate the default assessment conversion coefficient mean of the default assessment conversion coefficient set, and use the default assessment conversion coefficient mean as the default assessment conversion coefficient.

10. An enterprise credit risk assessment system based on information cross-validation, characterized in that: The system comprises: A default rate confidence calculation module is used to obtain multiple groups of risk assessment indicator combinations, extract risk assessment indicators in the risk assessment indicator combinations in sequence; identify forward risk indicator combinations of the risk assessment indicators, and construct an iterative risk indicator combination based on the risk assessment indicators and the forward risk indicator combinations, wherein the forward risk indicator combination refers to a combination of risk assessment indicators located before the risk assessment indicators in the risk assessment indicator combination; obtain the forward combination default rate and the iterative combination default rate of the forward risk indicator combination and the iterative risk indicator combination respectively; calculate the default rate approximation value of the risk assessment indicator based on the forward combination default rate and the iterative combination default rate to obtain a default rate approximation value set; calculate the default rate confidence of the risk assessment indicator based on the default rate approximation value set to obtain a default rate confidence set, wherein the default rate confidence refers to the proportion of the default rate approximation value of the risk assessment indicator; The credit risk regression assessment model construction module is used to construct a credit risk regression assessment model based on the default rate confidence set to obtain a credit risk regression assessment model set, wherein the credit risk regression assessment model is as follows: in, represents the credit risk regression assessment value, represents the confidence level of the first default rate, represents the default rate of the first risk assessment indicator in the risk assessment indicator combination, represents the confidence level of the nth default rate, represents the default rate of the nth risk assessment indicator in the risk assessment indicator combination; A target risk regression assessment model identification module is used to identify the target risk regression assessment model corresponding to the pre-acquired current risk assessment indicator combination in the credit risk regression assessment model set; The enterprise credit risk assessment value calculation module is used to extract the current risk assessment indicators in the current risk assessment indicator combination in sequence, identify the current indicator default rate of the current risk assessment indicator, and obtain the current indicator default rate set; perform information cross-validation calculation based on the current indicator default rate set and the target risk regression assessment model to obtain the enterprise credit risk assessment value.

Images