CN113506173A - Credit risk assessment method and related equipment thereof - Google Patents
Credit risk assessment method and related equipment thereof Download PDFInfo
- Publication number
- CN113506173A CN113506173A CN202110903799.5A CN202110903799A CN113506173A CN 113506173 A CN113506173 A CN 113506173A CN 202110903799 A CN202110903799 A CN 202110903799A CN 113506173 A CN113506173 A CN 113506173A
- Authority
- CN
- China
- Prior art keywords
- debt
- credit risk
- data
- analysis module
- enterprise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Abstract
The application discloses a credit risk assessment method and related equipment thereof, wherein the method comprises the following steps: after the feature description information of the debt item to be evaluated is acquired, the feature description information can be input into a pre-constructed credit risk evaluation model, so that the credit risk evaluation model can perform credit risk evaluation processing on the debt item to be evaluated according to the feature description information, and a credit risk evaluation result of the debt item to be evaluated is obtained and output. The credit risk assessment model is constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the credit risk assessment model has better credit risk assessment performance, the credit risk assessment result determined by the credit risk assessment model aiming at the debt item to be assessed can more accurately represent the credit risk of the debt item to be assessed, and the accuracy of credit risk assessment aiming at the debt item can be improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a credit risk assessment method and related devices.
Background
For some service scenarios (e.g., supply chain finance, etc.), a credit risk assessment is required for an object to be assessed (e.g., a debt existing between a financing enterprise and a core enterprise). Here, "supply chain finance" refers to a financial service derived on the basis of debt items resulting from trades occurring between upstream and downstream enterprises in the supply chain due to normal operations.
Currently, credit risk assessment is usually performed by a risk management staff for an object to be assessed. However, the evaluation values given by different risk managers for the same object to be evaluated are often different, which results in poor accuracy of credit risk evaluation.
Disclosure of Invention
In order to solve the technical problems in the prior art, the application provides a credit risk assessment method and related equipment thereof, which can improve the accuracy of credit risk assessment.
In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:
the embodiment of the application provides a credit risk assessment method, which comprises the following steps:
acquiring feature description information of the debt to be evaluated;
inputting the characteristic description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model to obtain a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model; the credit risk assessment model is constructed according to feature description information of at least one sample debt item and an actual risk assessment result of the at least one sample debt item.
In one possible embodiment, the characterization information includes at least one of core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise business characterization data, and financing enterprise financial data;
the core enterprise financial data includes at least one of revenue, gross interest rate, net interest rate, balance rate, flow ratio, speed ratio, cash guarantee multiple, pre-tax profit guarantee multiple, inventory turnover rate, and market share;
the macroscopic economic factor data comprises at least one of industry average gross profit rate, industry prosperity index, industry concentration, domestic production total value increase rate, currency expansion rate, production price index and purchase manager index;
the external support characterization data of the core enterprise comprises at least one of available credit balance of the core enterprise, core enterprise property, a core enterprise stock holder and debt balance of the core enterprise;
the financing enterprise operation representation data comprises at least one of electricity consumption data, electricity purchasing data, judicial litigation data, tax data and logistics data;
the financing enterprise financial data includes at least one of an inventory turnover rate, a sales gross rate, an accounts receivable turnover rate, and a net present ratio.
In one possible embodiment, the credit risk assessment model includes a data analysis module and a credit risk assessment module; wherein the input data of the credit risk assessment module comprises the output data of the data analysis module; the data analysis module comprises at least one of a core enterprise financial analysis module, a macro-economic analysis module, an external support analysis module, a financing enterprise operation analysis module and a financing enterprise financial analysis module.
In one possible implementation manner, the debt to be evaluated refers to a debt existing between a target financing enterprise and a target core enterprise, and the feature description information includes core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise operation characterization data, and financing enterprise financial data, and the data analysis module includes a core enterprise financial analysis module, a macro economic analysis module, an external support analysis module, a financing enterprise operation analysis module, and a financing enterprise financial analysis module;
the process for determining the credit risk assessment result of the debt to be assessed comprises the following steps:
inputting the core enterprise financial data of the debt to be evaluated into the core enterprise financial analysis module to obtain the financial characteristic category of the target core enterprise output by the core enterprise financial analysis module;
inputting the macro economic factor data of the debt to be evaluated into the macro economic analysis module to obtain the industry affected level corresponding to the debt to be evaluated and output by the macro economic analysis module;
inputting the external support characterization data of the core enterprise of the debt to be evaluated into the external support analysis module to obtain the external support strength of the target core enterprise output by the external support analysis module;
inputting the financing enterprise operation representation data of the debt to be evaluated into the financing enterprise operation analysis module to obtain the operation characteristic score of the target financing enterprise output by the financing enterprise operation analysis module;
inputting financial data of the financing enterprise of the debt to be evaluated into the financing enterprise financial analysis module to obtain the financial representation category of the target financing enterprise output by the financing enterprise financial analysis module;
inputting the financial characteristic category of the target core enterprise, the industry affected level corresponding to the debt to be evaluated, the external support strength of the target core enterprise, the operation characteristic score of the target financing enterprise and the financial characterization category of the target financing enterprise into the credit risk evaluation module, and obtaining the credit risk evaluation result of the debt to be evaluated, which is output by the credit risk evaluation module.
In one possible embodiment, the credit risk assessment model is constructed by a process including:
constructing the data analysis module by using the characteristic description information of the at least one sample debt item;
determining a data analysis result of the at least one sample debt item according to the constructed data analysis module and the feature description information of the at least one sample debt item;
training the credit risk assessment module by using the data analysis result of the at least one sample debt and the actual risk assessment result of the at least one sample debt;
and connecting the constructed data analysis module with the trained credit risk assessment module according to a preset mode to obtain the credit risk assessment model.
In a possible implementation manner, the credit risk assessment result of the debt to be assessed includes the credit risk level of the debt to be assessed and/or the default probability corresponding to the debt to be assessed.
An embodiment of the present application further provides a credit risk determining apparatus, including:
the information acquisition unit is used for acquiring the characteristic description information of the debt to be evaluated;
the risk evaluation unit is used for inputting the characteristic description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model to obtain a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model; the credit risk assessment model is constructed according to feature description information of at least one sample debt item and an actual risk assessment result of the at least one sample debt item.
An embodiment of the present application further provides an apparatus, where the apparatus includes a processor and a memory:
the memory is used for storing a computer program;
the processor is used for executing any implementation mode of the credit risk assessment method provided by the embodiment of the application according to the computer program.
Embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, where the computer program is used to execute any implementation manner of the credit risk assessment method provided in the embodiments of the present application.
The embodiment of the present application further provides a computer program product, which when running on a terminal device, enables the terminal device to execute any implementation manner of the credit risk assessment method provided by the embodiment of the present application.
Compared with the prior art, the embodiment of the application has at least the following advantages:
in the technical scheme provided by the embodiment of the application, after the feature description information of the debt item to be evaluated is obtained, the feature description information can be input into a pre-constructed credit risk evaluation model, so that the credit risk evaluation model can perform credit risk evaluation processing on the debt item to be evaluated according to the feature description information, and a credit risk evaluation result of the debt item to be evaluated is obtained and output. The credit risk assessment model is constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the credit risk assessment model has better credit risk assessment performance, the credit risk assessment result determined by the credit risk assessment model aiming at the debt item to be assessed can more accurately represent the credit risk of the debt item to be assessed, and the accuracy of credit risk assessment aiming at the debt item can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a credit risk assessment method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a credit risk assessment model according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of an encoding method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a credit risk assessment apparatus according to an embodiment of the present application.
Detailed Description
In research on credit risk assessment under supply chain finance, the inventor finds that for supply chain finance, in financing business with credit risk slow release of debt items generated by upstream and downstream enterprise trades in a supply chain, a risk manager can generally judge default risks by adopting a manner of debt credit rating and core enterprise main body credit rating, and the judgment manner is mainly influenced by human subjective factors, so that credit risk assessment results are different according to different evaluators. The "credit risk" refers to the possibility that a debtor will default due to the failure of timely and sufficient debt owing for various reasons.
Based on the above findings, in order to solve the technical problems in the background art section, an embodiment of the present application provides a credit risk assessment method, including: after the feature description information of the debt item to be evaluated is acquired, the feature description information can be input into a pre-constructed credit risk evaluation model, so that the credit risk evaluation model can perform credit risk evaluation processing on the debt item to be evaluated according to the feature description information, and a credit risk evaluation result of the debt item to be evaluated is obtained and output. The credit risk assessment model is constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the credit risk assessment model has better credit risk assessment performance, the credit risk assessment result determined by the credit risk assessment model aiming at the debt item to be assessed can more accurately represent the credit risk of the debt item to be assessed, and the accuracy of credit risk assessment aiming at the debt item can be improved.
In addition, the embodiment of the present application does not limit the execution subject of the credit risk assessment method, and for example, the credit risk assessment method provided by the embodiment of the present application may be applied to a data processing device such as a terminal device or a server. The terminal device may be a smart phone, a computer, a Personal Digital Assistant (PDA), a tablet computer, or the like. The server may be a stand-alone server, a cluster server, or a cloud server.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Method embodiment
Referring to fig. 1, the figure is a flowchart of a credit risk assessment method provided in an embodiment of the present application.
The credit risk assessment method provided by the embodiment of the application comprises the following steps of S1-S2:
s1: and acquiring the characteristic description information of the debt to be evaluated.
Where "debt to be assessed" is used to indicate that a debt exists between any two businesses. For example, "debt to be assessed" may refer to the debt that exists between the target financing business and the target core business. That is, when the target financing enterprise sells the commodity operated by the target financing enterprise to the target core enterprise, and the target core enterprise does not pay the target financing enterprise for the commodity, a debt item about the commodity can be formed between the target financing enterprise and the target core enterprise, so that the target financing enterprise can participate in the financing business by using the debt item.
The characteristic description information is used for describing information related to the debt to be evaluated; furthermore, the embodiment of the present application does not limit "profile information", and for example, it may specifically include at least one of core enterprise financial data, macro economic factor data, core enterprise external support profile data, financing enterprise business profile data, and financing enterprise financial data.
The core enterprise financial data is used for describing enterprise financial characteristics of a core enterprise (such as a target core enterprise) corresponding to the debt to be evaluated; also, the embodiments of the present application do not limit "core enterprise financial data", and may specifically include at least one of a revenue, a gross rate, a net rate, a liability rate, a liquidity ratio, a speed-action ratio, a cash guarantee multiple, a pre-interest tax profit guarantee multiple, an inventory turnover rate, and a market share, for example.
The 'macroscopic economic factor data' is used for describing the macroscopic economic characteristics of the debt to be evaluated when participating in financing; also, the present embodiment does not limit "macro economic factor data", and for example, it may include at least one of industry average Gross interest rate, industry prospect Index, industry concentration (e.g., CR5), Gross Domestic Product (GDP) growth rate, inflation rate, Production Price Index (PPI), and Purchase Manager Index (PMI). The "industry" refers to an industry in which an enterprise to which the debt to be evaluated relates (e.g., a target financing enterprise, a target core enterprise, etc.) is located.
The "external support characterization data of the core enterprise" is used for describing external support characteristics of the core enterprise (e.g., a target core enterprise) corresponding to the debt to be evaluated; moreover, embodiments of the subject application are not limited to "core enterprise external support characterization data," which may specifically include, for example, at least one of core enterprise available credit balances, core enterprise properties (e.g., central enterprise, national enterprise, listed company, private enterprise, etc.), core enterprise holdings, and core enterprise debt balances (e.g., which may include financing amounts in the application).
The operation representation data of the financing enterprise is used for describing the operation state characteristics of the financing enterprise (for example, a target financing enterprise) corresponding to the debt to be evaluated; moreover, the financial enterprise operation characterization data is not limited in the embodiments of the present application, and may specifically include at least one of electricity consumption data, electricity purchasing data, judicial litigation data (e.g., judicial execution records, distrust records, etc. related to the target financial enterprise), tax data (e.g., debt records, tax penalties, etc. related to the target financial enterprise), and logistics data (e.g., logistics history documents, logistics cost invoices, etc. related to the target financial enterprise).
The financial data of the financing enterprise is used for describing the financial state characteristics of the financing enterprise (for example, a target financing enterprise) corresponding to the debt to be evaluated; also, the embodiments of the present application do not limit "financing enterprise financial data," which may specifically include at least one of an inventory turnover rate, a sales profit rate, an accounts receivable turnover rate, and a net present ratio, for example.
In addition, the embodiment of the present application does not limit the manner of acquiring the "feature description information of the debt item to be evaluated", for example, after the original description information of the debt item to be evaluated is acquired, preset data processing (for example, filling of a missing data value, processing of an abnormal data sample, normalization of data, and the like) may be performed on the original description information, so as to obtain the feature description information of the debt item to be evaluated, so that the feature description information can better describe information related to the debt item to be evaluated.
S2: inputting the characteristic description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model, and obtaining a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model.
The credit risk assessment model is used for performing credit risk assessment processing on input data of the credit risk assessment model.
In addition, the embodiment of the present application does not limit the model structure of the "credit risk assessment model", for example, as shown in fig. 2, the credit risk assessment model 200 may specifically include a data analysis module 201 and a credit risk assessment module 202; and the input data to the credit risk assessment module 202 includes the output data of the data analysis module 201.
The data analysis module 201 is configured to perform preset analysis processing on input data of the data analysis module 201; moreover, the data analysis module 201 is not limited in the embodiments of the present application, and may specifically include at least one of a core enterprise financial analysis module, a macro-economic analysis module, an external support analysis module, a financing enterprise business analysis module, and a financing enterprise financial analysis module, for example. It should be noted that, for the relevant information of these modules, please refer to the following.
The credit risk assessment module 202 is configured to perform scoring processing on input data of the credit risk assessment module 202.
To facilitate understanding of the principles of operation of the credit risk assessment model 200, an example is described below.
It is assumed that the debt to be evaluated refers to the debt existing between the target financing enterprise and the target core enterprise, the data analysis module 201 includes a core enterprise financial analysis module, a macro economic analysis module, an external support analysis module, a financing enterprise operation analysis module, and a financing enterprise financial analysis module, and the "feature description information" includes core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise operation characterization data, and financing enterprise financial data.
As an example, based on the above assumptions, the process of determining the "credit risk assessment result of the debt to be assessed" by using the credit risk assessment model 200 may specifically include steps 11 to 16:
step 11: and inputting the core enterprise financial data of the debt to be evaluated into a core enterprise financial analysis module to obtain the financial characteristic category of the target core enterprise output by the core enterprise financial analysis module.
The core enterprise financial analysis module is used for performing financial characteristic analysis on input data of the core enterprise financial analysis module; moreover, the working principle of the core enterprise financial analysis module is not limited in the embodiment of the present application, and for example, the working principle may be specifically implemented by using a preset clustering algorithm (e.g., a k-nearest neighbor (KNN) clustering machine learning algorithm).
In addition, the "financial characteristics category of the target core enterprise" is used to represent the financial characteristics of the target core enterprise; furthermore, the embodiment of the present application does not limit the financial characteristics category of the target core enterprise, which may be, for example, category 1, category 2, … ….
Step 12: inputting the macro economic factor data of the debt to be evaluated into a macro economic analysis module to obtain the industry affected level corresponding to the debt to be evaluated and output by the macro economic analysis module.
The macro-economic analysis module is used for carrying out industry influenced feature analysis on input data of the macro-economic analysis module; moreover, the working principle of the macro economic analysis module is not limited in the embodiment of the application, for example, the macro economic analysis module can perform classification processing by using a logistic regression classification algorithm.
In addition, the 'industry influenced level corresponding to the debt to be evaluated' is used for representing the influence level of the macroscopic economy on the industry to which the debt to be evaluated belongs; furthermore, the embodiment of the present application does not limit the "industry affected level corresponding to the debt to be evaluated", for example, it may be-2 level, -1 level, 0 level, 1 level, or 2 level, etc.
Step 13: and inputting the external support characterization data of the core enterprise of the debt to be evaluated into an external support analysis module to obtain the external support strength of the target core enterprise output by the external support analysis module.
The external support analysis module is used for carrying out external support characteristic analysis on input data of the external support analysis module; moreover, the working principle of the external support analysis module is not limited in the embodiments of the present application, and for example, it can be implemented by using formulas (1) to (4).
ES＝(Scredit+SNature+Sholder)/30 (1)
In the formula, ES represents the external support strength of the target core enterprise.
It should be noted that in some cases, the core enterprise property of the target core enterprise may include multiple enterprise properties (e.g., national enterprise, central enterprise), in which case the "S" may be described as aboveNature"may be determined by the nature of the business with the highest score (e.g., the central enterprise).
The "external support strength of the target core enterprise" is used to indicate the external support capability of the target core enterprise.
Step 14: and inputting the financing enterprise operation representation data of the debt to be evaluated into the financing enterprise operation analysis module to obtain the operation characteristic score of the target financing enterprise output by the financing enterprise operation analysis module.
The financing enterprise operation analysis module is used for carrying out trade operation analysis processing on input data of the financing enterprise operation analysis module.
In addition, the embodiment of the present application does not limit the working principle of the financing enterprise operation analysis module, for example, the working principle may specifically include: firstly, performing feature coding processing (for example, coding processing is performed by adopting a coding method shown in fig. 3) on the financing enterprise operation representation data of the debt to be evaluated to obtain the financing enterprise operation features corresponding to the debt to be evaluated, so that the financing enterprise operation features can accurately represent the trade operation features of the target financing enterprise; and then, performing preset scoring processing (for example, performing weighted summation processing on the operation characteristics of each financing enterprise) according to the financing enterprise operation characteristics corresponding to the debt to be evaluated to obtain the operation characteristic score of the target financing enterprise, so that the operation characteristic score can accurately represent the characteristics of the target financing enterprise in the aspect of trade operation.
In addition, "business feature score of a target financing enterprise" is used to represent the features that the target financing enterprise presents in terms of trade operations.
Step 15: and inputting financial data of the financing enterprise of the debt to be evaluated into a financing enterprise financial analysis module to obtain the financial representation category of the target financing enterprise output by the financing enterprise financial analysis module.
The financial analysis module of the financing enterprise is used for carrying out financial analysis processing on input data of the financial analysis module of the financing enterprise; moreover, the working principle of the financial analysis module of the financing enterprise is not limited in the embodiments of the present application, for example, the classification process may be performed by using a logistic regression algorithm (as shown in formula (5)).
In the formula, p (Y ═ k | x) represents a financial characterization class of the target financing enterprise determined using the "financing enterprise financial data of the debt to be evaluated" described above"a likelihood of belonging to the kth financial category; y represents the financial representation category of the target financing enterprise; x represents financing enterprise financial data for the debt to be assessed; w is akRepresenting a weight vector corresponding to the kth financial category; k is 1, 2, 3, … …, N; n is a positive integer and N represents the number of financial categories.
The 'financial characterization category of the target financing enterprise' is used for representing the financial characteristics of the target financing enterprise; in addition, the embodiment of the present application does not limit the financial characterization category of the target financing enterprise, for example, it may be specifically any one of the categories of-2, -1, 0, 1, 2, and the like.
Step 16: inputting the financial characteristic category of the target core enterprise, the industry affected level corresponding to the debt to be evaluated, the external support strength of the target core enterprise, the business characteristic score of the target financing enterprise and the financial characterization category of the target financing enterprise into the credit risk evaluation module 202, and obtaining the credit risk evaluation result of the debt to be evaluated, which is output by the credit risk evaluation module 202.
The credit risk assessment module 202 is used for performing scoring processing on input data of the credit risk assessment module 202; moreover, the working principle of the credit risk assessment module 202 is not limited in the embodiment of the present application, and for example, the working principle may be implemented by using a Gradient Boosting Decision Tree (GBDT) algorithm.
In addition, the embodiment of the present application does not limit the model parameters of the "credit risk assessment module 202", and for example, the model parameters may specifically include the following: the loss function (loss) adopts a square loss function (ls); the learning rate (learning _ rate) is 0.1; taking 50 as the maximum iteration number (n _ estimators); subsample (subsample) is set to 0.70; the parameter value of the minimum sample number (min _ samples _ split) required by the internal node subdivision is 2; the leaf node minimum sample number (min _ samples _ leaf) value is 1; the maximum depth of the decision tree is 2; other parameters may be default to the system (or may be preset).
The "credit risk assessment result of the debt to be assessed" is used to indicate the credit risk of the debt to be assessed. In addition, the embodiment of the present application does not limit "the credit risk assessment result of the debt to be assessed," and for example, the credit risk assessment result may specifically include the credit risk level of the debt to be assessed and/or the default probability corresponding to the debt to be assessed. The "credit risk level of the debt to be evaluated" is used to indicate the level information reached by the credit risk of the debt to be evaluated. The "default probability corresponding to the debt item to be evaluated" is used to indicate the possibility of default of the debt item to be evaluated.
Based on the related contents of the above steps 11 to 16, for the credit risk assessment model 200, after the data (e.g., the core enterprise financial data, the macro economic factor data, the core enterprise external support characterization data, the financing enterprise operation characterization data, the financing enterprise financial data, etc.) corresponding to the debt to be assessed are input into the credit risk assessment model 200, the credit risk assessment model 200 may analyze and process the data respectively to obtain the analysis result (e.g., the financial characteristic category of the target core enterprise, the industry affected level corresponding to the debt to be assessed, the external support strength of the target core enterprise, the operation characteristic score of the target financing enterprise, the financial characterization category of the target financing enterprise, etc.) corresponding to each data; the credit risk assessment model 200 performs scoring processing on the analysis results corresponding to the data to obtain a credit risk assessment result of the debt to be assessed, so that the credit risk assessment result can accurately represent the credit risk presented by the debt to be assessed.
In addition, the credit risk assessment model can be constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of at least one sample debt item. Wherein "actual risk assessment result of sample debt" is used to represent actual credit risk presented by the sample debt.
In addition, the embodiment of the present application does not limit the building process of the "credit risk assessment model", and for example, the method may specifically include steps 21 to 24:
step 21: and constructing a data analysis module by using the characteristic description information of at least one sample debt item.
The embodiment of the present application does not limit the construction manner of step 21, for example, if the data analysis module includes a core enterprise financial analysis module, a macro economic analysis module, and a financing enterprise financial analysis module, step 21 may specifically include steps 211 to 213:
step 211: and clustering the core enterprise financial data of at least one sample debt item by using a preset clustering algorithm to obtain a data analysis module, so that the subsequent data analysis module can perform financial characteristic analysis according to the preset clustering algorithm.
Step 212: and training a macro-economic analysis module by utilizing the macro-economic factor data of at least one sample debt item and the actual industry influenced level corresponding to the at least one sample debt item, so that the trained macro-economic analysis module has better industry influenced level classification performance. The actual industry influenced level corresponding to the sample debt item refers to the actual influence level of the macro economy aiming at the industry to which the sample debt item belongs.
Step 213: and training the financial analysis module of the financing enterprise by using the financial data of the financing enterprise of at least one sample debt and the actual financial characterization category of the at least one sample debt, so that the trained financial analysis module of the financing enterprise has better classification performance of the financial characterization category. The "actual financial characterization category of the sample debt item" refers to the financial category to which the financing enterprise financial data of the sample debt item actually belongs.
Based on the related content of step 21, after the feature description information of at least one sample debt item is obtained, a data analysis module can be constructed by means of the feature description information of the at least one sample debt item, so that the constructed data analysis module has better data analysis performance.
Step 22: and determining the data analysis result of at least one sample debt item according to the constructed data analysis module and the feature description information of the at least one sample debt item.
The "data analysis result of the sample debt item" refers to a result obtained by performing data analysis processing on the feature description information of the sample debt item by the data analysis module.
In addition, the embodiment of the present application does not limit "the data analysis result of the sample debt," for example, if the data analysis module includes a core enterprise financial analysis module, a macro economic analysis module, an external support analysis module, a financing enterprise business analysis module, and a financing enterprise financial analysis module, the "data analysis result of the sample debt" may include a financial feature category of the core enterprise to which the sample debt relates, an industry affected level corresponding to the sample debt, an external support strength of the core enterprise to which the sample debt relates, a business feature score of the financing enterprise to which the sample debt relates, and a financial representation category of the financing enterprise to which the sample debt relates.
Step 23: and training a credit risk assessment module by using the data analysis result of the at least one sample debt and the actual risk assessment result of the at least one sample debt.
In the embodiment of the application, after the data analysis result of at least one sample debt item is obtained, the credit risk assessment module can be trained by using the data analysis result of the at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the scoring processing result obtained by the trained credit risk assessment module for the data analysis result of each sample debt item is very close to (even equal to) the actual risk assessment result of each sample debt item, and thus the trained credit risk assessment module has better scoring performance.
Step 24: and connecting the constructed data analysis module with the trained credit risk assessment module according to a preset mode to obtain a credit risk assessment model. The preset mode may be a preset connection mode (such as the connection mode shown in fig. 2).
Based on the related contents of the above steps 21 to 24, a credit risk assessment model can be constructed by means of the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the constructed credit risk assessment model has better credit risk assessment performance, and the credit risk assessment process can be subsequently performed by means of the constructed credit risk assessment model.
Based on the above-mentioned related contents of S1 to S2, in the credit risk assessment method provided in the embodiment of the present application, after the feature description information of the debt to be assessed is obtained, the feature description information may be input into a credit risk assessment model that is constructed in advance, so that the credit risk assessment model can perform credit risk assessment processing on the debt to be assessed according to the feature description information, and obtain and output a credit risk assessment result of the debt to be assessed. The credit risk assessment model is constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the credit risk assessment model has better credit risk assessment performance, the credit risk assessment result determined by the credit risk assessment model aiming at the debt item to be assessed can more accurately represent the credit risk of the debt item to be assessed, and the accuracy of credit risk assessment aiming at the debt item can be improved.
Based on the credit risk assessment method provided by the above method embodiment, the embodiment of the present application further provides a credit risk assessment apparatus, which is explained and explained below with reference to the accompanying drawings.
Device embodiment
Please refer to the above method embodiment for technical details of the credit risk assessment apparatus provided by the apparatus embodiment.
Referring to fig. 4, the figure is a schematic structural diagram of a credit risk assessment apparatus provided in the embodiment of the present application.
The credit risk assessment apparatus 400 provided in the embodiment of the present application includes:
an information obtaining unit 401, configured to obtain feature description information of a debt to be evaluated;
a risk evaluation unit 402, configured to input feature description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model, and obtain a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model; the credit risk assessment model is constructed according to feature description information of at least one sample debt item and an actual risk assessment result of the at least one sample debt item.
In one possible embodiment, the characterization information includes at least one of core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise business characterization data, and financing enterprise financial data;
the core enterprise financial data includes at least one of revenue, gross interest rate, net interest rate, balance rate, flow ratio, speed ratio, cash guarantee multiple, pre-tax profit guarantee multiple, inventory turnover rate, and market share;
the macroscopic economic factor data comprises at least one of industry average gross profit rate, industry prosperity index, industry concentration, domestic production total value increase rate, currency expansion rate, production price index and purchase manager index;
the external support characterization data of the core enterprise comprises at least one of available credit balance of the core enterprise, core enterprise property, a core enterprise stock holder and debt balance of the core enterprise;
the financing enterprise operation representation data comprises at least one of electricity consumption data, electricity purchasing data, judicial litigation data, tax data and logistics data;
the financing enterprise financial data includes at least one of an inventory turnover rate, a sales gross rate, an accounts receivable turnover rate, and a net present ratio.
In one possible embodiment, the credit risk assessment model includes a data analysis module and a credit risk assessment module; wherein the input data of the credit risk assessment module comprises the output data of the data analysis module; the data analysis module comprises at least one of a core enterprise financial analysis module, a macro-economic analysis module, an external support analysis module, a financing enterprise operation analysis module and a financing enterprise financial analysis module.
In one possible implementation manner, the debt to be evaluated refers to a debt existing between a target financing enterprise and a target core enterprise, and the feature description information includes core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise operation characterization data, and financing enterprise financial data, and the data analysis module includes a core enterprise financial analysis module, a macro economic analysis module, an external support analysis module, a financing enterprise operation analysis module, and a financing enterprise financial analysis module;
the risk assessment unit 402 is specifically configured to:
inputting the core enterprise financial data of the debt to be evaluated into the core enterprise financial analysis module to obtain the financial characteristic category of the target core enterprise output by the core enterprise financial analysis module;
inputting the macro economic factor data of the debt to be evaluated into the macro economic analysis module to obtain the industry affected level corresponding to the debt to be evaluated and output by the macro economic analysis module;
inputting the external support characterization data of the core enterprise of the debt to be evaluated into the external support analysis module to obtain the external support strength of the target core enterprise output by the external support analysis module;
inputting the financing enterprise operation representation data of the debt to be evaluated into the financing enterprise operation analysis module to obtain the operation characteristic score of the target financing enterprise output by the financing enterprise operation analysis module;
inputting financial data of the financing enterprise of the debt to be evaluated into the financing enterprise financial analysis module to obtain the financial representation category of the target financing enterprise output by the financing enterprise financial analysis module;
inputting the financial characteristic category of the target core enterprise, the industry affected level corresponding to the debt to be evaluated, the external support strength of the target core enterprise, the operation characteristic score of the target financing enterprise and the financial characterization category of the target financing enterprise into the credit risk evaluation module, and obtaining the credit risk evaluation result of the debt to be evaluated, which is output by the credit risk evaluation module.
In one possible implementation, the credit risk assessment apparatus 400 further includes:
the model construction unit is used for constructing the data analysis module by utilizing the characteristic description information of the at least one sample debt item; determining a data analysis result of the at least one sample debt item according to the constructed data analysis module and the feature description information of the at least one sample debt item; training the credit risk assessment module by using the data analysis result of the at least one sample debt and the actual risk assessment result of the at least one sample debt; and connecting the constructed data analysis module with the trained credit risk assessment module according to a preset mode to obtain the credit risk assessment model.
In a possible implementation manner, the credit risk assessment result of the debt to be assessed includes the credit risk level of the debt to be assessed and/or the default probability corresponding to the debt to be assessed.
Based on the above-mentioned related content of the credit risk assessment apparatus 400, for the credit risk assessment apparatus 400, after the feature description information of the debt item to be assessed is obtained, the feature description information may be input into a pre-constructed credit risk assessment model, so that the credit risk assessment model can perform credit risk assessment processing on the debt item to be assessed according to the feature description information, and obtain and output a credit risk assessment result of the debt item to be assessed. The credit risk assessment model is constructed in advance according to the feature description information of at least one sample debt item and the actual risk assessment result of the at least one sample debt item, so that the credit risk assessment model has better credit risk assessment performance, the credit risk assessment result determined by the credit risk assessment model aiming at the debt item to be assessed can more accurately represent the credit risk of the debt item to be assessed, and the accuracy of credit risk assessment aiming at the debt item can be improved.
Further, an embodiment of the present application further provides an apparatus, where the apparatus includes a processor and a memory:
the memory is used for storing a computer program;
the processor is used for executing any implementation mode of the credit risk assessment method provided by the embodiment of the application according to the computer program.
Further, an embodiment of the present application also provides a computer-readable storage medium, which is used for storing a computer program, where the computer program is used for executing any implementation manner of the credit risk assessment method provided by the embodiment of the present application.
Further, an embodiment of the present application also provides a computer program product, where when the computer program product runs on a terminal device, the terminal device is caused to execute any implementation of the credit risk assessment method provided in the embodiment of the present application.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (10)
1. A credit risk assessment method, the method comprising:
acquiring feature description information of the debt to be evaluated;
inputting the characteristic description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model to obtain a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model; the credit risk assessment model is constructed according to feature description information of at least one sample debt item and an actual risk assessment result of the at least one sample debt item.
2. The method of claim 1, wherein the characterization information includes at least one of core enterprise financial data, macro-economic factor data, core enterprise external support characterization data, financing enterprise business characterization data, and financing enterprise financial data;
the core enterprise financial data includes at least one of revenue, gross interest rate, net interest rate, balance rate, flow ratio, speed ratio, cash guarantee multiple, pre-tax profit guarantee multiple, inventory turnover rate, and market share;
the macroscopic economic factor data comprises at least one of industry average gross profit rate, industry prosperity index, industry concentration, domestic production total value increase rate, currency expansion rate, production price index and purchase manager index;
the external support characterization data of the core enterprise comprises at least one of available credit balance of the core enterprise, core enterprise property, a core enterprise stock holder and debt balance of the core enterprise;
the financing enterprise operation representation data comprises at least one of electricity consumption data, electricity purchasing data, judicial litigation data, tax data and logistics data;
the financing enterprise financial data includes at least one of an inventory turnover rate, a sales gross rate, an accounts receivable turnover rate, and a net present ratio.
3. The method of claim 1, wherein the credit risk assessment model comprises a data analysis module and a credit risk assessment module; wherein the input data of the credit risk assessment module comprises the output data of the data analysis module; the data analysis module comprises at least one of a core enterprise financial analysis module, a macro-economic analysis module, an external support analysis module, a financing enterprise operation analysis module and a financing enterprise financial analysis module.
4. The method according to claim 3, wherein the debt to be evaluated refers to the debt existing between the target financing enterprise and the target core enterprise, and the feature description information includes core enterprise financial data, macro economic factor data, core enterprise external support characterization data, financing enterprise business characterization data, and financing enterprise financial data, and the data analysis module includes a core enterprise financial analysis module, a macro economic analysis module, an external support analysis module, a financing enterprise business analysis module, and a financing enterprise financial analysis module;
the process for determining the credit risk assessment result of the debt to be assessed comprises the following steps:
inputting the core enterprise financial data of the debt to be evaluated into the core enterprise financial analysis module to obtain the financial characteristic category of the target core enterprise output by the core enterprise financial analysis module;
inputting the macro economic factor data of the debt to be evaluated into the macro economic analysis module to obtain the industry affected level corresponding to the debt to be evaluated and output by the macro economic analysis module;
inputting the external support characterization data of the core enterprise of the debt to be evaluated into the external support analysis module to obtain the external support strength of the target core enterprise output by the external support analysis module;
inputting the financing enterprise operation representation data of the debt to be evaluated into the financing enterprise operation analysis module to obtain the operation characteristic score of the target financing enterprise output by the financing enterprise operation analysis module;
inputting financial data of the financing enterprise of the debt to be evaluated into the financing enterprise financial analysis module to obtain the financial representation category of the target financing enterprise output by the financing enterprise financial analysis module;
inputting the financial characteristic category of the target core enterprise, the industry affected level corresponding to the debt to be evaluated, the external support strength of the target core enterprise, the operation characteristic score of the target financing enterprise and the financial characterization category of the target financing enterprise into the credit risk evaluation module, and obtaining the credit risk evaluation result of the debt to be evaluated, which is output by the credit risk evaluation module.
5. The method of claim 3, wherein the credit risk assessment model is constructed by:
constructing the data analysis module by using the characteristic description information of the at least one sample debt item;
determining a data analysis result of the at least one sample debt item according to the constructed data analysis module and the feature description information of the at least one sample debt item;
training the credit risk assessment module by using the data analysis result of the at least one sample debt and the actual risk assessment result of the at least one sample debt;
and connecting the constructed data analysis module with the trained credit risk assessment module according to a preset mode to obtain the credit risk assessment model.
6. The method according to claim 1, wherein the credit risk assessment result of the debt to be assessed comprises the credit risk level of the debt to be assessed and/or the default probability corresponding to the debt to be assessed.
7. A credit risk determination apparatus, comprising:
the information acquisition unit is used for acquiring the characteristic description information of the debt to be evaluated;
the risk evaluation unit is used for inputting the characteristic description information of the debt item to be evaluated into a pre-constructed credit risk evaluation model to obtain a credit risk evaluation result of the debt item to be evaluated, which is output by the credit risk evaluation model; the credit risk assessment model is constructed according to feature description information of at least one sample debt item and an actual risk assessment result of the at least one sample debt item.
8. An apparatus, comprising a processor and a memory:
the memory is used for storing a computer program;
the processor is configured to perform the method of any of claims 1-6 in accordance with the computer program.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program for performing the method of any of claims 1-6.
10. A computer program product, characterized in that the computer program product, when run on a terminal device, causes the terminal device to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110903799.5A CN113506173A (en) | 2021-08-06 | 2021-08-06 | Credit risk assessment method and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110903799.5A CN113506173A (en) | 2021-08-06 | 2021-08-06 | Credit risk assessment method and related equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113506173A true CN113506173A (en) | 2021-10-15 |
Family
ID=78015723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110903799.5A Pending CN113506173A (en) | 2021-08-06 | 2021-08-06 | Credit risk assessment method and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506173A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801529A (en) * | 2021-02-05 | 2021-05-14 | 北京同邦卓益科技有限公司 | Financial data analysis method and device, electronic device and medium |
| CN115082225A (en) * | 2022-07-21 | 2022-09-20 | 天津金城银行股份有限公司 | Enterprise financing risk assessment method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409641A (en) * | 2018-09-03 | 2019-03-01 | 平安科技（深圳）有限公司 | Risk evaluating method, device, computer equipment and storage medium |
| WO2019095572A1 (en) * | 2017-11-17 | 2019-05-23 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method, device, and storage medium |
| CN110264085A (en) * | 2019-06-21 | 2019-09-20 | 黄河科技学院 | A kind of assessment of industrial and commercial administration business risk and early warning system |
| CN110766541A (en) * | 2019-09-25 | 2020-02-07 | 平安科技（深圳）有限公司 | Loan risk assessment method, loan risk assessment device, loan risk assessment equipment and computer-readable storage medium |
| CN111915155A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Small and micro enterprise risk level identification method and device and computer equipment |
| CN112734559A (en) * | 2020-12-30 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise credit risk evaluation method and device and electronic equipment |
| CN112991043A (en) * | 2021-03-02 | 2021-06-18 | 北京同邦卓益科技有限公司 | Debt rating data processing method and device, electronic equipment and storage medium |
-
2021
- 2021-08-06 CN CN202110903799.5A patent/CN113506173A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019095572A1 (en) * | 2017-11-17 | 2019-05-23 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method, device, and storage medium |
| CN109409641A (en) * | 2018-09-03 | 2019-03-01 | 平安科技（深圳）有限公司 | Risk evaluating method, device, computer equipment and storage medium |
| CN110264085A (en) * | 2019-06-21 | 2019-09-20 | 黄河科技学院 | A kind of assessment of industrial and commercial administration business risk and early warning system |
| CN110766541A (en) * | 2019-09-25 | 2020-02-07 | 平安科技（深圳）有限公司 | Loan risk assessment method, loan risk assessment device, loan risk assessment equipment and computer-readable storage medium |
| CN111915155A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Small and micro enterprise risk level identification method and device and computer equipment |
| CN112734559A (en) * | 2020-12-30 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise credit risk evaluation method and device and electronic equipment |
| CN112991043A (en) * | 2021-03-02 | 2021-06-18 | 北京同邦卓益科技有限公司 | Debt rating data processing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张永春;陈岩;: "大数据背景下的中小企业信用风险评价与应用研究", 电子商务, no. 12, pages 34 - 36 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801529A (en) * | 2021-02-05 | 2021-05-14 | 北京同邦卓益科技有限公司 | Financial data analysis method and device, electronic device and medium |
| CN115082225A (en) * | 2022-07-21 | 2022-09-20 | 天津金城银行股份有限公司 | Enterprise financing risk assessment method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20130117278A1 (en) | Methods, computer-accessible medium and systems for construction of and interference with networked data, for example, in a financial setting | |
| CN111401600A (en) | Enterprise credit risk evaluation method and system based on incidence relation | |
| CN113506173A (en) | Credit risk assessment method and related equipment thereof | |
| CN109815480B (en) | Data processing method and device and storage medium | |
| Boguslauskas et al. | The selection of financial ratios as independent variables for credit risk assessment | |
| CN112801529A (en) | Financial data analysis method and device, electronic device and medium | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| Séverin et al. | Can earnings management information improve bankruptcy prediction models? | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| Liu et al. | Financial credit risk assessment of online supply chain in construction industry with a hybrid model chain | |
| CN115526700A (en) | Risk prediction method and device and electronic equipment | |
| Wei | A machine learning algorithm for supplier credit risk assessment based on supply chain management | |
| CN110689437A (en) | Communication construction project financial risk prediction method based on random forest | |
| CN114331671A (en) | Loan risk monitoring method and device, server and storage medium | |
| CN113988459A (en) | Small and medium-sized enterprise growth assessment method and system based on electric power marketing data | |
| Moedjahedy et al. | Stock price forecasting on telecommunication sector companies in Indonesia Stock Exchange using machine learning algorithms | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN110866829A (en) | Stock price prediction method based on integrated learning model | |
| CN113112186A (en) | Enterprise evaluation method, device and equipment | |
| CN115545909A (en) | Approval method, device, equipment and storage medium | |
| CN114943563A (en) | Rights and interests pushing method and device, computer equipment and storage medium | |
| CN113762415A (en) | Neural network-based intelligent matching method and system for automobile financial products | |
| Huang | Big data application in exchange rate financial prediction platform based on FPGA and human-computer interaction. | |
| CN114119107A (en) | Steel trade enterprise transaction evaluation method, device, equipment and storage medium | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |