CN112668945A - Enterprise credit risk assessment method and device - Google Patents
Enterprise credit risk assessment method and device Download PDFInfo
- Publication number
- CN112668945A CN112668945A CN202110110899.2A CN202110110899A CN112668945A CN 112668945 A CN112668945 A CN 112668945A CN 202110110899 A CN202110110899 A CN 202110110899A CN 112668945 A CN112668945 A CN 112668945A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- data
- index
- model
- dimension
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012502 risk assessment Methods 0.000 title claims description 17
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000013210 evaluation model Methods 0.000 claims abstract description 22
- 238000007477 logistic regression Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 37
- 238000010219 correlation analysis Methods 0.000 claims description 13
- 230000000875 corresponding effect Effects 0.000 claims description 9
- 238000010187 selection method Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 3
- 238000013179 statistical model Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- XVAIDCNLVLTVFM-UHFFFAOYSA-N methacetin Chemical compound COC1=CC=C(NC(C)=O)C=C1 XVAIDCNLVLTVFM-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the specification discloses a method and equipment for evaluating credit risk of an enterprise. To solve the problems that: the credit scoring rating of the enterprise can not be quickly and accurately made, so that the problems of difficult financing and slow financing of the enterprise are caused. The method comprises the following steps: acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse; processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and determining scores and dimension weights of the enterprise under each dimension by using the model entering index; establishing a credit evaluation model by using the model-entering index through a logistic regression algorithm and the AHP analytic hierarchy process, and generating a general score of the enterprise through the credit evaluation model; and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
Description
Technical Field
The invention relates to the field of enterprise credit assessment, in particular to an enterprise credit risk assessment method and equipment.
Background
The traditional enterprise credit risk assessment system is mainly established on the basis that the actual and effective financial index data of an enterprise is taken as the main data and other operation data are supplemented, the enterprise is required to provide accurate and credible financial data and other financial related dimension data, and non-financial data are acquired by means of on-site reconciliation judgment of a product manager or a credit operator.
Because the financial system of an enterprise is generally not standardized enough, real and effective data is often difficult to provide, and the limitations of field investigation and subjective judgment increase the difficulty of evaluating the credit risk of the enterprise, thereby reducing the credit approval efficiency and the passing rate of the bank to the enterprise.
Therefore, an enterprise credit risk assessment system is established, an enterprise credit risk assessment method is provided, credit scoring and rating are rapidly carried out on enterprises, and the problems that the enterprises are difficult to finance and slow in financing are solved.
Disclosure of Invention
One or more embodiments of the present specification provide an enterprise credit risk assessment method and apparatus. The method is used for solving the following technical problems: the credit scoring rating of the enterprise can not be quickly and accurately made, so that the problems of difficult financing and slow financing of the enterprise are caused.
To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:
in a first aspect, one or more embodiments of the present specification provide a method for assessing a credit risk of an enterprise, comprising:
acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse;
processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and calculating scores and dimension weights of the enterprise under each dimension by using the model entering index;
establishing a credit evaluation model by using the model entry indexes through a logistic regression algorithm and the AHP analytic hierarchy process in a combined manner, and generating a general score of the enterprise through the credit evaluation model;
and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
Optionally, the acquiring enterprise-related data and processing the related data to obtain index data specifically includes:
acquiring the related data of the enterprise through data extraction, and cleaning, converting and loading the related data;
and processing the cleaned, converted and loaded related data by using a data processing method to obtain index data.
Optionally, the processing the index data stored in the data warehouse by an AHP analytic hierarchy process to determine a modeling index, and calculating scores and dimension weights of the enterprise in each dimension by using the modeling index specifically includes:
carrying out hierarchical processing on the index data according to the mutual relation, and establishing a hierarchical structure model, wherein the hierarchical structure model is used for dividing the dimensionality of a variable corresponding to the index data;
and constructing a judgment matrix in a layered mode according to the hierarchical structure model, carrying out consistency check on the judgment matrix, and judging whether the judgment matrix has consistency.
Optionally, determining that the judgment matrix has consistency, and determining scores and the dimension weights of the enterprises under each dimension;
and determining that the judgment matrix does not have consistency, adjusting the judgment matrix, and judging the consistency of the adjusted judgment matrix.
Optionally, the dimension weights are hierarchically ordered.
Optionally, performing correlation analysis on the variables to obtain correlation analysis results;
and determining strong correlation variables according to the correlation analysis result, and reserving one variable in the strong correlation variables.
Optionally, the performing correlation analysis on the variable to obtain a correlation analysis result specifically includes:
calculating the IV value of each variable, if the IV value is larger than a first preset value, calculating the correlation coefficient of the variable corresponding to the IV value, if the correlation coefficient is smaller than a second preset value, determining that the variable is weakly correlated or does not exist, and reserving the variable.
Optionally, the reserved variables are grouped, and the proportion of the grouped variables in the grouping is greater than a third preset value.
Optionally, the modeling index is used to jointly establish a credit evaluation model through a logistic regression algorithm and the AHP analytic hierarchy process, and the method specifically includes:
and selecting the variables in the model entry indexes through a variable selection method by the logistic regression algorithm to establish a credit evaluation model.
In a second aspect, one or more embodiments of the present specification provide an enterprise credit risk assessment device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform:
acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse;
processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and determining scores and dimension weights of the enterprise under each dimension by using the model entering index;
establishing a credit evaluation model by using the model-entering index through a logistic regression algorithm and the AHP analytic hierarchy process, and generating a general score of the enterprise through the credit evaluation model;
and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
One or more embodiments of the present disclosure provide an enterprise credit risk assessment method and device, and through the scheme, the problems that an enterprise cannot be rapidly and accurately graded for credit scoring, so that the enterprise financing is difficult and slow are solved. Standardizing risk, the existence of a credit score rating gives the approver a simple and easy to use judgment criterion in financial transactions. More technical support and practical support are provided for the credit risk assessment of the enterprise.
Drawings
In order to more clearly illustrate the embodiments of the present specification 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 introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a schematic flow chart of a method for assessing a credit risk of an enterprise according to one or more embodiments of the present disclosure;
FIG. 2 is a schematic flow chart illustrating the storing of index data into a data warehouse according to one or more embodiments of the present disclosure;
FIG. 3 is a schematic flow diagram of a process for jointly establishing a credit evaluation model according to one or more embodiments of the present disclosure;
fig. 4 is a schematic structural diagram of an enterprise credit risk assessment device according to one or more embodiments of the present disclosure.
Detailed Description
The embodiment of the specification provides a method and equipment for mixed dispatching in a cross-time-period mode.
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, 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 obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of an enterprise credit risk assessment method according to one or more embodiments of the present disclosure.
S101: acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse.
In one or more embodiments of the present description, related data of an enterprise is obtained through data extraction, and the related data is cleaned, converted, and loaded; and processing the cleaned, converted and loaded related data by using a data processing method to obtain index data.
The related data refers to enterprise information issued by a national authority and behavior and qualification data of enterprise owners provided by domestic authoritative and leading big data wind control companies. The information of the branch enterprise released by the national authority comprises the enterprise industry and commerce, judicial expertise, intellectual property, integrity (enterprise), association (enterprise investment relation, enterprise owner external investment relation and the like) and the like which are published by the country. The data of the enterprise owner is derived from data of third-party big data companies about stability, bad information, real-name information verification, consumption condition, loan condition of non-bank financial institutions, personal credit risk score, media reading and the like of the enterprise owner. The non-bank financial institution loan condition refers to the multi-time application data of a non-bank big data system, including the multi-time application data in a shadow bank. It is noted that the acquisition of the relevant data is derived from the online data, the online data is derived from the data stored on the online itself, and the offline data is processed and stored on the online. The data from the national authority and the leading big data wind control company ensures the real reliability of the data, the credit records of enterprises in a non-bank credit investigation system are effectively restored under the condition of loan from a non-bank organization, and the data dimensionality of risk assessment is enriched by a large amount of data.
FIG. 2 is a schematic flow chart illustrating the process of storing the index data in the data warehouse according to one or more embodiments of the present disclosure. As shown in the figure, an enterprise own data source, a third-party data source and the internet are used for collecting data and converging the data into a data source, the data source is acquired related data of the enterprise, dispersed data aiming at each business system and different websites is extracted through data warehouse technology (Extract Transform Load, ETL), a needed related data source is specified, the related data source stores the related data, an operable related data source reading rule is formulated, and export work to a specified destination is performed. Related data sources are typically stored in multiple places and are of diverse types including, but not limited to, relational databases, text files, Excel files, DBF files.
The obtained related data is converted into data with the same format or type, wherein the conversion refers to data format conversion, data type conversion, data summarizing calculation, data splicing and the like, and the related data with different formats or types is converted into the data with the same format or type.
And processing the data processed by the ETL technology by using a knowledge graph construction technology, mining the association relation among the data, associating the data, performing joint analysis and fusing the data. For example, a network relation graph is formed based on the outward diffusion of investment, job assignment, patents, stock recruitment and complaint relation with a target enterprise as a core, and enterprise association is visually and stereoscopically shown. And recording the development process of the enterprise based on the time sequence of the investment financing events of the enterprise. And (4) searching the stockholder with the largest stock holding proportion based on the equity investment relation, and finally tracing the natural person or the national asset management department.
Standardizing data, wherein index data refers to data of indexes such as stockholders, investment, duties, patents, bid stocks, complaint relations, finance and the like, and index data.
S102: and processing the index data stored in the data warehouse by an AHP analytic hierarchy process to determine a model entry index, and determining scores and dimension weights of the enterprise under each dimension by using the model entry index.
FIG. 3 is a flowchart illustrating a process for jointly establishing a credit evaluation model according to one or more embodiments of the present disclosure.
In one or more embodiments of the present specification, index data is hierarchically processed according to a relationship therebetween, and a hierarchical structure model is established, where the hierarchical structure model is used to divide dimensions of variables corresponding to the index data; and constructing a judgment matrix in a layering way according to the hierarchical structure model, carrying out consistency check on the judgment matrix, and judging whether the constructed judgment matrix has consistency.
An Analytic Hierarchy Process (AHP) is a multi-scheme decision analysis method, which comprises the steps of firstly drawing a hierarchical structure chart, dividing the hierarchical structure chart into three layers, dividing a target layer of decision, a decision criterion factor and a decision object into a highest layer, a middle layer and a lowest layer according to the mutual relation. The highest layer corresponds to the target layer of the decision, the middle layer corresponds to the decision criterion factor considered, and the lowest layer corresponds to the decision object. It should be noted that the hierarchical structure diagram is not limited to three layers, and may also be two layers or four layers, and is not specifically limited.
Taking the middle layer as an example, in one or more embodiments of the present disclosure, the middle layer includes an industry, a debt, a development, an operation, a performance, and the like, and the industry, the debt, the development, the operation, the performance, and the like each correspond to a dimension. Each dimension contains a plurality of index data, for example, debts including total amount of liabilities, financial leverage, etc., and the plurality of index data is processed. The judgment matrix is constructed by adopting a consistent matrix method, all index data are not put together for comparison in the consistent matrix method, but are compared with each other pairwise, so that the difficulty in comparing the index data with different properties is reduced as much as possible, and the accuracy is improved.
In one or more embodiments of the present specification, it is determined that the judgment matrix has consistency, and scores and dimension weights under each dimension of an enterprise are determined; and determining that the judgment matrix does not have consistency, adjusting the judgment matrix, and judging the consistency of the adjusted judgment matrix.
In one or more embodiments of the present description, the dimension weights are hierarchically ordered.
Judging whether the constructed judgment matrix has consistency, carrying out normalization processing on each column of the judgment matrix, then dividing each component in any column after normalization by the corresponding component in all the columns in the matrix, and if all the element values in the obtained new matrix are 1, determining that the judgment matrix meets the requirement of complete consistency (at the moment, CR is 0); if all the element values in the matrix are close to 1, the consistency of the judgment matrix should be good (at this time, CR < 0.1); if some element values deviate from 1 greatly, the consistency of the judgment matrix is poor (in this case, CR > is 0.1), and the matrix needs to be adjusted. Recalculating the consistency index CR of the adjusted judgment matrix, and finishing the adjustment if CR is less than 0.1; otherwise, repeating the steps until the consistency requirement is met.
If the judgment matrix is a consistency matrix, judging that the eigenvector corresponding to the maximum eigenvalue of the matrix corresponds to the weight vector, calculating a single-level ranking weight vector and consistency check, and calculating a total-level ranking weight and consistency check to obtain the score and the dimension weight of the enterprise under each dimension. The hierarchical single ordering refers to the importance ordering of the factors of the hierarchy, and the hierarchical total ordering refers to the ordering of the relative importance of the factors of all the layers.
In one or more embodiments of the present description, correlation analysis is performed on variables to obtain a correlation analysis result; and determining strong correlation variables according to the correlation analysis result, and reserving one variable in the strong correlation variables.
In one or more embodiments of the present disclosure, an IV value of each variable is calculated, if the IV value is greater than a first preset value, a correlation coefficient calculation is performed on the variable corresponding to the IV value, and if the correlation coefficient is less than a second preset value, it is determined that the variable is weakly correlated or does not exist, and the variable is retained.
The variables should describe the enterprise as much as possible, such as describing the development prospect of the enterprise, the development status of the industry to which the enterprise belongs, and the like.
Calculating Information Values (IV) of the variables, wherein the IV values are used for measuring the prediction capability of the variables, and screening the IV values of the variables to leave the variables with the IV values larger than a first preset Value, wherein the first preset Value can be 0.01, and is not particularly limited. After removing the variables with IV values larger than the first preset value, there are many variables, the number of the variables is still large, and there may be strong correlation between the variables. And if the credit score rating of the enterprise is measured by using variables with strong correlation, the accuracy is high. For example, the number of credit report queries is assessed in the last 3 months, 6 months, 12 months and 24 months, and strong correlation may exist between the four variables.
And (4) carrying out correlation coefficient analysis on the variables retained by the IV value screening. The method for measuring the magnitude of the correlation between the variables comprises a correlation coefficient calculation method, if the correlation coefficient is greater than a second preset value, the correlation exists between the variables, and the second preset value can be 0.5, which is not limited. For the variables with the correlation, the variables with large IV values in the variables with the correlation are reserved. If the correlation coefficient is smaller than the preset value, the variables are directly reserved if correlation or nonexistence exists.
In one or more embodiments of the present disclosure, the reserved variables are grouped, and a ratio of the grouped variables in the grouping is greater than a third preset value.
S103: and (3) establishing a credit evaluation model by using the model-entering index through a logistic regression algorithm and the AHP analytic hierarchy process, and generating a general score of the enterprise through the credit evaluation model.
In one or more embodiments of the present description, the variables in the model-entering index are selected to establish the credit evaluation model through a variable selection method provided by a logistic regression algorithm.
The reserved variables are grouped, and the grouping can be a coarse grouping. The coarse grouping of the variables refers to merging the retained variable values, and combining the similar default rates together mainly according to the Evidence Weight (WOE) values and default rates corresponding to the variable groups. And dividing each variable into 4-5 groups, and ensuring that the occupation ratio of each group is not less than a third preset value, wherein the third preset value can be 5%.
The variable selection method comprises the steps of using all variables, forward selection, reverse selection, step-by-step selection and an optimal score statistical model. Using all variables allows one to see how much all variables contribute to the model. The forward selection allows significant variables to enter the model. The reverse selection gives each variable the opportunity to enter the model, but after the variable is removed, it must not re-enter the model even if it subsequently becomes significant. The stepwise selection allows both the opportunity to enter all variables into the model and the opportunity to remove the model from variables that are significant in the early stages and not significant in the late stages. The optimal score statistical model selects variables based on the score statistics notability, and then adds or removes variables in the model. In the present specification embodiment, an optimal score statistical model is used.
S104: and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
The credit score rating comprises a credit score and a credit rating of the enterprise, the credit score comprises scores under all dimensions, such as an enterprise industry score, a development score, an operation score and the like, the dimension weight refers to the proportion of all the dimensions, the enterprise general score is an overall score of the enterprise, the overall score is not necessarily a percentage system, and the percentage system credit score is obtained according to the proportion of the score under all the dimensions to all the dimensions and the overall score. The credit rating may be expressed by methacetin or a, AAAAA represents the highest credit rating, and a represents the difference in credit rating, and the method of expressing the credit rating is not particularly limited.
Fig. 4 is a schematic structural diagram of an enterprise credit risk assessment device provided in one or more embodiments of the present specification, where the device includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform:
acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse;
processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and determining scores and dimension weights of the enterprise under each dimension by using the model entering index;
establishing a credit evaluation model by using the model entry indexes through a logistic regression algorithm and the AHP analytic hierarchy process in a combined manner, and generating a general score of the enterprise through the credit evaluation model;
and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
At least one technical scheme adopted by one or more embodiments of the specification solves the problems that the enterprise financing is difficult and slow due to the fact that the enterprise cannot be rapidly and accurately graded by credit scoring. A large amount of real and reliable enterprise related data are obtained through an ETL technology and a knowledge graph construction technology, a credit evaluation model is established through the combination of an AHP analytic hierarchy process and a logistic regression algorithm, risk assessment is conducted on the enterprise, and the problem that the enterprise financing is difficult and slow is solved.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. An enterprise credit risk assessment method, comprising:
acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse;
processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and determining scores and dimension weights of the enterprise under each dimension by using the model entering index;
establishing a credit evaluation model by using the model-entering index through a logistic regression algorithm and the AHP analytic hierarchy process, and generating a general score of the enterprise through the credit evaluation model;
and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
2. The method according to claim 1, wherein the obtaining of the enterprise-related data, the processing of the enterprise-related data to obtain the index data, specifically comprises:
acquiring the related data of the enterprise through data extraction, and cleaning, converting and loading the related data;
and processing the cleaned, converted and loaded related data by using a data processing method to obtain index data.
3. The method of claim 1, wherein the processing the index data stored in the data warehouse by AHP analytic hierarchy process to determine an input index, and using the input index to calculate scores and dimension weights for each dimension of the enterprise comprises:
carrying out hierarchical processing on the index data according to the mutual relation, and establishing a hierarchical structure model, wherein the hierarchical structure model is used for dividing the dimensionality of a variable corresponding to the index data;
and constructing a judgment matrix in a layered mode according to the hierarchical structure model, carrying out consistency check on the judgment matrix, and judging whether the judgment matrix has consistency.
4. The method of claim 3, further comprising:
determining the consistency of the judgment matrix, and determining the scores and the dimension weights of the enterprises under all dimensions;
and determining that the judgment matrix does not have consistency, adjusting the judgment matrix, and judging the consistency of the adjusted judgment matrix.
5. The method of claim 4, further comprising:
and carrying out hierarchical ordering on the dimension weight.
6. The method of claim 4, further comprising:
carrying out correlation analysis on the variables to obtain correlation analysis results;
and determining strong correlation variables according to the correlation analysis result, and reserving one variable in the strong correlation variables.
7. The method according to claim 6, wherein the performing correlation analysis on the variables to obtain correlation analysis results specifically comprises:
calculating the IV value of each variable, if the IV value is larger than a first preset value, calculating the correlation coefficient of the variable corresponding to the IV value, if the correlation coefficient is smaller than a second preset value, determining that the variable is weakly correlated or does not exist, and reserving the variable.
8. The method of claim 7, further comprising:
and grouping the reserved variables, wherein the proportion of the grouped variables in the grouping is larger than a third preset value.
9. The method of claim 1, wherein the using the model-entry index to jointly establish a credit evaluation model through a logistic regression algorithm and the AHP analytic hierarchy process specifically comprises:
and selecting the variables in the model entry indexes through a variable selection method by the logistic regression algorithm to establish a credit evaluation model.
10. An enterprise credit risk assessment device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform:
acquiring related data of an enterprise, processing the related data to obtain index data, and storing the index data in a data warehouse;
processing the index data stored in the data warehouse through an AHP analytic hierarchy process to determine a model entering index, and determining scores and dimension weights of the enterprise under each dimension by using the model entering index;
establishing a credit evaluation model by using the model-entering index through a logistic regression algorithm and the AHP analytic hierarchy process, and generating a general score of the enterprise through the credit evaluation model;
and obtaining the credit score rating of the enterprise according to the score of each dimension of the enterprise, the dimension weight and the general score of the enterprise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110899.2A CN112668945A (en) | 2021-01-27 | 2021-01-27 | Enterprise credit risk assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110899.2A CN112668945A (en) | 2021-01-27 | 2021-01-27 | Enterprise credit risk assessment method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112668945A true CN112668945A (en) | 2021-04-16 |
Family
ID=75414729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110110899.2A Pending CN112668945A (en) | 2021-01-27 | 2021-01-27 | Enterprise credit risk assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668945A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538133A (en) * | 2021-07-26 | 2021-10-22 | 天元大数据信用管理有限公司 | Credit evaluation method, device and medium based on limited Boltzmann machine |
| CN113674081A (en) * | 2021-07-30 | 2021-11-19 | 浙江创邻科技有限公司 | Graph database-based wind control management system and method for small and medium-sized enterprises |
| CN113837859A (en) * | 2021-08-25 | 2021-12-24 | 天元大数据信用管理有限公司 | Small and micro enterprise portrait construction method |
| CN113988726A (en) * | 2021-12-28 | 2022-01-28 | 江苏荣泽信息科技股份有限公司 | Enterprise industry credit evaluation management system based on block chain |
| CN114022261A (en) * | 2021-10-13 | 2022-02-08 | 成都寻道数财科技有限公司 | System for college teacher financial credit evaluation |
| CN114266651A (en) * | 2021-12-27 | 2022-04-01 | 天元大数据信用管理有限公司 | A method, device and medium for batch acquisition of sample indicators and storage |
| CN115456753A (en) * | 2022-09-07 | 2022-12-09 | 安徽省优质采科技发展有限责任公司 | Enterprise credit information analysis method and system for bidding platform |
| CN116307811A (en) * | 2022-12-19 | 2023-06-23 | 武汉中科通达高新技术股份有限公司 | Method and device for automatically grading enterprise index data in staged mode |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132269A1 (en) * | 2010-08-06 | 2013-05-23 | The Dun And Bradstreet Corporation | Method and system for quantifying and rating default risk of business enterprises |
| CN106940833A (en) * | 2017-01-13 | 2017-07-11 | 国网浙江省电力公司经济技术研究院 | A kind of power grid enterprises' sale of electricity side methods of risk assessment based on fuzzy number and improved AHP method |
| CN110378545A (en) * | 2018-04-13 | 2019-10-25 | 北京三快在线科技有限公司 | Trade company's credit estimation method and device, storage medium, electronic equipment |
| CN112053234A (en) * | 2020-09-04 | 2020-12-08 | 天元大数据信用管理有限公司 | Enterprise credit rating method based on macroscopic region economic index and microscopic factor |
-
2021
- 2021-01-27 CN CN202110110899.2A patent/CN112668945A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132269A1 (en) * | 2010-08-06 | 2013-05-23 | The Dun And Bradstreet Corporation | Method and system for quantifying and rating default risk of business enterprises |
| CN106940833A (en) * | 2017-01-13 | 2017-07-11 | 国网浙江省电力公司经济技术研究院 | A kind of power grid enterprises' sale of electricity side methods of risk assessment based on fuzzy number and improved AHP method |
| CN110378545A (en) * | 2018-04-13 | 2019-10-25 | 北京三快在线科技有限公司 | Trade company's credit estimation method and device, storage medium, electronic equipment |
| CN112053234A (en) * | 2020-09-04 | 2020-12-08 | 天元大数据信用管理有限公司 | Enterprise credit rating method based on macroscopic region economic index and microscopic factor |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538133A (en) * | 2021-07-26 | 2021-10-22 | 天元大数据信用管理有限公司 | Credit evaluation method, device and medium based on limited Boltzmann machine |
| CN113674081A (en) * | 2021-07-30 | 2021-11-19 | 浙江创邻科技有限公司 | Graph database-based wind control management system and method for small and medium-sized enterprises |
| CN113674081B (en) * | 2021-07-30 | 2023-12-19 | 浙江创邻科技有限公司 | System and method for wind control management of middle and small enterprises based on graph database |
| CN113837859A (en) * | 2021-08-25 | 2021-12-24 | 天元大数据信用管理有限公司 | Small and micro enterprise portrait construction method |
| CN113837859B (en) * | 2021-08-25 | 2024-05-14 | 天元大数据信用管理有限公司 | Image construction method for small and micro enterprises |
| CN114022261A (en) * | 2021-10-13 | 2022-02-08 | 成都寻道数财科技有限公司 | System for college teacher financial credit evaluation |
| CN114266651A (en) * | 2021-12-27 | 2022-04-01 | 天元大数据信用管理有限公司 | A method, device and medium for batch acquisition of sample indicators and storage |
| CN113988726A (en) * | 2021-12-28 | 2022-01-28 | 江苏荣泽信息科技股份有限公司 | Enterprise industry credit evaluation management system based on block chain |
| CN115456753A (en) * | 2022-09-07 | 2022-12-09 | 安徽省优质采科技发展有限责任公司 | Enterprise credit information analysis method and system for bidding platform |
| CN116307811A (en) * | 2022-12-19 | 2023-06-23 | 武汉中科通达高新技术股份有限公司 | Method and device for automatically grading enterprise index data in staged mode |
| CN116307811B (en) * | 2022-12-19 | 2024-02-20 | 武汉中科通达高新技术股份有限公司 | Method and device for automatically grading enterprise index data in staged mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112668945A (en) | Enterprise credit risk assessment method and device | |
| Storz et al. | Do we want these two to tango? On zombie firms and stressed banks in Europe | |
| Barr et al. | Forecasting bank failure: A non-parametric frontier estimation approach | |
| Roy et al. | A credit scoring model for SMEs using AHP and TOPSIS | |
| CN112348654A (en) | Automatic assessment method, system and readable storage medium for enterprise credit line | |
| CN111754116B (en) | Credit evaluation method and device based on label portrait technology | |
| Catanach et al. | An ex post examination of auditor resignations | |
| Klieštik et al. | Prediction of financial health of business entities in transition economies | |
| CN113763154A (en) | A financial risk assessment method of steel trade supply chain based on fuzzy grey evaluation | |
| Chi et al. | Debt rating model based on default identification: Empirical evidence from Chinese small industrial enterprises | |
| CN113065969A (en) | Enterprise scoring model construction method, enterprise scoring method, medium and electronic device | |
| Hodžić | Bosnia and Herzegovina | |
| CN116468273A (en) | Customer risk identification method and device | |
| Mačerinskiene et al. | The evaluation model of a commercial bank loan portfolio | |
| Cucaro | The bankruptcy prediction model Z-ScoreM for Italian Manufacturing Listed Companies and Z'-ScoreM for Italian Industrial Company | |
| Önder et al. | Comparing macroeconomic performance of the union for the mediterranean countries using grey relational analysis and multi-dimensional scaling | |
| Widnyana et al. | Effect of Company Size, Profitability and Capital Structure on Firm Value in Indonesia | |
| KR20180104967A (en) | Investment Value Index and Model | |
| Ezeibekwe | Stock market development and economic growth: Empirical evidence from Nigeria | |
| CN107977804B (en) | A risk assessment method for confirming warehouse business | |
| Iftikhar et al. | Does Intellectual Capital Efficiency Matter for Firms' Investment Efficiency? | |
| Onyiri | Predicting Financial Distress using Altman's Z-score and the Sustainable Growth Rate | |
| Petrová et al. | Methods of evaluating international risks in the insurance market | |
| Javadi et al. | Financial Performance Evaluation of the Gas Distribution Companies of National Iranian Gas Company | |
| Jawad et al. | Using Decision Tree Technique to Predict the Financial Collapse of Iraqi Private Banks: An Applied Study |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |
|
| RJ01 | Rejection of invention patent application after publication |