CN111415239A - Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information - Google Patents
Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information Download PDFInfo
- Publication number
- CN111415239A CN111415239A CN201911145793.5A CN201911145793A CN111415239A CN 111415239 A CN111415239 A CN 111415239A CN 201911145793 A CN201911145793 A CN 201911145793A CN 111415239 A CN111415239 A CN 111415239A
- Authority
- CN
- China
- Prior art keywords
- referee
- document
- medium
- information
- small
- 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
- 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
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a credit risk prediction method and system for small and medium-sized enterprises fusing judicial soft information, and relates to the technical field of data processing. Firstly, acquiring structural information of a referee document based on the predicted referee document of a medium-sized and small enterprise; acquiring the financial information of the predicted medium and small enterprises; then screening the referee document based on the structured information of the referee document to obtain the predicted effective referee document of the medium and small enterprises; carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document; and finally, predicting the default probability of the medium and small enterprises based on the case and account, the characteristic amount, the financial information and the logistic regression model related to the default. The invention extracts non-financial characteristics from the referee document to carry out default prediction, effectively relieves the problem of information asymmetry between medium and small enterprises and loan institutions, and improves the accuracy of credit risk prediction.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a credit risk prediction method and system for small and medium-sized enterprises by fusing judicial soft information.
Background
As a key component of the development of the economic society, small and medium-sized enterprises play an important role in supporting the rapid growth of the economy of China, solving the employment of labor force, improving the technological innovation capability and the like. In the development process of small and medium-sized enterprises, financing is often required in the form of credit loan due to the reasons of insufficient mortgage and the like, and the financing mode needs to evaluate the credit risk of the enterprises.
A common credit risk prediction method in the prior art is to predict whether a default will occur to an enterprise based on structured information such as finance and the like. The method specifically comprises the step of evaluating the operation condition, the operation scale and the like of the enterprise by analyzing financial information (a quick action rate, an asset liability rate, an asset turnover rate and the like) of the enterprise. In addition, the use of non-financial information to assess credit risk to a business is also receiving increasing attention. These non-financial information mainly includes: text information in the financial statement, enterprise supply chain information, enterprise basic information (such as the number of employees, registered capital, geographic position, established years and the like) and the like.
However, the inventor of the present application finds that, due to the characteristics of non-standard management, non-transparent financial data, imperfect data disclosure mechanism and the like of medium and small enterprises, the problem of information asymmetry between the medium and small enterprises and the loan institution is serious, and thus the accuracy of the result of credit risk prediction is low.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a method and a system for predicting credit risk of small and medium-sized enterprises by fusing judicial soft information, and solves the technical problem of low accuracy of the result of credit risk prediction of the small and medium-sized enterprises in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention provides a credit risk prediction method for a medium-sized and small enterprise fusing judicial soft information, which is executed by a computer and comprises the following steps:
acquiring financial information and a referee document of a predicted medium-sized and small enterprise, and acquiring structural information of the referee document based on the referee document;
screening the referee document based on the structural information of the referee document to obtain the effective referee document of the predicted medium and small enterprises;
carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document;
and predicting the default probability of the medium and small enterprises based on the case and account related to the default, the characteristic amount, the financial information and a logistic regression model.
Preferably, the structured information of the official document includes: case number, referee document date, litigation status of the enterprise in the referee document, case order, referee result and referee amount.
Preferably, the screening the referee document based on the structured information of the referee document to obtain an effective referee document includes:
combing the relation between the referee documents according to the case number, and keeping the final referee document in the same case;
calculating the year difference between the date of the official document and the loan application date, and reserving the official document two years before the loan application date;
the litigation status in the referee documents is set as non-negative and negative, the referee document judgment results are divided into negative and non-negative, and the referee documents with negative litigation status and judgment results are reserved;
the official documents meeting the three conditions of negative final official, two years before the loan application date and litigation status and the trial result in the same case form an effective official document.
Preferably, before the step of selecting features of cases in the active official document, the method further comprises:
carrying out vector representation on the effective referee document to obtain a referee document vector;
and obtaining the predicted medium and small enterprise vectors based on the referee document vectors, and adding the referee document vectors to obtain the predicted medium and small enterprise vectors when the predicted medium and small enterprises have a plurality of referee documents.
Preferably, the characteristic selection of the case law in the effective official document to obtain the case law related to the default includes:
and performing feature selection on the predicted case routes in the medium and small-sized enterprise vectors based on chi-square and logistic regression methods to obtain case routes related to default.
Preferably, the constructing a feature amount based on the financial information and the structured information of the effective official document includes:
and constructing a characteristic amount based on the predicted trial amount in the vector of the medium and small enterprises and the average value of the business income of the major and minor enterprises in the years related to all the official documents of the medium and small enterprises in the financial information.
The invention also provides a credit risk prediction system of the medium and small enterprises fusing the judicial soft information, which comprises a computer, wherein the computer comprises:
at least one memory cell;
at least one processing unit;
wherein the at least one memory unit has stored therein at least one instruction that is loaded and executed by the at least one processing unit to perform the steps of:
acquiring the financial information and the referee document of the predicted medium and small enterprises, and acquiring the structural information of the referee document based on the referee document;
screening the referee document based on the structural information of the referee document to obtain the effective referee document of the predicted medium and small enterprises;
carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document;
and predicting the default probability of the medium and small enterprises based on the case and account related to the default, the characteristic amount, the financial information and a logistic regression model.
Preferably, the structured information of the official document includes: case number, referee document date, litigation status of the enterprise in the referee document, case order, referee result and referee amount.
Preferably, the screening the referee document based on the structured information of the referee document to obtain an effective referee document includes:
combing the relation between the referee documents according to the case number, and keeping the final referee document in the same case;
calculating the year difference between the date of the official document and the loan application date, and reserving the official document two years before the loan application date;
the litigation status in the referee documents is set as non-negative and negative, the referee document judgment results are divided into negative and non-negative, and the referee documents with negative litigation status and judgment results are reserved;
the official documents meeting the three conditions of negative final official, two years before the loan application date and litigation status and the trial result in the same case form an effective official document.
Preferably, before the step of selecting features of cases in the active official document, the method further comprises:
carrying out vector representation on the effective referee document to obtain a referee document vector;
and obtaining the predicted medium and small enterprise vectors based on the referee document vectors, and adding the referee document vectors to obtain the predicted medium and small enterprise vectors when the predicted medium and small enterprises have a plurality of referee documents.
(III) advantageous effects
The invention provides a credit risk prediction method and system for small and medium-sized enterprises by fusing judicial soft information. Compared with the prior art, the method has the following beneficial effects:
firstly, acquiring structural information of a referee document based on the predicted referee document of a medium-sized and small enterprise; acquiring the financial information of the predicted medium and small enterprises; then screening the referee document based on the structured information of the referee document to obtain the predicted effective referee document of the medium and small enterprises; carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document; and finally, predicting the default probability of the medium and small enterprises based on the case and account, the characteristic amount, the financial information and the logistic regression model related to the default. The invention extracts non-financial characteristics from the referee document to carry out default prediction, effectively relieves the problem of information asymmetry between small and medium-sized enterprises and loan institutions, improves the accuracy of credit risk prediction, can effectively help financial institutions such as banks and the like to identify the small and medium-sized enterprises which will have default, and reduces financial risks. Meanwhile, the official document data is disclosed in the Chinese official document network, so that the authority is provided, and the authenticity and reliability of the data can be ensured. In addition, the openness of the official document also reduces the cost of data collection by financial institutions such as banks.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings 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 of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a block diagram of a credit risk prediction method for a medium-sized and small enterprise fusing judicial soft information according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but 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 invention.
The embodiment of the application provides the credit risk prediction method and the credit risk prediction system for the medium and small enterprises fusing judicial soft information, solves the technical problem that the result accuracy of the credit risk prediction of the medium and small enterprises in the prior art is low, improves the accuracy of the credit risk prediction, effectively helps financial institutions such as banks to identify the medium and small enterprises which will be violated, and reduces financial risks.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
the embodiment of the invention firstly obtains the structural information of the referee document based on the predicted referee document of the medium and small enterprises; acquiring the financial information of the predicted medium and small enterprises; then screening the referee document based on the structured information of the referee document to obtain the predicted effective referee document of the medium and small enterprises; carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document; and finally, predicting the default probability of the medium and small enterprises based on the case and account, the characteristic amount, the financial information and the logistic regression model related to the default. The embodiment of the invention extracts non-financial characteristics from the referee document to carry out default prediction, effectively relieves the problem of information asymmetry between small and medium-sized enterprises and loan institutions, and improves the accuracy of credit risk prediction.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
The invention provides a credit risk prediction method for medium and small enterprises fusing judicial soft information, which is executed by a computer and comprises the following steps of S1-S4:
s1, acquiring the financial information and the referee document of the predicted medium and small enterprises, and acquiring the structural information of the referee document based on the referee document;
s2, screening the referee documents based on the structural information of the referee documents, and acquiring the effective referee documents of the predicted medium and small enterprises;
s3, selecting the characteristics of case routing in the effective official document, acquiring case routing related to default, and constructing characteristics amount based on financial information and the structural information of the effective official document;
and S4, predicting the default probability of the medium and small enterprises based on the case and account, the characteristic amount, the financial information and the logistic regression model related to the default.
The embodiment of the invention extracts non-financial characteristics from the referee document to carry out default prediction, effectively relieves the problem of information asymmetry between small and medium-sized enterprises and loan institutions, and improves the accuracy of credit risk prediction.
The individual steps are described in detail below:
in step S1, the financial information and the official document of the predicted medium-sized and small business are acquired, and the structured information of the official document is acquired based on the official document. The method specifically comprises the following steps:
acquiring the referee document and financial information of the predicted medium and small enterprises through a web crawler technology or manual input, and extracting the following structured information from the referee document: case number, referee document date, litigation status of the enterprise in the referee document, case order, trial result and trial amount.
In step S2, the official document is screened based on the structured information of the official document, and an effective official document of the predicted middle-sized and small-sized enterprise is obtained. The method specifically comprises the following steps:
s201, combing the relation among the referee documents according to case numbers, and only keeping the referee documents which are finally judged in the same case.
S202, calculating the year difference between the date of the official document and the date of the loan application, and obtaining the year difference with high default correlation within 2 years by the chi-square inspection and logistic regression method, so that the official document two years before the date of the loan application is reserved.
S203, the litigation status in the referee document is divided into non-negative status (original report, third party and the like) and negative status (reported and the like), the referee result of the referee document is divided into non-negative status (withdrawal is allowed, the referee is compensated and the like) and negative status (loss of the referee, compensation of goods money of the referee and the like), the negative status and the non-negative status of the litigation status and the referee result are arranged and combined, and the prediction capability of the referee document with the litigation status and the referee result being negative at the same time is the best for experimental verification. Therefore, the status of litigation is kept and the judge result is negative judge document.
S204, the official documents meeting the three conditions that the final official in the same case, two years before the loan application date, and both the litigation status and the trial result are negative are taken as effective official documents.
In step S3, a case in the active official document is feature-selected, a case related to the default is obtained, and a feature amount is constructed based on the financial information and the structured information of the active official document. The method specifically comprises the following steps:
s301, carrying out vector representation on the effective referee document to obtain a referee document vector. As valid referee document JiIs (Tu is 1)iA table composed of 2i… …, case by niAmount of triali) And i represents the ith official document. In the effective referee document i, the case 1 is recorded when the case is appeared, and the case 0 is recorded when the case is not appeared.
Based on the judgment document vector, obtaining the predicted medium and small enterprise vector, and adding the judgment document vectors when the predicted medium and small enterprise has a plurality of judgment documents to obtain the predicted medium and small enterprise vector Em=∑Jt(wherein m ═ 1, 2, 3, … …), EmIs a vector representation of enterprise m, t is an integer, JtIs a vector representation of the document t belonging to enterprise m). E.g., enterprise m vector denoted as EmIs (Tu is 1)mA table composed of 2m… …, case by nmAmount of trialm) And the enterprise without the referee document is a zero vector, and a predicted medium and small enterprise vector is obtained.
S302, carrying out feature selection on the case routes in the predicted medium and small enterprise vectors by using a chi-square and logistic regression method, and finding out case routes related to default. In the embodiment of the invention, the cases related to the default comprise borrowing contract disputes, production management disputes and operation contract disputes.
S303, acquiring a characteristic amount according to the trial amount in the enterprise vector E and the average value of the business income of the major operation of the year (avg (business income of major operation in the year)) related to all the official documents of the enterprise in the financial information;
in step S4, the default probability of the small and medium-sized enterprises is predicted based on the scenario, the characteristic amount, the financial information and the logistic regression model related to the default. The method specifically comprises the following steps:
and inputting the default correlation case, the characteristic amount and the financial information into a logistic regression model, and predicting the default probability of the small and medium enterprises according to the output of the logistic regression model. The logistic regression formula is as follows:
wherein:
y is the probability of breach;
θ0is a constant term;
θ*is a coefficient vector, θ*=(θ* 1,θ* 2,θ* 3…θ* k…θ* k+m+1);
Is an error term;
fithe financial characteristics in the financial information are represented, i is 1, 2, … … k, and k is the number of the financial characteristics;
djj is 1, 2, … … m, and m is the number of the default related cases.
Logistic regression is interpretable, it can be observed through the coefficients of the variables in the model results which variables will affect the violations, the degree of significance, and whether the effect between a variable and a violation is positive or negative.
The embodiment of the invention also provides a credit risk prediction system for medium and small enterprises fusing judicial soft information, which comprises a computer, wherein the computer comprises:
at least one memory cell;
at least one processing unit;
wherein, at least one instruction is stored in the at least one storage unit, and the at least one instruction is loaded and executed by the at least one processing unit to realize the following steps:
acquiring the financial information and the referee document of the predicted medium and small enterprises, and acquiring the structural information of the referee document based on the referee document;
screening the referee document based on the structured information of the referee document to obtain the effective referee document of the predicted medium and small enterprises;
carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document;
and predicting the default probability of the small and medium-sized enterprises based on the case and account, the characteristic amount, the financial information and the logistic regression model related to the default.
It can be understood that the above-mentioned system for predicting credit risk of a medium-sized and small enterprise fusing judicial soft information provided by the embodiment of the present invention corresponds to the above-mentioned method for predicting credit risk of a medium-sized and small enterprise fusing judicial soft information, and the explanation, examples, and beneficial effects of the relevant contents thereof may refer to the corresponding contents in the method for predicting credit risk of a medium-sized and small enterprise fusing judicial soft information, and are not described herein again.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the embodiment of the invention extracts non-financial characteristics from the referee document to carry out default prediction, effectively relieves the problem of information asymmetry between small and medium-sized enterprises and loan institutions, improves the accuracy of credit risk prediction, can effectively help financial institutions such as banks and the like to identify small and medium-sized enterprises which will have default, and reduces financial risks.
2. The referee document data in the embodiment of the invention is disclosed in the Chinese referee document network, has authority and can ensure the authenticity and reliability of the data. In addition, the openness of the official document also reduces the cost of data collection by financial institutions such as banks.
It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A credit risk prediction method for small and medium-sized enterprises fusing judicial soft information is characterized in that the method is executed by a computer and comprises the following steps:
acquiring financial information and a referee document of a predicted medium-sized and small enterprise, and acquiring structural information of the referee document based on the referee document;
screening the referee document based on the structural information of the referee document to obtain the effective referee document of the predicted medium and small enterprises;
carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document;
and predicting the default probability of the medium and small enterprises based on the case and account related to the default, the characteristic amount, the financial information and a logistic regression model.
2. The method for forecasting the credit risk of the medium and small enterprises fusing the judicial soft information as claimed in claim 1, wherein the structured information of the referee document comprises: case number, referee document date, litigation status of the enterprise in the referee document, case order, referee result and referee amount.
3. The method for forecasting the credit risk of the medium and small enterprises fusing the judicial soft information as claimed in claim 2, wherein the step of screening the official document based on the structured information of the official document to obtain the effective official document comprises the following steps:
combing the relation between the referee documents according to the case number, and keeping the final referee document in the same case;
calculating the year difference between the date of the official document and the loan application date, and reserving the official document two years before the loan application date;
the litigation status in the referee documents is set as non-negative and negative, the referee document judgment results are divided into negative and non-negative, and the referee documents with negative litigation status and judgment results are reserved;
the official documents meeting the three conditions of negative final official, two years before the loan application date and litigation status and the trial result in the same case form an effective official document.
4. The method for predicting credit risk of small and medium-sized enterprises fusing judicial soft information as claimed in claim 2, wherein before the step of selecting characteristics of case routing in effective referee documents, the method further comprises:
carrying out vector representation on the effective referee document to obtain a referee document vector;
and obtaining the predicted medium and small enterprise vectors based on the referee document vectors, and adding the referee document vectors to obtain the predicted medium and small enterprise vectors when the predicted medium and small enterprises have a plurality of referee documents.
5. The method for predicting the credit risk of the medium and small enterprises fusing the judicial soft information as claimed in claim 4, wherein the step of performing feature selection on case routes in the effective referee documents to obtain case routes related to the default comprises the following steps:
and performing feature selection on the predicted case routes in the medium and small-sized enterprise vectors based on chi-square and logistic regression methods to obtain case routes related to default.
6. The method for forecasting credit risk of middle and small enterprises fusing judicial soft information as claimed in claim 4, wherein the constructing the characteristic amount based on the financial information and the structured information of the effective official document comprises:
and constructing a characteristic amount based on the predicted trial amount in the vector of the medium and small enterprises and the average value of the business income of the major and minor enterprises in the years related to all the official documents of the medium and small enterprises in the financial information.
7. A credit risk prediction system for a medium and small enterprise fusing judicial soft information, which is characterized by comprising a computer, wherein the computer comprises:
at least one memory cell;
at least one processing unit;
wherein the at least one memory unit has stored therein at least one instruction that is loaded and executed by the at least one processing unit to perform the steps of:
acquiring the financial information and the referee document of the predicted medium and small enterprises, and acquiring the structural information of the referee document based on the referee document;
screening the referee document based on the structural information of the referee document to obtain the effective referee document of the predicted medium and small enterprises;
carrying out feature selection on case routes in the effective referee document, acquiring case routes related to default, and constructing a feature amount based on the financial information and the structural information of the effective referee document;
and predicting the default probability of the medium and small enterprises based on the case and account related to the default, the characteristic amount, the financial information and a logistic regression model.
8. The system of claim 7, wherein the structured information of the official document comprises: case number, referee document date, litigation status of the enterprise in the referee document, case order, referee result and referee amount.
9. The system for forecasting credit risk of middle and small enterprises with soft judicial information fusion of claim 8, wherein the screening of referee documents based on the structured information of the referee documents to obtain valid referee documents comprises:
combing the relation between the referee documents according to the case number, and keeping the final referee document in the same case;
calculating the year difference between the date of the official document and the loan application date, and reserving the official document two years before the loan application date;
the litigation status in the referee documents is set as non-negative and negative, the referee document judgment results are divided into negative and non-negative, and the referee documents with negative litigation status and judgment results are reserved;
the official documents meeting the three conditions of negative final official, two years before the loan application date and litigation status and the trial result in the same case form an effective official document.
10. The method for predicting credit risk of small and medium-sized enterprises fusing judicial soft information as claimed in claim 8, wherein before the step of selecting characteristics of case routing in effective referee documents, the method further comprises:
carrying out vector representation on the effective referee document to obtain a referee document vector;
and obtaining the predicted medium and small enterprise vectors based on the referee document vectors, and adding the referee document vectors to obtain the predicted medium and small enterprise vectors when the predicted medium and small enterprises have a plurality of referee documents.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911145793.5A CN111415239A (en) | 2019-11-21 | 2019-11-21 | Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911145793.5A CN111415239A (en) | 2019-11-21 | 2019-11-21 | Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111415239A true CN111415239A (en) | 2020-07-14 |
Family
ID=71490710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911145793.5A Pending CN111415239A (en) | 2019-11-21 | 2019-11-21 | Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111415239A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160000A (en) * | 2021-04-22 | 2021-07-23 | 广州广电运通信息科技有限公司 | Legal information analysis method, system, device and storage medium |
CN116342332A (en) * | 2023-05-31 | 2023-06-27 | 合肥工业大学 | Auxiliary judging method, device, equipment and storage medium based on Internet |
-
2019
- 2019-11-21 CN CN201911145793.5A patent/CN111415239A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160000A (en) * | 2021-04-22 | 2021-07-23 | 广州广电运通信息科技有限公司 | Legal information analysis method, system, device and storage medium |
CN116342332A (en) * | 2023-05-31 | 2023-06-27 | 合肥工业大学 | Auxiliary judging method, device, equipment and storage medium based on Internet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sadok et al. | Artificial intelligence and bank credit analysis: A review | |
Florackis et al. | Cybersecurity risk | |
CN112750029A (en) | Credit risk prediction method, device, electronic equipment and storage medium | |
CN112613977A (en) | Personal credit loan admission credit granting method and system based on government affair data | |
Amin et al. | Application of optimistic and pessimistic OWA and DEA methods in stock selection | |
CN115271912A (en) | Credit business intelligent wind control approval system and method based on big data | |
CN115422173A (en) | Data management method and system in financial credit field | |
Boussaada et al. | Is there a threshold effect in the liquidity risk–non‐performing loans relationship? A PSTR approach for MENA banks | |
CN111415239A (en) | Small and medium-sized enterprise credit risk prediction method and system fusing judicial soft information | |
Adebiyi | Exploring the impact of predictive analytics on accounting and auditing expertise: A regression analysis of LinkedIn survey data | |
Sampagnaro et al. | Monitoring in small business lending: How to observe the unobservable | |
Gupta | Financial determinants of corporate credit ratings: An Indian evidence | |
Wu et al. | Application analysis of credit scoring of financial institutions based on machine learning model | |
Ozlanski et al. | Kabbage: A fresh approach to understanding fundamental auditing concepts and the effects of disruptive technology | |
Liao et al. | Enterprise financial influencing factors and early warning based on decision tree model | |
Song et al. | Insurance as a risk management tool for ADR implementation in construction disputes | |
CN114862110A (en) | Method and device for building middle platform of commercial banking business, electronic equipment and storage medium | |
Perko | Behaviour-based short-term invoice probability of default evaluation | |
Veerla | To study the impact of Artificial Intelligence as Predictive model in banking sector: Novel approach | |
Adamov | Machine learning and advanced analytics in tax fraud detection | |
Al-Delawi et al. | The Impact of Human Capital on a Company's Value: A Cross-Cultural Study | |
Bhandari et al. | Birds of a feather flock together: Institutional investors with disciplinary history and financial reporting | |
Han | The impact of Artificial Intelligence (AI) and blockchain adoption in corporate governance: ethical perspectives | |
Achary | Artificial intelligence transforming indian banking sector | |
Feng et al. | State capacity and innovation policy performance: A comparative study on two types of innovation projects in China |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200714 |