CN113837862A - Post-credit risk early warning method, device and medium based on credit investigation - Google Patents
Post-credit risk early warning method, device and medium based on credit investigation Download PDFInfo
- Publication number
- CN113837862A CN113837862A CN202111136072.5A CN202111136072A CN113837862A CN 113837862 A CN113837862 A CN 113837862A CN 202111136072 A CN202111136072 A CN 202111136072A CN 113837862 A CN113837862 A CN 113837862A
- Authority
- CN
- China
- Prior art keywords
- early warning
- post
- credit
- risk
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000011835 investigation Methods 0.000 title claims abstract description 33
- 238000003066 decision tree Methods 0.000 claims abstract description 37
- 238000012502 risk assessment Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses a credit-investigation-based post-credit risk early warning method, device and medium, wherein the method comprises the following steps: acquiring multi-source data of a business related to credit; constructing an enterprise credit investigation database based on multi-source data; determining a post-credit risk early warning index according to an enterprise credit assessment database; constructing a post-credit risk early warning model based on the post-credit risk early warning indexes; the post-loan risk early warning model is related to a decision tree; and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model. According to the method and the device, the data sources are enriched by acquiring the multi-source data of the enterprise, the post-credit risk early warning indexes are extracted from the enterprise credit investigation database formed by the multi-source data, the post-credit risk early warning models related to the decision tree are obtained by modeling the post-credit risk early warning indexes, the computing power can be reduced, the computing efficiency is improved, and meanwhile the accuracy of post-credit risk information and early warning levels of the enterprise is effectively guaranteed, so that the post-credit risk information and the early warning levels of the enterprise are pushed to financial institutions in real time.
Description
Technical Field
The application relates to the technical field of financial credit, in particular to a credit-investigation-based risk-after-credit early-warning method, device and medium.
Background
The enterprise post-credit early warning hierarchical management is one of important means for financial institutions to control credit risks of lending enterprises, and the establishment of a post-credit-check risk early warning system is particularly urgent.
Financial institutions need to intelligently acquire early warning signals that customers may influence repayment capacity and will through a powerful post-loan risk early warning system, and early warning levels of enterprise risks are judged through artificial intelligent analysis of the early warning signals of customer operation risks, judicial risks, credit risks and the like.
However, due to the complex data of the enterprise and the imperfect post-loan risk early warning system, the financial institution cannot acquire the risk information and early warning level of the enterprise in time.
Disclosure of Invention
The embodiment of the application provides a credit investigation-based risk pre-warning method, device and medium after credit loan, which are used for solving the problem that a financial institution cannot timely acquire risk information and pre-warning level of an enterprise due to the fact that the data of the enterprise is complex and a risk pre-warning system after credit loan is imperfect.
The embodiment of the application adopts the following technical scheme:
in one aspect, an embodiment of the present application provides a post-credit risk early warning method based on credit investigation, including: acquiring multi-source data of a business related to credit; constructing the enterprise credit investigation database based on the multi-source data; determining a post-credit risk early warning index according to the enterprise credit investigation database; constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree; and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
In one example, the determining a post-credit risk early warning indicator according to the enterprise credit assessment database specifically includes: extracting a post-credit risk early warning index based on the enterprise credit investigation database; determining a post-loan risk early warning index system according to the post-loan risk early warning index of the enterprise; the post-credit early warning index system comprises a first-level index, a second-level index and a third-level index; the first-level indexes are used for dividing the post-loan risk early warning dimensionality, the third-level indexes are used for dividing the post-loan risk assessment indexes, and the second-level indexes are used for assessing the early warning levels corresponding to the enterprise under the post-loan risk early warning dimensionality through the post-loan risk assessment indexes.
In one example, an index early warning level rule model is generated based on the post-credit risk early warning index; generating a single tree early warning grade and probability rule model according to the index early warning grade rule model; and generating a summary early warning grade and probability rule model according to the single tree early warning grade and probability rule model.
In one example, the generating an index early warning level rule model based on the post-credit risk early warning index specifically includes: determining a post-credit risk early warning dimensionality under the first-level index and a plurality of post-credit risk assessment indexes under the third-level indexes; under the post-credit risk early warning dimensionality, if any one of the post-credit risk assessment indexes triggers preset first early warning information, determining the early warning level of the corresponding secondary index to be a first level; if the plurality of post-loan risk assessment indexes are all the first pre-warning information which is not triggered, counting the number of indexes triggering the second pre-warning information; the risk degree corresponding to the preset second early warning information is smaller than the risk degree corresponding to the preset first early warning information; and when the index number exceeds a preset threshold value, determining the early warning level of the secondary index as the first level.
In one example, the generating a single tree early warning level and probability rule model according to the index early warning level rule model specifically includes: respectively generating a plurality of post-credit risk early warning dimensions into corresponding decision trees;
the early warning level of the corresponding secondary index in each decision tree is decided to generate the early warning probability of each decision tree, and a label corresponding to the maximum value of the early warning probability is used as the early warning label of each decision tree; and converting the early warning probability of each decision tree into the early warning grade of each decision tree.
In one example, the generating a summary early warning level and probability rule model according to the single tree early warning level and probability rule model specifically includes: determining a decision target of the hierarchical structure model as an early warning level and a decision criterion as each post-credit risk early warning dimension; determining a hierarchical analysis scoring matrix based on the hierarchical structure model, and performing consistency check on the result of the hierarchical analysis scoring matrix; if the consistency check is passed, determining the weight vector of each post-credit risk early warning dimension through an arithmetic mean method; determining early warning probability of the enterprise through a preset summarizing rule based on the weight vector; and converting the early warning probability of the enterprise into the early warning level of the enterprise.
In one example, the determining, based on the weight vector and by using a preset aggregation rule, the early warning probability of the enterprise specifically includes: if the early warning level of each decision tree comprises a first early warning level, the early warning level of the enterprise is the first early warning level and the early warning probability corresponding to the first early warning level; and if the early warning level of each decision tree does not comprise the first early warning level, determining the early warning probability of the enterprise through a preset early warning expression based on the weight vector.
In one example, after determining the risk information of the enterprise and the warning level of the risk information according to the post-credit risk warning model, the method further includes: determining a preset early warning critical value corresponding to the early warning grade; in a preset period, determining default probability of the enterprise according to a plurality of preset early warning critical values; and displaying a corresponding early warning signal according to the risk interval where the default probability is located.
On the other hand, the embodiment of the present application provides a post-credit risk early warning device based on credit investigation, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: acquiring multi-source data of a business related to credit; constructing the enterprise credit investigation database based on the multi-source data; determining a post-credit risk early warning index according to the enterprise credit investigation database; constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree; and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
In another aspect, an embodiment of the present application provides a credit-based post-credit risk early warning nonvolatile computer storage medium, which stores computer-executable instructions, where the computer-executable instructions are configured to: acquiring multi-source data of a business related to credit; constructing the enterprise credit investigation database based on the multi-source data; determining a post-credit risk early warning index according to the enterprise credit investigation database; constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree; and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
according to the method and the device, the data sources are enriched by acquiring the multi-source data of the enterprise, the post-credit risk early warning indexes are extracted from the enterprise credit investigation database formed by the multi-source data, the post-credit risk early warning models related to the decision tree are obtained by modeling the post-credit risk early warning indexes, the computing power can be reduced, the computing efficiency is improved, and meanwhile the accuracy of post-credit risk information and early warning levels of the enterprise is effectively guaranteed, so that the post-credit risk information and the early warning levels of the enterprise are pushed to financial institutions in real time.
Drawings
In order to more clearly explain the technical solutions of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which:
fig. 1 is a schematic flowchart of a post-credit risk early warning method based on credit according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of post-credit risk early warning equipment based on credit according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following embodiments and accompanying drawings. It should be apparent that the described embodiments are only some 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.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a post-credit risk early warning method based on credit according to an embodiment of the present application.
The analysis method according to the embodiment of the present application may be implemented by a terminal device or a server, and the present application is not limited to this. For convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
It should be noted that the server may be a single device, or may be a system composed of multiple devices, that is, a distributed server, which is not specifically limited in this application.
The process in fig. 1 may include the following steps:
s101: multi-source data about credit is obtained for a business.
The enterprise can be one or a plurality of enterprises, and the multi-source data comprises government data covering enterprise business, public accumulation fund, social security, water and electricity, tax, committee for improvement, bank security supervision, administrative penalty and the like, e-commerce data reflecting online operation information of the enterprise, feedback information on the enterprise network and the like.
The credit is a form of value movement conditioned on repayment and payment. Generally, the credit activities include bank deposit, loan and the like, and the credit activities refer to bank loan only in a narrow sense and are used as credit in a broad sense.
S102: and constructing an enterprise credit investigation database based on the multi-source data.
In some embodiments of the application, the server firstly makes a unified data standard specification to perform standardized data management on the multi-source data stored in the database based on the multi-source data with different sources and different structures. And secondly, the multi-source data is treated and processed through ETL and other data treatment tools, stock data such as e-commerce and feedback are periodically pulled, real-time interface data are processed through a memory, and data processing, data standardization, index calculation, light characteristic mining and the like are performed on the data in combination with a batch flow processing mode. And finally, the multi-source data are converged into a unified enterprise credit investigation database through horizontal and vertical data fusion, namely, the enterprise credit investigation database is created, and information such as standard database data, a processed index database, a processed feature database and the like after the multi-source data are fused are stored in the enterprise credit investigation database.
S103: and determining the post-credit risk early warning index according to the enterprise credit investigation database.
In some embodiments of the present application, the server extracts the post-credit risk early warning index based on the enterprise credit investigation database, and then determines a post-credit risk early warning index system according to the post-credit risk early warning index of the enterprise. The post-loan early warning index system comprises a first-level index, a second-level index and a third-level index, wherein the first-level index is used for dividing post-loan risk early warning dimensionality, the third-level index is used for dividing post-loan risk assessment indexes, and the second-level index is used for assessing early warning levels corresponding to enterprises under the post-loan risk early warning dimensionality through the post-loan risk assessment indexes.
Specifically, the first-level indexes are enterprise risk early warning dimensions, for example, seven major dimensions including industry, judicial, management, association, feedback, credit and legal representative persons, the third-level indexes are specific enterprise post-loan risk assessment indexes, for example, 400 or more third-level indexes including share right change, enterprise business license reimbursement, non-specified annual newspaper submission, power consumption ring ratio reduction rate, power credit rating, tax payment rating, arrearage amount, associated guarantee, quality equity amount, mortgage withheld debt amount, investment enterprise reimbursement, associated enterprise owed tax, administrative punishment, judicial filing plan, executives, trust loss executives, legal representative person accumulation, social insurance outage payment and the like, the second-level indexes are enterprise credit risk early warning index arrangement categories which are classified based on business knowledge and integrated on the basis of the third-level indexes and are used for assessing risk conditions of the enterprise under each post-loan risk early warning dimension, namely, the early warning level of the enterprise in each post-credit risk early warning dimension.
The early warning grade is divided into three grades of red, yellow and green according to the severity of the event, the red early warning grade is the highest, and the yellow is the second grade, and the green is risk-free.
S104: and constructing a post-credit risk early warning model based on the post-credit risk early warning indexes.
In some embodiments of the present application, the post-loan risk early warning model is associated with a decision tree. The server firstly generates an index early warning level rule model based on the post-loan risk early warning index, generates a single tree early warning level and probability rule model according to the index early warning level rule model, and generates a summary early warning level and probability rule model according to the single tree early warning level and probability rule model.
Specifically, when the server generates the index early warning level rule model based on the post-credit risk early warning index, the method specifically includes:
the method comprises the steps that a server determines a post-loan risk early warning dimensionality under a first-level index and a plurality of post-loan risk assessment indexes under a third-level index, then under the post-loan risk early warning dimensionality, if any post-loan risk assessment index in the plurality of post-loan risk assessment indexes triggers preset first early warning information, the early warning grade of the corresponding second-level index is determined to be a first grade, if the plurality of post-loan risk assessment indexes do not trigger the preset first early warning information, the index quantity triggering preset second early warning information is counted, and when the index quantity exceeds a preset threshold value, the early warning grade of the second-level index is determined to be the first grade. And the risk degree corresponding to the preset second early warning information is smaller than the risk degree corresponding to the preset first early warning information.
For example, the first-level indicators are classified into 6 types, and the same first-level indicators are classified into one type, namely judicial, legal, industrial and commercial, management, association and credit. And determining the early warning grade of each secondary index under the same class. When the risk assessment index after credit triggers a red early warning, the early warning grade of the secondary index is red, when the risk assessment index after credit does not trigger the red early warning, the yellow early warning quantity is counted, when the yellow early warning quantity exceeds a given threshold value, the early warning grade of the secondary index changes from yellow to red, otherwise, the secondary index is still yellow.
Further, when the server generates the single tree early warning level and probability rule model according to the index early warning level rule model, the method specifically includes:
the server respectively generates corresponding decision trees from the plurality of credited risk early warning dimensions, decides the early warning level of the corresponding secondary index in each decision tree to generate the early warning probability of each decision tree, and converts the early warning probability of each decision tree into the early warning level of each decision tree. Meanwhile, the label corresponding to the maximum value of the early warning probability is used as the early warning label of each decision tree.
For example, the single tree early warning level and probability rule model covers 6 rule trees including first-level index judicial, legal, industrial and commercial, management, association and credit, and generates comprehensive single tree early warning level and probability according to the early warning level condition of the index in the rule trees. For a single monitoring enterprise, the model generates 6 early warning levels based on 6 trees and prompts the corresponding early warning label probability in each tree. The probability is expressed in the form of (red, yellow and green), the probability output by each tree is the probability corresponding to the path where the enterprise is located, and the early warning label is the label corresponding to the maximum probability.
Further, the server generates a summary early warning level and probability rule model according to the single tree early warning level and probability rule model, and the method specifically includes:
the server firstly determines that a decision target of a hierarchical structure model is an early warning level and a decision criterion is each post-credit risk early warning dimension, secondly determines a hierarchical analysis scoring matrix based on the hierarchical structure model, performs consistency check on the result of the hierarchical analysis scoring matrix, determines a weight vector of each post-credit risk early warning dimension through an arithmetic mean method if the consistency check passes, and finally determines the early warning probability of an enterprise through a preset summarizing rule based on the weight vector, and then converts the early warning probability of the enterprise into the early warning level of the enterprise.
For example, the decision criteria are judicial, legal, industrial and commercial, management, association and credit, and the server adds the probabilities of the 6 early warning levels by an analytic hierarchy process probability summation method based on the single tree early warning level and the probability rule model to generate the final early warning label and early warning probability. The expression form of the probability is (red, yellow and green), and the output label is the label corresponding to the maximum probability.
When the server determines the early warning probability of an enterprise through a preset summarizing rule based on the weight vector, if the early warning level of each decision tree comprises a first early warning level, the early warning level of the enterprise is the first early warning level and the early warning probability corresponding to the first early warning level, and if the early warning level of each decision tree does not comprise the first early warning level, the early warning probability of the enterprise is determined through a preset early warning expression based on the weight vector.
For example, when the early warning levels generated by the 6 trees respectively include one or more reds, the final early warning level is red, and the early warning probability is (100%, 0%, 0%), and when the early warning levels generated by the 6 trees respectively do not include a red early warning, the early warning probability has an expression as follows: judicial weight, judicial probability + juridical weight, juridical probability + associated weight, associated probability + credit probability (total probability red%, total probability yellow%, total probability green%).
S105: and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
In some embodiments of the present application, because the risk early warning mechanism is an early risk early warning signal for discovering the risk after the enterprise is credited through post-credit check, the method combining quantitative analysis and qualitative analysis is applied to identify the category, degree, reason and development trend of the risk as early as possible, expose the risk in time, and take targeted treatment measures and timely precaution, control and solution to the risk according to the specified authority and program.
Therefore, after the server obtains the risk information of the enterprise and the early warning levels of the risk information, in order to show the corresponding risk information to the user, the server first determines the preset early warning critical values corresponding to the early warning levels, then determines the default probability of the enterprise according to the plurality of preset early warning critical values in a preset period, and finally displays corresponding early warning signals according to the risk interval where the default probability is located, for example, sends out corresponding early warning signals of three colors of red, yellow and green.
It should be noted that the risk early warning signal of the enterprise customer is mainly expressed from the aspects of judicial law, legal personnel, industry and commerce, management, related parties, credit and the like.
For example, the warning signals in judicial works are mainly the court level colleges and above, the enterprises are executives, and the assets of the enterprises are checked or frozen. The early warning signal of the legal person is mainly that the legal person breaks to pay social security or public accumulation. The early warning signals in the industry and commerce are mainly stock right change, operation range change, registered capital reduction, legal person change, address name change, whether the operation state of the industry and commerce is cancelled, stopped operation, liquidation and the like in enterprise change. The early warning signals in operation mainly comprise abnormal operation state, intellectual property quality, mortgage state of movable property, equity quality state, receivable pledge state and financing lease state. The early warning signals in the correlation are mainly the operation state of the invested enterprise and the operation state of the branch. The early warning signals in the credit mainly comprise a spot check inspection result, an administrative penalty, tax violation, tax owed situation, tax payment rating and whether the credit is included in a credit blacklist.
Furthermore, the server designs an early warning index triggering mechanism under a single or combined early warning mode according to the characteristics of the post-credit early warning signals, and establishes a post-credit early warning grading rule model by means of a rete algorithm, so that an intelligent decision engine is constructed.
Further, the server pushes risk information and early warning levels identified by the post-credit risk early warning model to relevant authority personnel of the financial institution in real time in the modes of short messages, mails and the like, and processes post-credit risk avoiding measures.
It should be noted that, although the embodiment of the present application describes steps S101 to S105 in sequence with reference to fig. 1, this does not mean that steps S101 to S105 must be executed in strict sequence. The embodiment of the present application is described by sequentially describing step S101 to step S105 according to the sequence shown in fig. 1, so as to facilitate those skilled in the art to understand the technical solutions of the embodiment of the present application. In other words, in the embodiment of the present application, the sequence between step S101 and step S105 may be appropriately adjusted according to actual needs.
Through the method of FIG. 1, the embodiment of the application can perform data standardization management based on multi-source data fusion of enterprise operation data, judicial data, industrial and commercial data, feedback data and the like, and establish an enterprise post-loan risk early warning index system on the basis of the multi-source data fusion, so that enterprise risk assessment dimensionality is richer, assessment indexes are more comprehensive, and the defect of performing enterprise post-loan risk monitoring by using a single data source is overcome.
Furthermore, the embodiment of the application is based on the fact that the decision tree and the probability rule model are fused to construct the post-credit risk early warning model on the basis of the post-credit risk early warning index system, the calculation power can be reduced, the calculation efficiency is improved, and meanwhile the enterprise early warning level can be judged more accurately, so that the prevention and control measures taken by a financial institution for the post-credit early warning risk are more targeted, and the practical guarantee is provided for the safety of credit assets.
Further, compared with the traditional risk index rule matching, the intelligent decision engine based on the rete algorithm is constructed in the embodiment of the application, the intelligent decision engine based on the rete algorithm can be competent for high concurrency and real-time processing efficiency based on massive credit investigation big data, and the defect of insufficient data processing efficiency in the traditional expert system design is overcome.
Based on the same idea, some embodiments of the present application further provide a device and a non-volatile computer storage medium corresponding to the above method.
Fig. 2 is a schematic diagram of a post-credit risk early warning structure based on credit according to an embodiment of the present application, including:
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 content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring multi-source data of a business related to credit;
constructing an enterprise credit investigation database based on multi-source data;
determining a post-credit risk early warning index according to an enterprise credit assessment database;
constructing a post-credit risk early warning model based on the post-credit risk early warning indexes; the post-loan risk early warning model is related to a decision tree;
and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
Some embodiments of the present application provide a credit-based post-credit risk early warning non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring multi-source data of a business related to credit;
constructing an enterprise credit investigation database based on multi-source data;
determining a post-credit risk early warning index according to an enterprise credit assessment database;
constructing a post-credit risk early warning model based on the post-credit risk early warning indexes; the post-loan risk early warning model is related to a decision tree;
and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the technical principle of the present application shall fall within the protection scope of the present application.
Claims (10)
1. A credit-based post-credit risk early warning method is characterized by comprising the following steps:
acquiring multi-source data of a business related to credit;
constructing the enterprise credit investigation database based on the multi-source data;
determining a post-credit risk early warning index according to the enterprise credit investigation database;
constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree;
and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
2. The method according to claim 1, wherein determining a post-credit risk early warning indicator according to the enterprise credit assessment database specifically comprises:
extracting a post-credit risk early warning index based on the enterprise credit investigation database;
determining a post-loan risk early warning index system according to the post-loan risk early warning index of the enterprise;
the post-credit early warning index system comprises a first-level index, a second-level index and a third-level index; the first-level indexes are used for dividing the post-loan risk early warning dimensionality, the third-level indexes are used for dividing the post-loan risk assessment indexes, and the second-level indexes are used for assessing the early warning levels corresponding to the enterprise under the post-loan risk early warning dimensionality through the post-loan risk assessment indexes.
3. The method according to claim 2, wherein constructing a post-credit risk early warning model based on the post-credit risk early warning indicators specifically comprises:
generating an index early warning level rule model based on the post-loan risk early warning index;
generating a single tree early warning grade and probability rule model according to the index early warning grade rule model;
and generating a summary early warning grade and probability rule model according to the single tree early warning grade and probability rule model.
4. The method according to claim 3, wherein generating an indicator early warning level rule model based on the post-credit risk early warning indicator specifically comprises:
determining a post-credit risk early warning dimensionality under the first-level index and a plurality of post-credit risk assessment indexes under the third-level indexes;
under the post-credit risk early warning dimensionality, if any one of the post-credit risk assessment indexes triggers preset first early warning information, determining the early warning level of the corresponding secondary index to be a first level;
if the plurality of post-loan risk assessment indexes are all the first pre-warning information which is not triggered, counting the number of indexes triggering the second pre-warning information; the risk degree corresponding to the preset second early warning information is smaller than the risk degree corresponding to the preset first early warning information;
and when the index number exceeds a preset threshold value, determining the early warning level of the secondary index as the first level.
5. The method according to claim 4, wherein the generating of the single tree early warning level and probability rule model according to the index early warning level rule model specifically comprises:
respectively generating a plurality of post-credit risk early warning dimensions into corresponding decision trees;
the early warning level of the corresponding secondary index in each decision tree is decided to generate the early warning probability of each decision tree, and a label corresponding to the maximum value of the early warning probability is used as the early warning label of each decision tree;
and converting the early warning probability of each decision tree into the early warning grade of each decision tree.
6. The method according to claim 5, wherein generating a summary early warning level and probability rule model according to the single tree early warning level and probability rule model specifically comprises:
determining a decision target of the hierarchical structure model as an early warning level and a decision criterion as each post-credit risk early warning dimension;
determining a hierarchical analysis scoring matrix based on the hierarchical structure model, and performing consistency check on the result of the hierarchical analysis scoring matrix;
if the consistency check is passed, determining the weight vector of each post-credit risk early warning dimension through an arithmetic mean method;
determining early warning probability of the enterprise through a preset summarizing rule based on the weight vector;
and converting the early warning probability of the enterprise into the early warning level of the enterprise.
7. The method according to claim 6, wherein the determining the early warning probability of the enterprise based on the weight vector through a preset aggregation rule specifically comprises:
if the early warning level of each decision tree comprises a first early warning level, the early warning level of the enterprise is the first early warning level and the early warning probability corresponding to the first early warning level;
and if the early warning level of each decision tree does not comprise the first early warning level, determining the early warning probability of the enterprise through a preset early warning expression based on the weight vector.
8. The method of claim 2, wherein after determining risk information for the enterprise and the warning level of the risk information according to the post-mortgage risk warning model, the method further comprises:
determining a preset early warning critical value corresponding to the early warning grade;
in a preset period, determining default probability of the enterprise according to a plurality of preset early warning critical values;
and displaying a corresponding early warning signal according to the risk interval where the default probability is located.
9. A credit-based post-credit risk early warning 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 content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring multi-source data of a business related to credit;
constructing the enterprise credit investigation database based on the multi-source data;
determining a post-credit risk early warning index according to the enterprise credit investigation database;
constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree;
and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
10. A credit-based post-credit risk pre-warning non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring multi-source data of a business related to credit;
constructing the enterprise credit investigation database based on the multi-source data;
determining a post-credit risk early warning index according to the enterprise credit investigation database;
constructing a post-credit risk early warning model based on the post-credit risk early warning index; the post-credit risk early warning model is related to a decision tree;
and determining the risk information of the enterprise and the early warning level of the risk information according to the post-credit risk early warning model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111136072.5A CN113837862A (en) | 2021-09-27 | 2021-09-27 | Post-credit risk early warning method, device and medium based on credit investigation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111136072.5A CN113837862A (en) | 2021-09-27 | 2021-09-27 | Post-credit risk early warning method, device and medium based on credit investigation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837862A true CN113837862A (en) | 2021-12-24 |
Family
ID=78970862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111136072.5A Pending CN113837862A (en) | 2021-09-27 | 2021-09-27 | Post-credit risk early warning method, device and medium based on credit investigation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837862A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997750A (en) * | 2022-08-03 | 2022-09-02 | 广东知得失网络科技有限公司 | Risk information pushing method, system, equipment and medium |
| 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 |
| CN117314163A (en) * | 2023-09-27 | 2023-12-29 | 吉贝克信息技术（北京）有限公司 | Social security data processing method and system based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230143A (en) * | 2018-02-05 | 2018-06-29 | 深圳微众税银信息服务有限公司 | Data report generation method and system after a kind of loan |
| CN112348654A (en) * | 2020-09-23 | 2021-02-09 | 民生科技有限责任公司 | Automatic assessment method, system and readable storage medium for enterprise credit line |
| CN112597775A (en) * | 2020-12-16 | 2021-04-02 | 中国工商银行股份有限公司 | Credit risk prediction method and device |
| CN112668944A (en) * | 2021-01-26 | 2021-04-16 | 天元大数据信用管理有限公司 | Enterprise wind control method, device, equipment and medium based on big data credit investigation |
| CN112862339A (en) * | 2021-02-25 | 2021-05-28 | 厦门渊亭信息科技有限公司 | Risk decision method and system |
| CN113256075A (en) * | 2021-04-29 | 2021-08-13 | 浙江非线数联科技股份有限公司 | Enterprise risk level evaluation method based on hierarchical analysis and fuzzy comprehensive evaluation method |
-
2021
- 2021-09-27 CN CN202111136072.5A patent/CN113837862A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230143A (en) * | 2018-02-05 | 2018-06-29 | 深圳微众税银信息服务有限公司 | Data report generation method and system after a kind of loan |
| CN112348654A (en) * | 2020-09-23 | 2021-02-09 | 民生科技有限责任公司 | Automatic assessment method, system and readable storage medium for enterprise credit line |
| CN112597775A (en) * | 2020-12-16 | 2021-04-02 | 中国工商银行股份有限公司 | Credit risk prediction method and device |
| CN112668944A (en) * | 2021-01-26 | 2021-04-16 | 天元大数据信用管理有限公司 | Enterprise wind control method, device, equipment and medium based on big data credit investigation |
| CN112862339A (en) * | 2021-02-25 | 2021-05-28 | 厦门渊亭信息科技有限公司 | Risk decision method and system |
| CN113256075A (en) * | 2021-04-29 | 2021-08-13 | 浙江非线数联科技股份有限公司 | Enterprise risk level evaluation method based on hierarchical analysis and fuzzy comprehensive evaluation method |
Non-Patent Citations (1)
| Title |
|---|
| 王培元;: "基于信用画像的银税互动平台关键技术研究", 信息技术与信息化, no. 2018, 25 April 2018 (2018-04-25), pages 153 - 156 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997750A (en) * | 2022-08-03 | 2022-09-02 | 广东知得失网络科技有限公司 | Risk information pushing method, system, equipment and medium |
| CN114997750B (en) * | 2022-08-03 | 2022-10-25 | 广东知得失网络科技有限公司 | Risk information pushing method, system, equipment and medium |
| 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 |
| CN117314163A (en) * | 2023-09-27 | 2023-12-29 | 吉贝克信息技术（北京）有限公司 | Social security data processing method and system based on big data |
| CN117314163B (en) * | 2023-09-27 | 2024-04-12 | 吉贝克信息技术（北京）有限公司 | Social security data processing method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113837862A (en) | Post-credit risk early warning method, device and medium based on credit investigation | |
| Hu et al. | Dynamics of the federal funds target rate: a nonstationary discrete choice approach | |
| KR20190064749A (en) | Method and device for intelligent decision support in stock investment | |
| Kiyak et al. | Assessment of the practical application of corporate bankruptcy prediction models | |
| CN111476660A (en) | Intelligent wind control system and method based on data analysis | |
| CN115271912A (en) | Credit business intelligent wind control approval system and method based on big data | |
| CN114298566A (en) | Asset information management method, equipment and medium based on enterprise portrait | |
| Çelik | Micro credit risk metrics: a comprehensive review | |
| Xie et al. | A Big Data Technique for Internet Financial Risk Control | |
| CN112766814A (en) | Training method, device and equipment for credit risk pressure test model | |
| KR101666824B1 (en) | Chain bankruptcy risk management system and bankruptcy risk management method using the same | |
| CN113674075A (en) | Method for credit rating of enterprise debt financing tool | |
| Chowdhury et al. | Application of Data Analytics in Risk Management of Fintech Companies | |
| TWM581728U (en) | Credit risk stress testing system | |
| Li | Research on the impact of AI application on capital chain resilience | |
| Cheng et al. | BIS Papers | |
| KR102334923B1 (en) | Loan expansion hypothesis testing system using artificial intelligence and method using the same | |
| Kang et al. | Predicting the relationship between corporate financial information and credit rating using deep learning | |
| Jiang | Financial stability of banking system in China | |
| Li et al. | Research on the Risk Measurement Algorithm of Supply Chain Order Financing Based on Insurance Actuarial | |
| Hapsari et al. | The Law And Digital Revolution In Financial Technology (Fintech) Present Significant Opportunities To Accelerate Digital Financing Of The Sdgs | |
| Turdyeva et al. | OVERSEAS EXPERIENCE OF RISK ASSESSMENT OF COMMERCIAL BANKS | |
| Zhao | Research on Mathematical Model P2P Online Credit Risk Evaluation Based on Data Processing | |
| Singh et al. | Operational Risk and Regulatory Capital: Do Public and Private Banks Differ? | |
| Kamata et al. | The influence of natural disaster regional information on investment flows in Aceh |
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 |