CN112734559B - Enterprise credit risk evaluation method and device and electronic equipment - Google Patents
Enterprise credit risk evaluation method and device and electronic equipment Download PDFInfo
- Publication number
- CN112734559B CN112734559B CN202011643781.8A CN202011643781A CN112734559B CN 112734559 B CN112734559 B CN 112734559B CN 202011643781 A CN202011643781 A CN 202011643781A CN 112734559 B CN112734559 B CN 112734559B
- Authority
- CN
- China
- Prior art keywords
- risk
- enterprise
- data
- target
- exogenous
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 99
- 238000013210 evaluation model Methods 0.000 claims abstract description 67
- 238000012502 risk assessment Methods 0.000 claims abstract description 44
- 238000010801 machine learning Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 31
- 229940088592 immunologic factor Drugs 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 6
- 238000010845 search algorithm Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 239000000367 immunologic factor Substances 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000011002 quantification Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012946 outsourcing Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000501754 Astronotus ocellatus Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003121 nonmonotonic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
- G06Q40/06—Asset management; Financial planning or 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an enterprise credit risk evaluation method, an enterprise credit risk evaluation device and electronic equipment, which relate to the technical field of data processing, and are used for acquiring risk evaluation data of a target enterprise when evaluating the enterprise credit risk of the target enterprise; then determining target endogenous risk characteristics and target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph; and determining a credit risk evaluation result of the target enterprise according to the target endogenous risk characteristics, the target exogenous risk characteristics, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model. Compared with the existing evaluation mode based on rules, the evaluation mode based on mathematical statistics and machine learning is mainly based on the statistical rules of data, is less influenced by artificial subjective risk preference, and is relatively stable in operation, so that the effect is more stable, and the reliability of risk evaluation results is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for evaluating credit risk of an enterprise, and an electronic device.
Background
The enterprise credit risk is also called default risk, which refers to the possibility that an enterprise is unwilling or unable to fulfill contract conditions for various reasons to form default, so that a bank, an investor or a transaction partner is lost.
The present enterprise credit risk evaluation scheme is usually based on relevant rules established by experts, namely, the enterprise credit risk is evaluated according to manually set risk propagation rules. Because the scheme is greatly influenced by the subjective of an expert, artificial deviation is easy to occur, the effect is unstable, and the reliability of a risk evaluation result is poor.
Disclosure of Invention
The invention aims to provide an enterprise credit risk evaluation method, an enterprise credit risk evaluation device and electronic equipment, so as to improve reliability of a risk evaluation result.
The embodiment of the invention provides an enterprise credit risk evaluation method, which comprises the following steps:
Acquiring risk assessment data of a target enterprise;
Determining target endogenous risk characteristics and target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph;
and determining a credit risk evaluation result of the target enterprise according to the target endogenous risk characteristics, the target exogenous risk characteristics, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model.
Further, the step of acquiring risk assessment data of the target enterprise includes:
And purchasing risk assessment data of the target enterprise through a preset data service provider, wherein the risk assessment data comprises industrial and commercial data, judicial data, stock market and bond market transaction data, announcement data, enterprise management data, financial data, enterprise relation data, enterprise guarantee data and rating data.
Further, the step of determining the target endogenous risk feature and the target exogenous risk feature according to the risk assessment data and a pre-constructed index system comprises the following steps:
Carrying out data processing and integration on the risk assessment data through a preset relational database to obtain a data report; the data report forms comprise an enterprise basic information table, a relation report form, a financial class report form, an operation class report form, an announcement class report form, a public opinion report form, a guarantee class report form, a financial market transaction report form, an external rating class report form, a judicial class report form and an enterprise credit class report form;
generating a target endogenous risk feature corresponding to the endogenous risk index and a target exogenous risk feature corresponding to the exogenous risk index according to the data report; the endophytic risk index comprises a management structure, enterprise attributes, illegal information, credit records, profitability, asset structure evaluation, debt repaying capability, cash flow, income quality, growth capability and judicial complaints; the exogenous risk index comprises a structural index, a scale index, an attenuation factor and an immune factor, wherein the structural index is related to the number of internal members and the average degree of ingress and egress, the scale index is related to the total assets, the total liabilities, the total incomes, the total profits and the number of clients with negative profits, the attenuation factor is related to the number of bad clients and the number of clients with credit balances, and the immune factor is inversely related to the probability of default.
Further, the step of determining the credit risk evaluation result of the target enterprise according to the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model includes:
Respectively inputting the target endogenous risk feature and the target exogenous risk feature into a trained endogenous risk evaluation model and a trained exogenous risk evaluation model to obtain an endogenous risk violation probability output by the endogenous risk evaluation model and an exogenous risk violation probability output by the exogenous risk evaluation model;
and determining a credit risk evaluation result of the target enterprise according to the endogenous risk violation probability and the exogenous risk violation probability.
Further, the step of determining the credit risk evaluation result of the target enterprise according to the endogenous risk breach probability and the exogenous risk breach probability includes:
Comparing the intrinsic risk default probability and the extrinsic risk default probability with a preset probability threshold value respectively to obtain a comparison result;
and determining a credit risk evaluation result of the target enterprise according to the comparison result.
Further, the method further comprises:
Acquiring a training set sample, wherein the training set sample comprises historical evaluation data of a historical credit enterprise in a prediction window and actual credit violation results of a prediction time point;
determining sample endogenous risk characteristics and sample exogenous risk characteristics according to the historical evaluation data and the index system;
Training an initial endophytic risk evaluation model according to the sample endophytic risk characteristics and the actual credit violation results to obtain a trained endophytic risk evaluation model;
And training an initial exogenous risk evaluation model according to the sample exogenous risk characteristics and the actual credit violation results to obtain a trained exogenous risk evaluation model.
Further, training an initial endogenous risk evaluation model according to the sample endogenous risk characteristics and the actual credit violation results to obtain a trained endogenous risk evaluation model, which comprises the following steps:
training a plurality of preset initial machine learning models through K-fold cross verification and grid search algorithm according to the sample endogenous risk characteristics and the actual credit violation results to obtain a plurality of trained machine learning models;
and determining an optimal model in the plurality of machine learning models as a trained endogeneous risk evaluation model.
The embodiment of the invention also provides an enterprise credit risk evaluation device, which comprises:
the data acquisition module is used for acquiring risk assessment data of a target enterprise;
the feature determining module is used for determining target endogenous risk features and target exogenous risk features according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph;
The result determining module is used for determining a credit risk evaluation result of the target enterprise according to the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program which can run on the processor, and the processor realizes the enterprise credit risk evaluation method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, and the computer program is executed by a processor to execute the enterprise credit risk evaluation method.
According to the enterprise credit risk evaluation method, the enterprise credit risk evaluation device and the electronic equipment, when enterprise credit risk evaluation is carried out on a target enterprise, risk evaluation data of the target enterprise are acquired first; then determining target endogenous risk characteristics and target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph; and determining a credit risk evaluation result of the target enterprise according to the target endogenous risk characteristics, the target exogenous risk characteristics, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model. Therefore, by utilizing machine learning and knowledge graph theoretical tools, the enterprise credit risk evaluation result which can be updated in a time-sharing frequency manner is constructed. Compared with the existing evaluation mode based on rules, the evaluation mode based on mathematical statistics and machine learning is mainly based on the statistical rules of data, is less influenced by artificial subjective risk preference, and is relatively stable in operation, so that the effect is more stable, and the reliability of risk evaluation results is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an enterprise credit risk evaluation method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of model training according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an implementation architecture of an enterprise credit risk assessment method according to an embodiment of the present invention;
Fig. 4 is a schematic diagram showing the result of an enterprise credit risk evaluation method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an enterprise credit risk evaluation device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Machine learning is a science of studying how to simulate or realize human learning activities using a computer, and its theory and method have been widely applied to solve complex problems in engineering application and science fields, which is one of the most intelligent features and forefront research fields in artificial intelligence. Since the 80 s of the 20 th century, machine learning has attracted widespread interest in the artificial intelligence world as a way to implement artificial intelligence, and particularly in recent decades, research work in the machine learning field has progressed rapidly, which has become one of the important subjects of artificial intelligence. Machine learning is widely used not only in knowledge-based systems, but also in many fields such as natural language understanding, non-monotonic reasoning, machine vision, pattern recognition, etc. Whether a system has learning capabilities has become a sign of whether it has "intelligence". The study of machine learning is largely divided into two categories: the first category is the study of traditional machine learning, which is mainly study of learning mechanisms and focuses on exploring the learning mechanism of a simulator; the second category is machine learning research in big data environments, which is mainly to study how to effectively use information, focusing on obtaining hidden, effective and understandable knowledge from huge amounts of data.
Based on the above, the enterprise credit risk evaluation method, the enterprise credit risk evaluation device and the electronic equipment provided by the embodiment of the invention solve the problems of quantification and evaluation of the internal risk and the external risk of an enterprise by means of machine learning and knowledge graph theoretical tools under the big data background, and can improve the reliability of a risk evaluation result.
For the convenience of understanding the present embodiment, first, a method for evaluating credit risk of an enterprise disclosed in the present embodiment is described in detail.
The embodiment of the invention provides an enterprise credit risk evaluation method which can be executed by electronic equipment with data processing capability, such as a desktop computer, a notebook computer, a tablet computer or a mobile phone. Referring to a flow chart of an enterprise credit risk evaluation method shown in fig. 1, the method mainly includes steps S102 to S106 as follows:
Step S102, acquiring risk assessment data of a target enterprise.
In some possible embodiments, the risk assessment data for the target enterprise may be purchased through a third channel of preset data facilitators, such as wisdom, sink, elements, etc., which may include business data, judicial data, stock bond transaction data, bulletin data, enterprise business data, financial data, enterprise relationship data, enterprise guarantee data, and ratings data, etc.
Step S104, determining target endogenous risk characteristics and target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph.
In some possible embodiments, the risk assessment data may be processed and integrated through a preset relational database to obtain a data report; the data report comprises an enterprise basic information table, a relation report, a financial report, an operation report, an announcement report, a public opinion report, a guarantee report, a financial market transaction report, an external rating report, a judicial report, an enterprise credit report and the like. Then, generating a target endogenous risk feature corresponding to the endogenous risk index and a target exogenous risk feature corresponding to the exogenous risk index according to the data report; the endogenous risk indexes comprise management structures, enterprise attributes, illegal information, credit records, profitability, asset structure evaluation, debt repayment capacity, cash flow, income quality, growth capacity and judicial complaints; exogenous risk indicators include structural indicators related to the number of internal members and average ingress and egress, scale indicators related to the total assets, total liabilities, total incomes, total profits, and number of customers with negative profits, attenuation factors related to the number of bad customers and the number of customers with credit balances, and immune factors inversely related to the probability of breach (generally, the higher the probability of breach, the lower the immune factor).
The exogenous risk index is constructed based on a knowledge graph, which is also called a historical enterprise graph network, and is formed by researching data, documents and the like. The exogenous risk of the enterprise can be propagated to the enterprise through relationships in the historical enterprise atlas network, i.e., the associated risk is propagated. The associated risk propagation is related to attenuation factors and immune factors, wherein the attenuation factors refer to attenuation degree coefficients of the exogenous risks of enterprises transmitted to the enterprises through relationships in the spectrograms, generally, the greater the attenuation degree is, the smaller the external risk propagation paths and influence are, the attenuation factors (also called attenuation coefficients) are mainly related to steady-state poor client rates in the historical enterprise spectrogram networks, the different steady-state poor client rates of the historical enterprise spectrogram networks with different sizes are different, and the attenuation factors are also different; immune factors (also referred to as immune factors) refer to the ability of an enterprise to withstand exogenous risks, with the higher the immune factor, the greater the ability of an enterprise to withstand exogenous risks, immune factor = 1-probability of violation.
In specific implementation, after the risk assessment data is purchased and accessed, the risk assessment data can be stored in a preset relational database, data processing and integration are performed, and the data report is formed after integration is completed. Data cleaning and processing may then be performed: and according to the definition of each index (the endogenous risk index and the exogenous risk index) in the index system which is constructed, finishing the processing of the index system, and uniformly filling zero values for the abnormal value and the blank value, thereby obtaining the target endogenous risk characteristic corresponding to the endogenous risk index and the target exogenous risk characteristic corresponding to the exogenous risk index.
Step S106, determining a credit risk evaluation result of the target enterprise according to the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model.
In some possible embodiments, the target endogenous risk feature and the target exogenous risk feature may be respectively input into the trained endogenous risk evaluation model and the trained exogenous risk evaluation model, so as to obtain an endogenous risk violation probability output by the endogenous risk evaluation model and an exogenous risk violation probability output by the exogenous risk evaluation model; and then determining the credit risk evaluation result of the target enterprise according to the infraction risk breach probability and the extinguishment risk breach probability.
Further, the step of determining the credit risk evaluation result of the target enterprise according to the endogenous risk breach probability and the exogenous risk breach probability may be implemented by the following process: respectively comparing the infraction probability of the endogenous risk and the infraction probability of the exogenous risk with a preset probability threshold value to obtain a comparison result; and determining the credit risk evaluation result of the target enterprise according to the comparison result.
Further, the credit risk evaluation result may include an enterprise endogenous risk evaluation corresponding to an endogenous risk breach probability, an enterprise exogenous risk evaluation corresponding to an exogenous risk breach probability, and an enterprise comprehensive risk evaluation corresponding to a comprehensive breach probability; the enterprise endogenous risk evaluation refers to quantification and evaluation of risks generated in production and operation activities of enterprises; the enterprise exogenous risk evaluation refers to quantification and evaluation of the enterprise under the influence of other enterprises in the map relationship network where the enterprise is located; the enterprise comprehensive risk evaluation refers to comprehensive quantification and evaluation of enterprise endogenous risks and exogenous risks, and the comprehensive breach probability is the sum of the endogenous risk breach probability and the exogenous risk breach probability.
The preset probability threshold may be set according to actual requirements, which is not limited herein. For example, if the preset probability threshold is 0.5 and the comparison result is that only the risk default probability of the enterprise is greater than 0.5, the credit risk evaluation result of the target enterprise is that the enterprise risk of the enterprise is higher; if the comparison result shows that the probability of the exogenous risk violation is more than 0.5, the credit risk evaluation result of the target enterprise is that the exogenous risk of the enterprise is higher; if the comparison result is that the sum of the infraction probability and the foreign risk violation probability is more than 0.5, the credit risk evaluation result of the target enterprise is that the enterprise comprehensive risk is higher; if the comparison result is that the sum of the intrinsic risk violation probability and the extrinsic risk violation probability is smaller than or equal to 0.5, the credit risk evaluation result of the target enterprise is that the enterprise comprehensive risk is lower.
The enterprise credit risk evaluation method provided by the embodiment of the invention utilizes machine learning and graph network theory to construct quantitative evaluation results capable of updating the internal and external risks of the enterprise at a time-sharing frequency. Compared with the existing evaluation mode based on rules, the evaluation mode based on mathematical statistics and machine learning is mainly based on the statistical rules of data, is less influenced by artificial subjective risk preference, and is relatively stable in operation, so that the effect is more stable, and the reliability of risk evaluation results is improved.
The embodiment of the invention also provides a training process of the endogenous risk evaluation model and the exogenous risk evaluation model, referring to a schematic flow diagram of model training shown in fig. 2, the training process of the endogenous risk evaluation model and the exogenous risk evaluation model comprises the following steps:
Step S202, a training set sample is obtained, wherein the training set sample comprises historical evaluation data of a historical credit enterprise in a prediction window and actual credit violation results of a prediction time point.
When the sample is obtained, a prediction time point and a prediction window are selected, the prediction window can be selected for 6 months or 1 year, a characteristic wide table is obtained according to the prediction time point, a historical credit enterprise is selected as the sample according to the prediction window, and the sample is randomly divided into a training set sample and a test set sample according to a certain proportion. For example, a feature broad table is taken according to the predicted time point 2018, 30 th 06, a 1-year history credit business is constructed, and a history overdue business is taken as a target sample, for example, 7:3 are randomly divided into training set samples and test set samples. The actual credit violation results can be subdivided into five categories, i.e., default due to endogenous risk, default due to exogenous risk, default due to integrated risk, and non-default.
Step S204, according to the historical evaluation data and the index system, determining the sample endogenous risk characteristics and the sample exogenous risk characteristics.
The sample in-growth risk feature and the sample out-growth risk feature are both composed of the section data of the predicted time point, and the specific process of step S204 may refer to the corresponding content of step S104, which is not described herein.
And step S206, training the initial endophytic risk evaluation model according to the sample endophytic risk characteristics and the actual credit violation results to obtain a trained endophytic risk evaluation model.
In some possible embodiments, training a plurality of preset initial machine learning models through K-fold cross validation and grid search algorithms according to the sample endogenous risk characteristics and the actual credit violation results to obtain a plurality of trained machine learning models; and determining an optimal model in the multiple machine learning models as a trained endophytic risk evaluation model.
The initial machine learning model can be selected according to actual requirements, for example, four models including logistic regression, random forest and Xgboost, adaboost are selected. The optimal value of the main parameters of the model can be found out through K-fold cross validation and a grid search algorithm, and then the optimal model is selected according to the comprehensive evaluation of the service angle and the accuracy rate and recall rate of the balanced model. For example, model training is performed by using the four mainstream machine learning models and the unbalanced sample processing method, and a final endogenetic risk evaluation model is preferentially selected by taking the F1 value as a standard.
And step S208, training the initial exogenous risk evaluation model according to the sample exogenous risk characteristics and the actual credit violation results to obtain a trained exogenous risk evaluation model.
The specific process of step S208 may refer to the corresponding content of step S206, which is not described herein.
In order to facilitate understanding, the embodiment of the invention also provides an implementation process of the enterprise credit risk evaluation method, which comprises the following steps:
The first step: the method comprises the steps of preparing, carrying out data investigation, literature investigation, expert investigation in industry and the like, constructing a risk characteristic index library, constructing an Oscar database and index system based on big data, preparing and completing basic works such as development environment, basic codes, model codes and the like, and establishing a feasible technical scheme implementation route.
As shown in fig. 3, the data layer covers 14 layers of industry and commerce, judicial, management, financial report, rating, credit, transaction, market, bulletin, public opinion, group, guarantee, industry, region, and the like, the risk index layer includes nearly 400 indexes of an endogenous risk index and an exogenous risk index, the endogenous risk index includes management structure, enterprise attribute, illegal information, credit record, profitability, asset structure evaluation, debt repayment capability, cash flow, income quality, growth capability, judicial complaints, and the like, and the exogenous risk index includes (1) structural indexes: internal member number and average degree of ingress and egress; (2) Scale index: total assets, total liabilities, total revenues, total profits, and number of customers with negative profits; (3) attenuation factor: poor customer count and customer count of stock credit balance; (4) immune factor: probability of breach.
And a second step of: and integrating the data sources, and cleaning and processing the data to form index factor characteristics. The data sources may include nearly 100 financial websites, and the related data includes business data, judicial data, stock market debt transaction data, bulletin data, business operation data, financial data, guarantee data, rating data, investment relationship data, and the like.
And a third step of: dividing the index factor characteristics into two types of endogenous risk characteristics and exogenous risk characteristics, and taking a 1-year history credit client construction sample as a target sample by using a history overdue client.
As shown in fig. 3, the risk of endogenous and exogenous risk identification and propagation are performed at the risk occurrence layer.
Fourth step: as shown in fig. 3, at the risk evaluation model layer, four machine learning models are used to train the models, and the trained endophytic risk evaluation model can output the endophytic risk violation probability D of a single enterprise, and the endophytic risk violation probability is used as the endophytic risk evaluation of the enterprise.
Fifth step: the attenuation factor and the immune factor are calculated.
Sixth step: as shown in fig. 3, at the risk evaluation model layer, an exogenous risk evaluation model is constructed by the structural index, the scale index, the attenuation factor and the immune factor: exogenous risk violation probability = F (structural index, scale index, attenuation factor, and immune factor).
Seventh step: and outputting the credit risk evaluation result of the enterprise.
As shown in fig. 3, at the evaluation result output layer, the output contents are as follows: only the infraction probability of the endogenous risk is more than 0.5, and the output enterprise's endogenous risk is higher; only the exogenous risk violation probability is more than 0.5, and the exogenous risk of the output enterprise is higher; the probability of infraction of the risk of infraction and the probability of infraction of the risk of outsourcing are more than 0.5, and the comprehensive risk of the output enterprise is higher; the probability of infraction of the risk of infraction and the probability of infraction of the risk of outsourcing are less than or equal to 0.5, and the comprehensive risk of the output enterprise is lower.
Eighth step: after the endogenous risk evaluation model and the exogenous risk evaluation model are constructed, risk characteristics can be input in real time, and the endogenous risk, the exogenous risk and the comprehensive risk of the enterprise can be evaluated in real time.
The embodiment of the invention also provides a result display example of the enterprise credit risk evaluation method, and the result display schematic diagram of the enterprise credit risk evaluation method shown in fig. 4 is a XX bank company customer risk early warning monitoring platform, and mainly comprises a model monitoring area and an early warning list area. The model monitoring area comprises two sub-areas, and one sub-area is used for displaying the following contents: headquarter early warning client statistics and upper period variation, branch office early warning client statistics and upper period variation, industry early warning client statistics and upper period variation and regional early warning client statistics and upper period variation; the other sub-region is used to present the following: precision, recall, KS (Kolmogorov-Smirnov), AUC (Area Under Curve), effective pre-warning, false alarm and missed alarm rates. The early warning list area mainly shows the following contents: customer number, customer name, membership group, membership branch, industry, area, pre-warning reason, pre-warning level and pre-warning feedback.
Corresponding to the enterprise credit risk evaluation method, the embodiment of the invention also provides an enterprise credit risk evaluation device, referring to a schematic structure diagram of the enterprise credit risk evaluation device shown in fig. 5, the device comprises:
a data acquisition module 52, configured to acquire risk assessment data of a target enterprise;
the feature determining module 54 is configured to determine a target endogenous risk feature and a target exogenous risk feature according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph;
The result determining module 56 is configured to determine a credit risk evaluation result of the target enterprise according to the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk evaluation model, and the trained exogenous risk evaluation model.
The enterprise credit risk evaluation device provided by the embodiment of the invention utilizes machine learning and graph network theory to construct quantitative evaluation results capable of updating the internal and external risks of an enterprise at a time-sharing frequency. Compared with the existing evaluation mode based on rules, the evaluation mode based on mathematical statistics and machine learning is mainly based on the statistical rules of data, is less influenced by artificial subjective risk preference, and is relatively stable in operation, so that the effect is more stable, and the reliability of risk evaluation results is improved.
Further, the data acquisition module 52 is specifically configured to: and purchasing risk assessment data of the target enterprise through a preset data service provider, wherein the risk assessment data comprises business data, judicial data, stock market and bond market transaction data, announcement data, enterprise management data, financial data, enterprise relationship data, enterprise guarantee data and rating data.
Further, the above-mentioned feature determination module 54 is specifically configured to: carrying out data processing and integration on the risk assessment data through a preset relational database to obtain a data report; the data report comprises an enterprise basic information table, a relation report, a financial report, an operation report, an announcement report, a public opinion report, a guarantee report, a financial market transaction report, an external rating report, a judicial report and an enterprise credit report; generating a target endogenous risk feature corresponding to the endogenous risk index and a target exogenous risk feature corresponding to the exogenous risk index according to the data report; the endogenous risk indexes comprise management structures, enterprise attributes, illegal information, credit records, profitability, asset structure evaluation, debt repayment capacity, cash flow, income quality, growth capacity and judicial complaints; exogenous risk indicators include structural indicators related to the number of internal members and average ingress and egress, scale indicators related to the total assets, total liabilities, total incomes, total profits, and number of customers with negative profits, attenuation factors related to the number of bad customers and the number of customers with stock credit balances, and immune factors inversely related to the probability of breach.
Further, the above-mentioned result determination module 56 is specifically configured to: respectively inputting the target endogenous risk feature and the target exogenous risk feature into a trained endogenous risk evaluation model and a trained exogenous risk evaluation model to obtain an endogenous risk violation probability output by the endogenous risk evaluation model and an exogenous risk violation probability output by the exogenous risk evaluation model; and determining a credit risk evaluation result of the target enterprise according to the endogenous risk violation probability and the exogenous risk violation probability.
Further, the result determining module 56 is further configured to: respectively comparing the infraction probability of the endogenous risk and the infraction probability of the exogenous risk with a preset probability threshold value to obtain a comparison result; and determining the credit risk evaluation result of the target enterprise according to the comparison result.
Further, the apparatus further comprises a training module coupled to the result determination module 56 for:
Acquiring a training set sample, wherein the training set sample comprises historical evaluation data of a historical credit enterprise in a prediction window and actual credit violation results of a prediction time point;
Determining the sample endogenous risk characteristics and the sample exogenous risk characteristics according to the historical evaluation data and the index system;
Training the initial endophytic risk evaluation model according to the sample endophytic risk characteristics and the actual credit violation results to obtain a trained endophytic risk evaluation model;
and training the initial exogenous risk evaluation model according to the sample exogenous risk characteristics and the actual credit violation results to obtain a trained exogenous risk evaluation model.
Further, the training module is specifically configured to: training a plurality of preset initial machine learning models through K-fold cross validation and grid search algorithm according to the sample endogenous risk characteristics and the actual credit violation results to obtain a plurality of trained machine learning models; and determining an optimal model in the multiple machine learning models as a trained endophytic risk evaluation model.
The device provided in this embodiment has the same implementation principle and technical effects as those of the foregoing method embodiment, and for brevity, reference may be made to the corresponding content of the foregoing method embodiment where the device embodiment is not mentioned.
Referring to fig. 6, an embodiment of the present invention further provides an electronic device 100, including: a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 being connected by the bus 62; the processor 60 is arranged to execute executable modules, such as computer programs, stored in the memory 61.
The memory 61 may include a random access memory (Random Access Memory, abbreviated as RAM) and may further include a non-volatile memory (NVM), such as at least one disk memory. The communication connection between the system network element and at least one other network element is achieved via at least one communication interface 63 (which may be wired or wireless), and may use the internet, a wide area network, a local network, a metropolitan area network, etc.
Bus 62 may be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.
The memory 61 is configured to store a program, and the processor 60 executes the program after receiving an execution instruction, and the method executed by the apparatus for defining a flow disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 60 or implemented by the processor 60.
The processor 60 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 60. The processor 60 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 61 and the processor 60 reads the information in the memory 61 and in combination with its hardware performs the steps of the method described above.
The embodiment of the invention also provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to execute the enterprise credit risk assessment method in the previous method embodiment. The computer-readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a RAM, a magnetic disk, or an optical disk, etc., which can store program codes.
Any particular values in all examples shown and described herein are to be construed as merely illustrative and not a limitation, and thus other examples of exemplary embodiments may have different values.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the 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 scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (9)
1. An enterprise credit risk assessment method, comprising the steps of:
Acquiring risk assessment data of a target enterprise;
Determining target endogenous risk characteristics and target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph;
Determining a credit risk evaluation result of the target enterprise according to the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model;
determining the target endogenous risk characteristics and the target exogenous risk characteristics according to the risk assessment data and a pre-constructed index system, wherein the method comprises the following steps of:
Carrying out data processing and integration on the risk assessment data through a preset relational database to obtain a data report; the data report forms comprise an enterprise basic information table, a relation report form, a financial class report form, an operation class report form, an announcement class report form, a public opinion report form, a guarantee class report form, a financial market transaction report form, an external rating class report form, a judicial class report form and an enterprise credit class report form;
generating a target endogenous risk feature corresponding to the endogenous risk index and a target exogenous risk feature corresponding to the exogenous risk index according to the data report; the endophytic risk index comprises a management structure, enterprise attributes, illegal information, credit records, profitability, asset structure evaluation, debt repaying capability, cash flow, income quality, growth capability and judicial complaints; the exogenous risk index comprises a structural index, a scale index, an attenuation factor and an immune factor, wherein the structural index is related to the number of internal members and the average degree of ingress and egress, the scale index is related to the total assets, the total liabilities, the total incomes, the total profits and the number of clients with negative profits, the attenuation factor is related to the number of bad clients and the number of clients with credit balances, and the immune factor is inversely related to the probability of default.
2. The enterprise credit risk assessment method according to claim 1, wherein the step of acquiring risk assessment data of the target enterprise comprises:
And purchasing risk assessment data of the target enterprise through a preset data service provider, wherein the risk assessment data comprises industrial and commercial data, judicial data, stock market and bond market transaction data, announcement data, enterprise management data, financial data, enterprise relation data, enterprise guarantee data and rating data.
3. The method of claim 1, wherein the step of determining the credit risk assessment result of the target enterprise based on the target endogenous risk feature, the target exogenous risk feature, the trained endogenous risk assessment model, and the trained exogenous risk assessment model comprises:
Respectively inputting the target endogenous risk feature and the target exogenous risk feature into a trained endogenous risk evaluation model and a trained exogenous risk evaluation model to obtain an endogenous risk violation probability output by the endogenous risk evaluation model and an exogenous risk violation probability output by the exogenous risk evaluation model;
and determining a credit risk evaluation result of the target enterprise according to the endogenous risk violation probability and the exogenous risk violation probability.
4. The method of claim 3, wherein determining the credit risk assessment result of the target enterprise based on the endogenous risk breach probability and the exogenous risk breach probability comprises:
Comparing the intrinsic risk default probability and the extrinsic risk default probability with a preset probability threshold value respectively to obtain a comparison result;
and determining a credit risk evaluation result of the target enterprise according to the comparison result.
5. The enterprise credit risk assessment method according to claim 1, wherein the method further comprises:
Acquiring a training set sample, wherein the training set sample comprises historical evaluation data of a historical credit enterprise in a prediction window and actual credit violation results of a prediction time point;
determining sample endogenous risk characteristics and sample exogenous risk characteristics according to the historical evaluation data and the index system;
Training an initial endophytic risk evaluation model according to the sample endophytic risk characteristics and the actual credit violation results to obtain a trained endophytic risk evaluation model;
And training an initial exogenous risk evaluation model according to the sample exogenous risk characteristics and the actual credit violation results to obtain a trained exogenous risk evaluation model.
6. The method of claim 5, wherein training an initial endogenous risk assessment model based on the sample endogenous risk characteristics and the actual credit violation results to obtain a trained endogenous risk assessment model comprises:
training a plurality of preset initial machine learning models through K-fold cross verification and grid search algorithm according to the sample endogenous risk characteristics and the actual credit violation results to obtain a plurality of trained machine learning models;
and determining an optimal model in the plurality of machine learning models as a trained endogeneous risk evaluation model.
7. An enterprise credit risk assessment apparatus, comprising:
the data acquisition module is used for acquiring risk assessment data of a target enterprise;
the feature determining module is used for determining target endogenous risk features and target exogenous risk features according to the risk assessment data and a pre-constructed index system; the index system comprises an endogenous risk index and an exogenous risk index obtained based on a knowledge graph;
The result determining module is used for determining a credit risk evaluation result of the target enterprise according to the target endogenous risk characteristics, the target exogenous risk characteristics, the trained endogenous risk evaluation model and the trained exogenous risk evaluation model;
The characteristic determining module is specifically configured to: carrying out data processing and integration on the risk assessment data through a preset relational database to obtain a data report; the data report forms comprise an enterprise basic information table, a relation report form, a financial class report form, an operation class report form, an announcement class report form, a public opinion report form, a guarantee class report form, a financial market transaction report form, an external rating class report form, a judicial class report form and an enterprise credit class report form; generating a target endogenous risk feature corresponding to the endogenous risk index and a target exogenous risk feature corresponding to the exogenous risk index according to the data report; the endophytic risk index comprises a management structure, enterprise attributes, illegal information, credit records, profitability, asset structure evaluation, debt repaying capability, cash flow, income quality, growth capability and judicial complaints; the exogenous risk index comprises a structural index, a scale index, an attenuation factor and an immune factor, wherein the structural index is related to the number of internal members and the average degree of ingress and egress, the scale index is related to the total assets, the total liabilities, the total incomes, the total profits and the number of clients with negative profits, the attenuation factor is related to the number of bad clients and the number of clients with credit balances, and the immune factor is inversely related to the probability of default.
8. An electronic device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, wherein the processor implements the method of any of claims 1-6 when the computer program is executed.
9. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor performs the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643781.8A CN112734559B (en) | 2020-12-30 | 2020-12-30 | Enterprise credit risk evaluation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643781.8A CN112734559B (en) | 2020-12-30 | 2020-12-30 | Enterprise credit risk evaluation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734559A CN112734559A (en) | 2021-04-30 |
| CN112734559B true CN112734559B (en) | 2024-04-30 |
Family
ID=75609282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011643781.8A Active CN112734559B (en) | 2020-12-30 | 2020-12-30 | Enterprise credit risk evaluation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734559B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313615A (en) * | 2021-06-23 | 2021-08-27 | 北京鼎泰智源科技有限公司 | Method and device for quantitatively grading and grading enterprise judicial risks |
| CN113506173A (en) * | 2021-08-06 | 2021-10-15 | 国网电子商务有限公司 | A credit risk assessment method and related equipment |
| CN113822761A (en) * | 2021-09-26 | 2021-12-21 | 深圳微众信用科技股份有限公司 | Credit risk assessment method and system |
| CN114004491A (en) * | 2021-10-29 | 2022-02-01 | 中国建设银行股份有限公司 | Retail risk exposure pool dividing method and device, computer equipment and medium |
| CN114019942B (en) * | 2021-11-04 | 2023-08-29 | 哈尔滨工业大学 | A security threat assessment method for industrial robot systems based on time-sharing frequency |
| CN114841792A (en) * | 2021-12-22 | 2022-08-02 | 云汉芯城（上海）互联网科技股份有限公司 | A method for predicting customer credit limit based on machine learning |
| CN114240210B (en) * | 2021-12-22 | 2024-12-24 | 建信金融科技有限责任公司 | Credit evaluation method, device, equipment and computer-readable storage medium |
| CN114462891A (en) * | 2022-04-07 | 2022-05-10 | 国家电投集团科学技术研究院有限公司 | A carbon emission detection method and device thereof |
| CN115496357B (en) * | 2022-09-20 | 2025-07-15 | 合肥工业大学 | Enterprise credit risk early warning method and system integrating forum text temporal characteristics |
| CN117112808B (en) * | 2023-10-24 | 2024-01-19 | 中国标准化研究院 | A method for constructing information knowledge graph of credit-breaking subjects |
| CN117610941B (en) * | 2024-01-18 | 2024-04-26 | 杭州智诚惠通科技有限公司 | Method, system and medium for evaluating large-scale transportation credit based on database processing |
| CN119357198A (en) * | 2024-12-25 | 2025-01-24 | 石家庄学院 | Business big data analysis method, equipment and storage medium based on machine learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110443458A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN111784508A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | Enterprise risk assessment method, apparatus and electronic equipment |
-
2020
- 2020-12-30 CN CN202011643781.8A patent/CN112734559B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110443458A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN111784508A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | Enterprise risk assessment method, apparatus and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734559A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734559B (en) | Enterprise credit risk evaluation method and device and electronic equipment | |
| JP5566422B2 (en) | High risk procurement analysis and scoring system | |
| EP1361526A1 (en) | Electronic data processing system and method of using an electronic processing system for automatically determining a risk indicator value | |
| CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
| CN112950359B (en) | User identification method and device | |
| KR102628559B1 (en) | Method and device for providing real estate mortgage loan automatic screening platform | |
| CN106408325A (en) | User consumption behavior prediction analysis method based on user payment information and system | |
| CN111626855A (en) | Bond credit interest difference prediction method and system | |
| CN114118793B (en) | A local exchange risk warning method, device and equipment | |
| KR20230094936A (en) | Activist alternative credit scoring system model using work behavior data and method for providing the same | |
| CN110348922B (en) | Method and apparatus for generating information | |
| CN112785112A (en) | Risk rule extraction method and risk rule extraction device | |
| CN114418776A (en) | Data processing method, device, terminal equipment and medium | |
| CN114707733A (en) | Risk indicator prediction method and device, electronic equipment and storage medium | |
| CN114239985A (en) | Exchange rate prediction method and device, electronic equipment and storage medium | |
| CN119205305A (en) | A financial product intelligent matching and pre-credit method and system | |
| CN117934154A (en) | Transaction risk prediction method, model training method, device, equipment, medium and program product | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
| CN118096170A (en) | Risk prediction method and apparatus, device, storage medium, and program product | |
| CN117709710A (en) | Risk identification method, apparatus, device and storage medium | |
| CN116308615A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| US20220261824A1 (en) | System and method for determining and managing reputation of entities and industries through use of behavioral connections | |
| CN118411251A (en) | Information processing method and apparatus, device, storage medium, and program product | |
| CN119741054A (en) | Potential customer prediction method, device, electronic device and program product | |
| CN117934061A (en) | User repurchase behavior prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |