CN114092216A - Enterprise credit rating method, apparatus, computer device and storage medium - Google Patents
Enterprise credit rating method, apparatus, computer device and storage medium Download PDFInfo
- Publication number
- CN114092216A CN114092216A CN202111109293.3A CN202111109293A CN114092216A CN 114092216 A CN114092216 A CN 114092216A CN 202111109293 A CN202111109293 A CN 202111109293A CN 114092216 A CN114092216 A CN 114092216A
- Authority
- CN
- China
- Prior art keywords
- risk
- reliability
- enterprise
- model
- data
- 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 64
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 238000012502 risk assessment Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 45
- 238000012795 verification Methods 0.000 claims description 37
- 238000012360 testing method Methods 0.000 claims description 34
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000000926 separation method Methods 0.000 claims description 5
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 238000009826 distribution Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 6
- 238000004140 cleaning Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013138 pruning Methods 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Abstract
The application relates to an enterprise credit rating method, an enterprise credit rating device, computer equipment and a storage medium. The method comprises the following steps: acquiring enterprise data according to an enterprise identifier in a rating request by responding to the rating request of a client; after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data; performing risk assessment on the risk characteristic indexes through a risk model to obtain an assessment score; reliability calculation is carried out on the reliability characteristic indexes through the reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level. The method is favorable for obtaining accurate enterprise credit rating, and greatly facilitates the problem of credit evaluation of small and medium-sized enterprises.
Description
Technical Field
The application relates to the technical field of big data, in particular to an enterprise credit rating method, an enterprise credit rating device, computer equipment and a storage medium.
Background
For many enterprises, credit can ensure the fund flow of the enterprises, and great help can be provided in the aspects of enterprise infrastructure construction, important project promotion, daily operation, emergency and the like.
In the conventional technology, credit assessment is generally performed by adopting an expert assessment method, and the specific assessment scheme is as follows: the business credit is rated using the expertise of the credit officer. The method needs a large number of high-end talents, is strong in subjectivity, only pays attention to certain key elements, lacks of comprehensive calculation of enterprise risks, has high requirements on the qualification of enterprises, and is difficult to obtain accurate credit rating because small and medium-sized micro enterprises often lack of related qualifications and key elements. Meanwhile, manual rating also brings a long auditing period, and results in low rating efficiency.
Disclosure of Invention
In view of the above, it is desirable to provide an enterprise credit rating method, apparatus, computer device and storage medium capable of more accurately rating a credit for an enterprise.
A method of enterprise credit rating, the method comprising:
responding to a rating request of a client, and acquiring enterprise data according to an enterprise identifier in the rating request;
after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data;
performing risk assessment on the risk characteristic indexes through a target risk model to obtain an assessment score;
performing reliability calculation on the reliability characteristic index through a target reliability model to obtain a reliability level;
and generating an enterprise credit rating result according to the evaluation score and the reliability level.
In one embodiment, before obtaining the enterprise data according to the enterprise identifier in the rating request, the method further comprises:
establishing different types of risk data characteristics according to the enterprise data samples; evaluating the effectiveness of the risk data features for enterprise risk prediction; screening risk data features with effectiveness larger than a threshold value from the risk data features to form a feature pool; dividing the risk data features in the feature pool into a training set, a test set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models; and selecting an optimal model from the plurality of first risk models as the target risk model.
In one embodiment, the selecting an optimal risk model from the plurality of first risk models as the target risk model includes:
if the risk data features in the training set selected by different models in the fitting process are different, adjusting the risk data features in the training set, the test set and the verification set; refitting the adjusted training set through a plurality of target algorithms to obtain a plurality of second risk models; and selecting an optimal model from the plurality of second risk models as the target risk model.
In one embodiment, the method further comprises:
performing risk assessment on the test set and the verification set through each second risk model to obtain risk probability; calculating the distinguishing degree and stability of the model according to the risk probability and the risk label; and selecting an optimal model from the plurality of second risk models as the risk model according to the risk probability, the discrimination and the stability.
In one embodiment, said assessing the effectiveness of said risk data characteristic in enterprise risk prediction comprises:
performing box separation on the risk data characteristics of different types to obtain box separation results; calculating an IV value and a GINI coefficient based on the binning result; and evaluating the effectiveness of the data characteristics on enterprise risk prediction through the IV value and the GINI coefficient.
In one embodiment, before obtaining the enterprise data according to the enterprise identifier in the rating request, the method further comprises:
establishing different types of reliability data characteristics according to the enterprise data samples;
evaluating the effectiveness of the reliability data features on enterprise reliability prediction;
screening reliability data features with effectiveness larger than a threshold value from the reliability data features to form a feature pool;
dividing the reliability data features in the feature pool into a training set, a test set and a verification set;
fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models;
and when the plurality of first reliability models reach a stable state and the accuracy reaches a preset threshold value according to the test set and the verification set, selecting an optimal model from the plurality of first reliability models as the target reliability model.
In one embodiment, the performing risk assessment on the risk characteristic indicator through a risk model to obtain an assessment score includes:
performing risk assessment on the risk characteristic indexes through a risk model to obtain target risk probability;
converting the target risk probability into the evaluation score based on the inter-score and the first odds ratio;
the reliability calculation of the reliability characteristic index through the reliability model to obtain the reliability level comprises:
reliability calculation is carried out on the reliability characteristic indexes through a reliability model to obtain reliability probability;
and converting the reliability probability into the reliability level based on the reliability mapping relation and the second advantage.
An enterprise credit rating apparatus, the apparatus comprising:
the business module is used for responding to a rating request of a client and acquiring enterprise data according to an enterprise identifier in the rating request;
the computing module is used for determining a risk characteristic index and a reliability characteristic index according to the enterprise data after being cleaned;
the decision-making module is used for carrying out risk assessment on the risk characteristic indexes through a risk model to obtain assessment scores; reliability calculation is carried out on the reliability characteristic indexes through a reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level.
In one embodiment, the apparatus further comprises:
the first modeling module is used for establishing different types of risk data characteristics according to the enterprise data samples; evaluating the effectiveness of the risk data features for enterprise risk prediction; screening risk data features with effectiveness larger than a threshold value from the risk data features to form a feature pool; dividing the risk data features in the feature pool into a training set, a test set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models; and selecting an optimal model from the plurality of first risk models as the target risk model.
In one embodiment, the first modeling module is further configured to adjust the risk data features in the training set, the test set, and the verification set if there is a difference in the risk data features in the training set selected by different models in the fitting process; refitting the adjusted training set through a plurality of target algorithms to obtain a plurality of second risk models; and selecting an optimal model from the plurality of second risk models as the target risk model.
In one embodiment, the apparatus further comprises:
the first verification module is used for respectively performing risk assessment on the test set and the verification set through each second risk model to obtain risk probability; calculating the distinguishing degree and stability of the model according to the risk probability and the risk label; and selecting an optimal model from the plurality of second risk models as the risk model according to the risk probability, the discrimination and the stability.
In one embodiment, the first modeling module is further configured to perform binning on the risk data features of different types to obtain binning results; calculating an IV value and a GINI coefficient based on the binning result; and evaluating the effectiveness of the data characteristics on enterprise risk prediction through the IV value and the GINI coefficient.
In one embodiment, the apparatus further comprises:
the second modeling module is used for establishing different types of reliability data characteristics according to the enterprise data samples; evaluating the effectiveness of the reliability data features on enterprise reliability prediction; screening reliability data features with effectiveness larger than a threshold value from the reliability data features to form a feature pool; dividing the reliability data features in the feature pool into a training set, a test set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models;
and the second verification module is used for selecting an optimal model from the first reliability models as the target reliability model when the first reliability models reach a stable state and the accuracy reaches a preset threshold value according to the test set and the verification set.
In one embodiment, the decision module is further configured to perform risk assessment on the risk characteristic indicator through a risk model to obtain a target risk probability; converting the target risk probability into the evaluation score based on the inter-score and the first odds ratio;
the decision module is further used for performing reliability calculation on the reliability characteristic indexes through a reliability model to obtain reliability probability; and converting the reliability probability into the reliability level based on the reliability mapping relation and the second advantage.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the above-described enterprise credit rating method.
A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, causes the processor to carry out the steps of the above-described enterprise credit rating method.
The enterprise credit rating method, the device, the equipment and the storage medium respond to the rating request of the client and acquire enterprise data according to the enterprise identification in the rating request; after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data; performing risk assessment on the risk characteristic indexes through a risk model to obtain an assessment score; reliability calculation is carried out on the reliability characteristic indexes through the reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level. By cleaning the enterprise data and then calculating the characteristic indexes, the abnormity and the repetition of the data can be reduced, and more accurate characteristic value marks are obtained, so that an accurate rating model is obtained. The credit level of the enterprise is comprehensively evaluated through the results of the risk model and the reliability model, the repayment capacity and the operation stability of the enterprise can be reflected more truly, the accurate credit rating of the enterprise is obtained, and the credit evaluation of small and medium-sized enterprises is facilitated greatly.
Drawings
FIG. 1 is a diagram of an application environment for the method of enterprise credit rating in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for enterprise credit rating, in one embodiment;
FIG. 3 is a diagram that illustrates the results of a business credit rating in one embodiment;
FIG. 4 is a process diagram of an enterprise credit rating method in one embodiment;
FIG. 5 is a schematic flow chart diagram of a risk model construction method in one embodiment;
FIG. 6 is a schematic representation of a risk profile indicator in one embodiment;
FIG. 7 is a schematic flow chart illustrating selection of an optimal model in one embodiment;
FIG. 8 is a schematic flow chart diagram illustrating a method for risk model testing and validation in one embodiment;
FIG. 9 is a graphical illustration of a reliability feature index in one embodiment;
FIG. 10 is a block diagram of the architecture of an enterprise credit rating apparatus in one embodiment;
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The enterprise credit rating method provided by the application can be applied to the application environment shown in FIG. 1. In the application environment, a terminal 102 and a server 104 are included.
The server 104 responds to the rating request of the terminal 102, and acquires enterprise data according to the enterprise identification in the rating request; after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data; the server 104 performs risk assessment on the risk characteristic indexes through the target risk model to obtain assessment scores; reliability calculation is carried out on the reliability characteristic indexes through a target reliability model to obtain reliability levels; the enterprise credit rating results are generated based on the evaluation scores and reliability levels, and the server 104 transmits the enterprise credit rating results back to the terminal 102.
The terminal 102 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like.
The server 104 may be an independent physical server or a service node in a blockchain system, a point-To-point (P2P, Peer To Peer) network is formed among the service nodes in the blockchain system, and the P2P Protocol is an application layer Protocol operating on a Transmission Control Protocol (TCP).
In addition, the server 104 may also be a server cluster composed of a plurality of physical servers, and may be a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
The terminal 102 and the server 104 may be connected through communication connection manners such as bluetooth, USB (Universal Serial Bus), or network, which is not limited herein.
In one embodiment, as shown in FIG. 2, there is provided a method for enterprise credit rating, illustrated by way of example as applied to the server of FIG. 1, comprising the steps of:
s202, responding to the rating request of the client, and acquiring enterprise data according to the enterprise identification in the rating request.
The enterprise id may refer to unique information for identifying an enterprise, such as a complete name or a unified credit code of an enterprise registered by a business. Enterprise data may refer to enterprise business data.
In one embodiment, a client sends a rating request carrying a business identification to a server, the rating request being used to obtain a credit rating for the business. And when the server receives the rating request, the server acquires enterprise data related to the enterprise from the database according to the enterprise identification in the rating request so as to rate the enterprise to obtain credit rating. Wherein the rating request includes a unique request sequence number.
S204, after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data;
the characteristic indexes may be simply called features or simply called indexes, and include risk characteristic indexes and reliability characteristic indexes. The risk characteristic index is an index for measuring whether an enterprise has an operation risk, and the reliability characteristic index is an index for measuring whether an enterprise is reliable.
In one embodiment, after the enterprise data is obtained, a business module in the server loads the enterprise data, and after the loading is completed, the enterprise data is cleaned and processed. Cleaning can refer to processing null values and abnormal values of data in the enterprise data and deleting repeated values; processing may refer to renaming conflicting keys in enterprise data, as well as data formatting and data sorting, among other things.
In one embodiment, the business module loads the cleaned enterprise data into a high-speed memory, and sends a feature index calculation request to a calculation module in the server, wherein parameters in the feature index calculation request may include an enterprise identifier and a request serial number.
In one embodiment, after receiving the characteristic index calculation request, the calculation module reads the cleaned enterprise data from the high-speed memory according to two parameters, namely the enterprise identifier and the request serial number, and performs characteristic calculation on the enterprise data by using a data flow calculation technology to quickly calculate a risk characteristic index and a reliability characteristic index. Wherein the risk characteristic indicator and the reliability characteristic indicator may form a set of characteristic indicators.
The data streaming computing technology is one of data processing technologies commonly used for big data, adopts a distributed computing system, and has the advantages of low delay, high throughput, continuous and stable operation, elastic scalability and the like.
In one embodiment, the calculation module performs format conversion on the feature index set obtained through calculation by the data stream type calculation technology to obtain a feature index set in a JSON format, and then returns the feature index set in the JSON format to the service module.
Among them, the JSON format is a lightweight data exchange format, easy to read and understand, easy to analyze and generate by a machine, and is an ideal data exchange language.
And S206, carrying out risk evaluation on the risk characteristic indexes through the target risk model to obtain evaluation scores.
In one embodiment, after a decision module in a server receives a rating grading request including feature index parameters and enterprise identification parameters sent by a business system, the decision module loads a target risk model file, and processes risk feature indexes through a target risk model to obtain a target risk probability so as to calculate an evaluation score.
In one embodiment, a decision module performs risk assessment on a risk characteristic index through a risk model to obtain a target risk probability; and converting the target risk probability into an evaluation score based on the score interval and the first odds ratio.
Wherein, the score areas are composed of continuous score sections, and the odds ratio refers to the ratio of the probability of a certain conjecture being true to the probability of a certain conjecture being false. A mapping relationship exists between the first odds ratio and the evaluation score, and the evaluation score is lower when the odds ratio is higher; conversely, the higher the evaluation score.
And S208, performing reliability calculation on the reliability characteristic indexes through the target reliability model to obtain reliability levels.
In one embodiment, after the decision module receives a rating grading request including the characteristic index parameter and the enterprise identification parameter sent by the service system, the decision module loads a target reliability model file, and processes the reliability characteristic index through a target reliability model to obtain the reliability level.
In one embodiment, the decision module performs reliability calculation on the reliability characteristic index through a reliability model to obtain reliability probability; and converting the reliability probability into a reliability level based on the reliability mapping relation and the second dominance ratio.
The reliability mapping relationship may refer to a mapping relationship between a preset reliability score and a reliability level, and the higher the reliability score is, the higher the reliability level is; the lower the reliability score is, the lower the reliability level is, a mapping relation exists between the second dominance ratio and the reliability score, and when the dominance ratio is larger, the lower the reliability score is; conversely, the higher the reliability level.
And S210, generating a business credit rating result according to the evaluation score and the reliability level.
In one embodiment, the decision module inputs the evaluation score and the reliability level into the comprehensive rating matrix model to obtain an enterprise credit rating result.
The comprehensive rating matrix is composed of evaluation scores and reliability levels, as shown in table 1, the comprehensive rating result is S, A, B, C, D, E of 6 levels, the S level represents that the credit risk of the enterprise is lowest, and the E level represents that the credit risk of the enterprise is highest. The evaluation scores are divided into 6 scoring areas of 800-; the data reliability is divided into three levels of high, medium and low.
TABLE 1
In one embodiment, the decision module returns the business credit rating results in JSON format to the business module, the business credit rating results including four parts of the assessment score, the composite rating, the assessment time, and the expiration date, as shown in fig. 3.
In one embodiment, the business module returns the enterprise credit rating result to the client, and the presentation mode of the enterprise credit rating result can be that the enterprise credit rating result is presented on a business system rating page, and the enterprise credit rating result can also be sent to other terminals through an api interface.
To make the business credit rating method more intuitive for those skilled in the art, it is described in conjunction with FIG. 4. And the user sends a rating application with the enterprise identification to the service system, and the service system loads data in combination with the enterprise identification after receiving the rating request and cleans the data. And after receiving the request for calculating the characteristic indexes sent by the service system, the real-time calculating system calculates the characteristic indexes of the data and returns the calculated result to the service system. And then, the business system requests the characteristic indexes and the enterprise identifications as parameters to a decision engine system, the decision engine processes the characteristic indexes through an operation model and a reliability model after receiving the characteristic indexes to obtain credit rating results, and finally, the credit rating results are sent back to the client and displayed.
The enterprise credit rating method is used for responding to a rating request of a client and acquiring enterprise data according to an enterprise identifier in the rating request; after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data; performing risk assessment on the risk characteristic indexes through a risk model to obtain an assessment score; reliability calculation is carried out on the reliability characteristic indexes through the reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level. By cleaning the enterprise data and then calculating the characteristic indexes, the abnormity and the repetition of the data can be reduced, and more accurate characteristic value marks are obtained, so that an accurate rating model is obtained. The credit level of the enterprise is comprehensively evaluated through the results of the risk model and the reliability model, the repayment capacity and the operation stability of the enterprise can be reflected more truly, the accurate credit rating of the enterprise is obtained, and the credit evaluation of small and medium-sized enterprises is facilitated greatly.
In one embodiment, as shown in fig. 5, a risk model building method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
and S502, establishing different types of risk data characteristics according to the enterprise data samples.
As shown in fig. 6, the risk data characteristics are established based on historical customer sample data of each type of industry and commerce and judicial works of the enterprise, and include a static operation index, a dynamic operation index, a peer competitiveness index, an intellectual property index, an enterprise growth index, and an enterprise integrity index.
In one embodiment, a first modeling module in the server presets a risk modeling objective based on business experience of a professional.
And S504, evaluating the effectiveness of the risk data characteristics on enterprise risk prediction.
In one embodiment, the first modeling module performs binning on different types of risk data characteristics to obtain binning results; calculating an IV value and a GINI coefficient based on the binning result; and evaluating the effectiveness of the data characteristics on enterprise risk prediction through the IV value and the GINI coefficient.
The binning refers to a data preprocessing technology, and the risk data features are grouped according to a specific rule, so that the discretization of data is realized, the stability of the data is enhanced, and the risk of model overfitting is reduced. The IV value and the GINI coefficient are used to measure the ability of the data to distinguish between good and bad samples. The GINI index is also called as AR index, and represents the probability of a randomly selected feature being mistaken in the feature set, a smaller GINI index represents a smaller probability of a selected sample being mistaken in the set, whereas a larger GINI index represents a larger probability of a selected sample being mistaken in the set, and the calculation method of the kini index is as follows:
wherein P is the number of consistent pairs, Q is the number of inconsistent pairs, n is the number of all enterprises, and n.jIs the frequency sum in column j, i.e., the number sum of premium and non-premium businesses.
Watch two
| Risk rating | Good taste | Bad |
| Is low in | 8 | 2 |
| In | 3 | 4 |
| Height of | 1 | 10 |
| Total up to | 12 | 16 |
P＝2×[8×(4+10)+3×10]＝284
Q＝2×[3×2+1×(2+4)]＝24
For example, as shown in table two, the process of calculating the AR index is as above, with the final AR index being 0.6771.
In one embodiment, the first modeling module uses a variety of methods, such as quartiles, decision trees, and the like, to bin the features. The decision tree sub-box belongs to supervised sub-box, the data which is needed to be discretized and a prediction target are fitted through a tree model, the result after the decision tree training provides a threshold value of an internal node, the threshold value becomes the boundary of the sub-box, and the data are divided through the boundary to obtain the sub-box result.
And S506, screening the risk data characteristics with effectiveness larger than a threshold value from the risk data characteristics to form a characteristic pool.
In one embodiment, the first modeling module evaluates the effectiveness of the features on risk high-low prediction through the IV value and the GINI coefficient, and screens risk data features with effectiveness larger than a preset threshold value to form a feature pool.
And S508, dividing the risk data features in the feature pool into a training set, a testing set and a verification set.
The test set is used for evaluating the generalization ability of the model final model, but cannot be used as a basis for selection related to algorithms such as parameter adjustment and feature selection. The validation set is a sample set left alone before model training and can be used to demonstrate that a model is not over-trained resulting in validation of the training data only, but with the same evaluation effect for all samples.
In one embodiment, the test set may be a contemporaneous test set; the validation set may be a cross-term validation set.
And S510, fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models.
In one embodiment, the model is fitted using logistic regression, random forest, GBDT, XGBOOST, etc. algorithms to the training set. The random forest is a classifier which trains and predicts samples by using a plurality of decision trees and has the advantages of high fitting speed and capability of processing a large amount of data.
S512, selecting an optimal model from the plurality of first risk models as a target risk model.
In one implementation, the first risk model that best meets the business logic may be selected as the optimal risk model to participate in the ranking process of the decision module.
In one embodiment, if the risk data characteristics in the training set selected by different models in the fitting process are different, the risk data characteristics in the training set, the test set and the verification set are adjusted, the adjusted training set is re-fitted through a plurality of target algorithms to obtain a plurality of second risk models, and an optimal model is selected from the plurality of second risk models to serve as a target risk model.
The adjusting may refer to continuously adjusting the characteristic index until the characteristic index selected by the second risk model after refitting meets business logic by comparing the difference of the first risk model to the characteristic selection, where the adjusting manner of the characteristic index includes: aperture adjustment, feature pruning and feature merging.
According to the risk model modeling method, different types of risk data characteristics are established according to enterprise data samples; evaluating the effectiveness of the risk data characteristics on enterprise risk prediction; screening risk data features with effectiveness larger than a threshold value from the risk data features to form a feature pool; dividing the risk data features in the feature pool into a training set, a testing set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models; and selecting an optimal model from the plurality of first risk models as a target risk model. The characteristics are screened to form a characteristic pool, so that the model modeling efficiency can be improved; and selecting the optimal model from the plurality of first risk models as a target risk model, and obtaining the risk model which best accords with business logic through various selection modes, so that the accuracy of credit rating is improved.
In an embodiment, as shown in fig. 7, S512 may specifically include:
s702, performing risk assessment on the test set and the verification set through each second risk model to obtain risk probability;
s704, calculating model discrimination and stability according to the risk probability and the risk label;
in one embodiment, a first verification module in the server calculates the probability of a test set and a cross-period verification set according to a fitted model, and then calculates the model discrimination and stability index comprehensive evaluation to select an optimal model, wherein the discrimination indexes comprise AR, GINI kini coefficient, KS statistic, separation degree, model stability index PSI and feature stability VSI.
The model discrimination refers to the discrimination or discrimination of the model to the tested sample, and the discrimination of the model is calculated by commonly using KS statistical value, GINI coefficient and the like. And the KS statistic value is used for evaluating the risk discrimination capability of the model, and the greater the difference of the good and bad samples is, the greater the KS index is, the stronger the risk discrimination capability of the model is. The model stability refers to whether the prediction capabilities of the models are consistent in the time dimension, namely the models have the same degree of distinction in the test set, the interim verification set and the formal use, and the stability of the models is measured by using a PSI (program specific information) index in practice, wherein the index reflects the stability of the distribution of different samples in each section. The stability is required to be referred to, so the PSI indicator uses the actual distribution and the expected distribution as a reference, a training sample is usually used as the expected distribution during modeling, a verification sample is usually used as the actual distribution, and the calculation formula of the PSI is as follows:
wherein A isiRepresenting the fraction of validation samples in each bin, EiRepresenting the ratio of the training samples in each bin, the smaller the PSI value, the smaller the difference between the two distributions, representing the higher the model stability.
And S706, selecting an optimal model from the plurality of second risk models as a risk model according to the risk probability, the discrimination and the stability.
In the above embodiment, the first verification module in the server may select the optimal risk model by calculating the discrimination and stability of the model, so that the accuracy of the credit rating model is improved, and a more accurate enterprise rating result is obtained.
In one embodiment, as shown in fig. 8, a reliability model building method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s802, establishing different types of reliability data characteristics according to the enterprise data samples;
as shown in fig. 9, the reliability data characteristics include basic information indexes, negative information indexes, suspicious indexes of the shell company, associated transaction risk indexes, tax payment behaviors, cross validation indexes, and other abnormal behaviors.
S804, evaluating the effectiveness of the reliability data characteristics on enterprise reliability prediction;
s806, screening reliability data features with effectiveness larger than a threshold value from the reliability data features to form a feature pool;
s808, dividing the reliability data characteristics in the characteristic pool into a training set, a test set and a verification set;
s810, fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models;
and S812, when the plurality of first reliability models reach a stable state and the accuracy reaches a preset threshold value according to the test set and the verification set, selecting an optimal model from the plurality of first reliability models as a target reliability model.
For the modeling process of the reliability model in S802 to S810, reference may be specifically made to S502 to S512.
In the embodiment, different types of reliability data characteristics are established according to the enterprise data samples; evaluating the effectiveness of the reliability data characteristics on enterprise reliability prediction; screening reliability data characteristics with effectiveness larger than a threshold value from the reliability data characteristics to form a characteristic pool; dividing the reliability data features in the feature pool into a training set, a test set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models; and when the plurality of first reliability models reach a stable state and the accuracy reaches a preset threshold value according to the test set and the verification set, selecting an optimal model from the plurality of first reliability models as a target reliability model. The characteristics are screened to form a characteristic pool, so that the modeling efficiency of the model can be improved; and selecting an optimal model from the plurality of first reliability models as a target reliability model, and obtaining the reliability model which best accords with the business logic through judgment of the stable state and calculation of the accuracy rate, so that the accuracy of credit rating is improved.
It should be understood that although the various steps in the flowcharts of fig. 2, 5, 7-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 5, 7-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at multiple times, which are not necessarily performed in sequence, but may be performed alternately or in alternation with other steps or at least some of the other steps or stages.
In one embodiment, as shown in FIG. 10, there is provided an enterprise credit rating apparatus, which may be part of a computer device using a software module or a hardware module, or a combination of both, the apparatus comprising: a business module 1002, a calculation module 1004, and a decision module 1006, wherein:
the business module 1002 is configured to respond to a rating request of a client, and obtain enterprise data according to an enterprise identifier in the rating request;
the computing module 1004 is used for determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data after the cleaning of the enterprise data is completed;
a decision module 1006, configured to perform risk assessment on the risk characteristic indicator through the risk model to obtain an assessment score; reliability calculation is carried out on the reliability characteristic indexes through the reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level.
In the embodiment, the enterprise data is acquired according to the enterprise identification in the rating request by responding to the rating request of the client; after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data; performing risk assessment on the risk characteristic indexes through a risk model to obtain an assessment score; reliability calculation is carried out on the reliability characteristic indexes through the reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level. By cleaning the enterprise data and then calculating the characteristic indexes, the abnormity and the repetition of the data can be reduced, and more accurate characteristic value marks are obtained, so that an accurate rating model is obtained. The credit level of the enterprise is comprehensively evaluated through the results of the risk model and the reliability model, the repayment capacity and the operation stability of the enterprise can be reflected more truly, the accurate credit rating of the enterprise is obtained, and the credit evaluation of small and medium-sized enterprises is facilitated greatly.
In one embodiment, the apparatus further comprises:
a first modeling module 1008 for establishing different types of risk data characteristics from the enterprise data samples; evaluating the effectiveness of the risk data characteristics on enterprise risk prediction; screening risk data features with effectiveness larger than a threshold value from the risk data features to form a feature pool; dividing the risk data features in the feature pool into a training set, a testing set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models; and selecting an optimal model from the plurality of first risk models as a target risk model.
In one embodiment, the first modeling module 1008 is further configured to adjust risk data features in the training set, the test set, and the verification set if there is a difference in risk data features in the training set selected by different models in the fitting process; refitting the adjusted training set through a plurality of target algorithms to obtain a plurality of second risk models; and selecting the optimal model from the plurality of second risk models as a target risk model.
In one embodiment, the apparatus further comprises:
the first verification module 1010 is configured to perform risk assessment on the test set and the verification set through each second risk model to obtain a risk probability; calculating the distinguishing degree and stability of the model according to the risk probability and the risk label; and selecting an optimal model from the plurality of second risk models as a risk model according to the risk probability, the discrimination and the stability.
In one embodiment, the first modeling module 1008 is further configured to perform binning on the different types of risk data features to obtain binning results; calculating an IV value and a GINI coefficient based on the binning result; and evaluating the effectiveness of the data characteristics on enterprise risk prediction through the IV value and the GINI coefficient.
In one embodiment, the apparatus further comprises:
a second modeling module 1012 for establishing different types of reliability data characteristics from the enterprise data samples; evaluating the effectiveness of the reliability data characteristics on enterprise reliability prediction; screening reliability data characteristics with effectiveness larger than a threshold value from the reliability data characteristics to form a characteristic pool; dividing the reliability data features in the feature pool into a training set, a test set and a verification set; fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models;
the second verification module 1014 is configured to select an optimal model from the multiple first reliability models as a target reliability model when it is determined that the multiple first reliability models reach a stable state and the accuracy reaches a preset threshold according to the test set and the verification set.
In one embodiment, the decision module 1006 is further configured to perform risk assessment on the risk characteristic indicator through a risk model to obtain a target risk probability; converting the target risk probability into an evaluation score based on the score interval and the first dominance ratio;
the decision module 1006 is further configured to perform reliability calculation on the reliability feature index through the reliability model to obtain a reliability probability; and converting the reliability probability into a reliability level based on the reliability mapping relation and the second advantage.
For specific definitions of the enterprise credit rating means, reference may be made to the above definitions of the enterprise credit rating method, which are not described in detail herein. The various modules in the enterprise credit rating apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store enterprise data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements an enterprise credit rating method.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer-readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the steps in the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of business credit rating, the method comprising:
responding to a rating request of a client, and acquiring enterprise data according to an enterprise identifier in the rating request;
after the enterprise data are cleaned, determining a risk characteristic index and a reliability characteristic index according to the cleaned enterprise data;
performing risk assessment on the risk characteristic indexes through a target risk model to obtain an assessment score;
performing reliability calculation on the reliability characteristic index through a target reliability model to obtain a reliability level;
and generating an enterprise credit rating result according to the evaluation score and the reliability level.
2. The method of claim 1, wherein prior to obtaining business data based on the business identification in the rating request, the method further comprises:
establishing different types of risk data characteristics according to the enterprise data samples;
evaluating the effectiveness of the risk data features for enterprise risk prediction;
screening risk data features with effectiveness larger than a threshold value from the risk data features to form a feature pool;
dividing the risk data features in the feature pool into a training set, a test set and a verification set;
fitting the training set through a plurality of target algorithms to obtain a plurality of first risk models;
and selecting an optimal model from the plurality of first risk models as the target risk model.
3. The method of claim 2, wherein said selecting an optimal model among the plurality of first risk models as the target risk model comprises:
if the risk data features in the training set selected by different models in the fitting process are different, adjusting the risk data features in the training set, the test set and the verification set;
refitting the adjusted training set through a plurality of target algorithms to obtain a plurality of second risk models;
and selecting an optimal model from the plurality of second risk models as the target risk model.
4. The method of claim 3, further comprising:
performing risk assessment on the test set and the verification set through each second risk model to obtain risk probability;
calculating the distinguishing degree and stability of the model according to the risk probability and the risk label;
and selecting an optimal model from different second risk models as the risk model according to the risk probability, the discrimination and the stability.
5. The method of any of claims 2 to 4, wherein said assessing the effectiveness of said risk data characteristic for enterprise risk prediction comprises:
performing box separation on the risk data characteristics of different types to obtain box separation results;
calculating an IV value and a GINI coefficient based on the binning result;
and evaluating the effectiveness of the data characteristics on enterprise risk prediction through the IV value and the GINI coefficient.
6. The method of claim 1, wherein prior to obtaining business data based on the business identification in the rating request, the method further comprises:
establishing different types of reliability data characteristics according to the enterprise data samples;
evaluating the effectiveness of the reliability data features on enterprise reliability prediction;
screening reliability data features with effectiveness larger than a threshold value from the reliability data features to form a feature pool;
dividing the reliability data features in the feature pool into a training set, a test set and a verification set;
fitting the training set through a plurality of target algorithms to obtain a plurality of first reliability models;
and when the plurality of first reliability models reach a stable state and the accuracy reaches a preset threshold value according to the test set and the verification set, selecting an optimal model from the plurality of first reliability models as the target reliability model.
7. The method according to any one of claims 1 to 4 or 6, wherein the risk assessment of the risk characteristic indicator by a risk model, and obtaining an assessment score comprises:
performing risk assessment on the risk characteristic indexes through a risk model to obtain target risk probability;
converting the target risk probability into the evaluation score based on the inter-score and the first odds ratio;
the reliability calculation of the reliability characteristic index through the reliability model to obtain the reliability level comprises:
reliability calculation is carried out on the reliability characteristic indexes through a reliability model to obtain reliability probability;
and converting the reliability probability into the reliability level based on the reliability mapping relation and the second advantage.
8. An apparatus for enterprise credit rating, the apparatus comprising:
the business module is used for responding to a rating request of a client and acquiring enterprise data according to an enterprise identifier in the rating request;
the computing module is used for determining a risk characteristic index and a reliability characteristic index according to the enterprise data after being cleaned;
the decision-making module is used for carrying out risk assessment on the risk characteristic indexes through a risk model to obtain assessment scores; reliability calculation is carried out on the reliability characteristic indexes through a reliability model to obtain reliability levels; and generating an enterprise credit rating result according to the evaluation score and the reliability level.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109293.3A CN114092216A (en) | 2021-09-22 | 2021-09-22 | Enterprise credit rating method, apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109293.3A CN114092216A (en) | 2021-09-22 | 2021-09-22 | Enterprise credit rating method, apparatus, computer device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114092216A true CN114092216A (en) | 2022-02-25 |
Family
ID=80296160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111109293.3A Pending CN114092216A (en) | 2021-09-22 | 2021-09-22 | Enterprise credit rating method, apparatus, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114092216A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777597A (en) * | 2023-06-19 | 2023-09-19 | 中国银行保险信息技术管理有限公司 | Financial risk assessment method, device, storage medium and computer equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311401A (en) * | 2020-03-30 | 2020-06-19 | 百维金科(上海)信息科技有限公司 | Financial default probability prediction model based on LightGBM |
| CN111507822A (en) * | 2020-04-13 | 2020-08-07 | 深圳微众信用科技股份有限公司 | Enterprise risk assessment method based on feature engineering |
| CN112116245A (en) * | 2020-09-18 | 2020-12-22 | 平安科技（深圳）有限公司 | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium |
| CN112613972A (en) * | 2020-12-16 | 2021-04-06 | 江苏警官学院 | Credit risk-based medium and small micro-enterprise credit decision method |
| CN112767121A (en) * | 2020-12-31 | 2021-05-07 | 山东数字能源交易中心有限公司 | Method and device for processing risk level data |
| CN112767120A (en) * | 2020-12-31 | 2021-05-07 | 山东数字能源交易中心有限公司 | Enterprise evaluation data processing method and device |
| CN112785086A (en) * | 2021-02-10 | 2021-05-11 | 中国工商银行股份有限公司 | Credit overdue risk prediction method and device |
| CN113409150A (en) * | 2021-06-21 | 2021-09-17 | 深圳微众信用科技股份有限公司 | Operation risk and credit risk assessment method, device and computer storage medium |
-
2021
- 2021-09-22 CN CN202111109293.3A patent/CN114092216A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311401A (en) * | 2020-03-30 | 2020-06-19 | 百维金科(上海)信息科技有限公司 | Financial default probability prediction model based on LightGBM |
| CN111507822A (en) * | 2020-04-13 | 2020-08-07 | 深圳微众信用科技股份有限公司 | Enterprise risk assessment method based on feature engineering |
| CN112116245A (en) * | 2020-09-18 | 2020-12-22 | 平安科技（深圳）有限公司 | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium |
| CN112613972A (en) * | 2020-12-16 | 2021-04-06 | 江苏警官学院 | Credit risk-based medium and small micro-enterprise credit decision method |
| CN112767121A (en) * | 2020-12-31 | 2021-05-07 | 山东数字能源交易中心有限公司 | Method and device for processing risk level data |
| CN112767120A (en) * | 2020-12-31 | 2021-05-07 | 山东数字能源交易中心有限公司 | Enterprise evaluation data processing method and device |
| CN112785086A (en) * | 2021-02-10 | 2021-05-11 | 中国工商银行股份有限公司 | Credit overdue risk prediction method and device |
| CN113409150A (en) * | 2021-06-21 | 2021-09-17 | 深圳微众信用科技股份有限公司 | Operation risk and credit risk assessment method, device and computer storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777597A (en) * | 2023-06-19 | 2023-09-19 | 中国银行保险信息技术管理有限公司 | Financial risk assessment method, device, storage medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876600B (en) | Early warning information pushing method, device, computer equipment and medium | |
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| CN109165840B (en) | Risk prediction processing method, risk prediction processing device, computer equipment and medium | |
| CN109272396B (en) | Customer risk early warning method, device, computer equipment and medium | |
| CN107633265B (en) | Data processing method and device for optimizing credit evaluation model | |
| WO2017133492A1 (en) | Risk assessment method and system | |
| CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
| WO2007106786A2 (en) | Methods and systems for multi-credit reporting agency data modeling | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN112053061A (en) | Method and device for identifying surrounding label behaviors, electronic equipment and storage medium | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| CN111738843B (en) | Quantitative risk evaluation system and method using running water data | |
| CN111401600A (en) | Enterprise credit risk evaluation method and system based on incidence relation | |
| CN113537807B (en) | Intelligent wind control method and equipment for enterprises | |
| CN113298373A (en) | Financial risk assessment method, device, storage medium and equipment | |
| Wanke et al. | Revisiting camels rating system and the performance of Asean banks: a comprehensive mcdm/z-numbers approach | |
| CN114118793A (en) | Local exchange risk early warning method, device and equipment | |
| CN114092216A (en) | Enterprise credit rating method, apparatus, computer device and storage medium | |
| CN113554310A (en) | Enterprise credit dynamic evaluation model based on intelligent contract | |
| CN117010914A (en) | Identification method and device for risk group, computer equipment and storage medium | |
| CN113435713B (en) | Risk map compiling method and system based on GIS technology and two-model fusion | |
| CN113779116B (en) | Object ordering method, related equipment and medium | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN114170000A (en) | Credit card user risk category identification method, device, computer equipment and medium | |
| CN113112186A (en) | Enterprise evaluation method, device and equipment |
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 |