CN109409677A - Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium - Google Patents
Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN109409677A CN109409677A CN201811135377.2A CN201811135377A CN109409677A CN 109409677 A CN109409677 A CN 109409677A CN 201811135377 A CN201811135377 A CN 201811135377A CN 109409677 A CN109409677 A CN 109409677A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- credit risk
- credit
- risk evaluation
- model
- 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
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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to big data analysis process fields, a kind of Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium are disclosed, this method comprises: obtain business data of the Target Enterprise in preset period of time, according to business data determine Target Enterprise belonging to category of employment;Search the corresponding Credit Risk Assessment Model of category of employment;Credit risk characteristic variable is extracted from business data by preset data dimension and is input to Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result;Then Enterprise Credit Risk Evaluation report is generated according to Enterprise Credit Risk Evaluation result, since the present invention is category of employment belonging to first determining enterprise, then the corresponding Credit Risk Assessment Model of the sector classification is searched, it will be input in model from the credit risk characteristic variable extracted in business data again and carry out assessing credit risks, so that Enterprise Credit Risk Evaluation is more targeted, it is ensured that assessing credit risks result accuracy with higher and reliability.
Description
Technical field
The present invention relates to big data analysis processing technology field more particularly to a kind of Enterprise Credit Risk Evaluation methods, dress
It sets, equipment and storage medium.
Background technique
Currently, part financial institution to enterprise carry out assessing credit risks when, to all enterprises all use it is identical or
Similar assessment models carry out, but the difference of the actually affiliated industry of enterprise, management mode, the scope of business, Asset Allocation
Equal business data are different from, and the general business data by different enterprises is input to the same assessment models and carries out credit risk
The case where assessment result accuracy that assessment will lead to finally obtain is lower, even will appear estimation error when serious.Therefore,
How assessing credit risks accurately and effectively to be carried out to different enterprises, is a urgent problem to be solved.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of Enterprise Credit Risk Evaluation method, apparatus, equipment and storages to be situated between
Matter, it is intended to solve the technical issues of prior art accurately and effectively can not carry out assessing credit risks to different enterprises.
To achieve the above object, the present invention provides a kind of Enterprise Credit Risk Evaluation method, the method includes following
Step:
Business data of the Target Enterprise in preset period of time is obtained, the Target Enterprise is determined according to the business data
Affiliated category of employment;
The corresponding Credit Risk Assessment Model of the category of employment is searched in the mapping relations constructed in advance;
Credit risk characteristic variable, the credit risk that will be extracted are extracted from the business data by preset data dimension
Characteristic variable is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result;
The corresponding Enterprise Credit Risk Evaluation report of the Target Enterprise is generated according to the Enterprise Credit Risk Evaluation result
It accuses.
Preferably, the Credit Risk Assessment Model includes multiple assessing credit risks submodels;
It is described that credit risk characteristic variable, the credit that will be extracted are extracted from the business data by preset data dimension
The step of feature of risk variable is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result include:
Credit risk characteristic variable is extracted from the business data by preset data dimension;
The credit risk characteristic variable is divided according to the assessing credit risks submodel corresponding model classification
Class obtains sorted credit risk characteristic variable;
The sorted credit risk characteristic variable is separately input into corresponding assessing credit risks submodel;
The credit scoring for obtaining each assessing credit risks submodel output, is looked forward to according to the credit scoring
Industry assessing credit risks result.
Preferably, the credit scoring for obtaining each assessing credit risks submodel output, according to the credit wind
The step of danger scoring obtains Enterprise Credit Risk Evaluation result, comprising:
The credit scoring of each assessing credit risks submodel output is obtained, and inquires each credit risk in the database
Assess the corresponding default weighted value of submodel;
According to the default weighted value, summation is weighted to the credit scoring by following formula and obtains summation knot
Fruit, and using the summed result as Enterprise Credit Risk Evaluation result;
In formula, S is summed result, YiFor the credit scoring of assessing credit risks submodel output, XiFor credit risk
Assess the corresponding default weighted value of submodel.
Preferably, the business data for obtaining Target Enterprise in preset period of time, is determined according to the business data
Before the step of category of employment belonging to the Target Enterprise, the method also includes:
The company information for obtaining several enterprises classifies to the company information by default category of employment, obtains each
The corresponding trade information sample of category of employment;
Credit risk characteristic variable is extracted from the trade information sample by preset data dimension, and according to extracting
Credit risk characteristic variable establish the corresponding Credit Risk Assessment Model of every profession and trade classification.
It is preferably, described to extract credit risk characteristic variable from the trade information sample by preset data dimension,
And the step of corresponding Credit Risk Assessment Model of every profession and trade classification is established according to the credit risk characteristic variable extracted, packet
It includes:
Credit risk characteristic variable is extracted from the trade information sample by preset data dimension;
It carries out discretization to the credit risk characteristic variable that extracts and decomposes to obtain Variable Factors, and by the Variable Factors
It is input to default neural network model and carries out model training, obtain the corresponding Credit Risk Assessment Model of every profession and trade classification.
Preferably, after the step of acquisition every profession and trade classification corresponding Credit Risk Assessment Model, the method is also
Include:
Preset model decomposition rule is read from database, according to the model decomposition rule to every profession and trade classification
Corresponding Credit Risk Assessment Model carries out model fractionation, obtains corresponding assessing credit risks of each Credit Risk Assessment Model
Model;
Weight configuration is carried out to the corresponding assessing credit risks submodel of each Credit Risk Assessment Model respectively, obtains each letter
With the corresponding default weighted value of risk assessment submodel.
Preferably, described that the corresponding business standing of the Target Enterprise is generated according to the Enterprise Credit Risk Evaluation result
Before the step of Risk Assessment Report, the method also includes:
According to business data lookup, there are the affiliated enterprises of incidence relation with the Target Enterprise, and in the data
Inquiry whether there is the corresponding affiliated enterprise's assessing credit risks result of the affiliated enterprise in library;
If it exists, then affiliated enterprise's assessing credit risks result is obtained;
It is described to be commented according to the corresponding Credit Risk Assessment of Enterprise of the Enterprise Credit Risk Evaluation result generation Target Enterprise
The step of estimating report, comprising:
It is commented according to affiliated enterprise's assessing credit risks result and the corresponding Credit Risk Assessment of Enterprise of the Target Enterprise
Estimate the Enterprise Credit Risk Evaluation report that result generates the Target Enterprise.
In addition, to achieve the above object, the present invention also proposes a kind of Enterprise Credit Risk Evaluation device, described device packet
It includes: industry determining module, model searching module, risk evaluation module and report generation module;
Wherein, the industry determining module, for obtaining business data of the Target Enterprise in preset period of time, according to described
Business data determines category of employment belonging to the Target Enterprise;
The model searching module, for searching the corresponding credit of the category of employment in the mapping relations constructed in advance
Risk evaluation model;
The risk evaluation module, for extracting the change of credit risk feature from the business data by preset data dimension
The credit risk characteristic variable extracted is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation by amount
As a result;
The report generation module, it is corresponding for generating the Target Enterprise according to the Enterprise Credit Risk Evaluation result
Enterprise Credit Risk Evaluation report.
In addition, to achieve the above object, the present invention also proposes a kind of Enterprise Credit Risk Evaluation equipment, the equipment packet
It includes: memory, processor and being stored in the Enterprise Credit Risk Evaluation that can be run on the memory and on the processor
Program, the Enterprise Credit Risk Evaluation program are arranged for carrying out the step of Enterprise Credit Risk Evaluation method as described above
Suddenly.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, enterprise is stored on the storage medium
Assessing credit risks program, the Enterprise Credit Risk Evaluation program realize enterprise's letter as described above when being executed by processor
The step of with methods of risk assessment.
The present invention determines that target is looked forward to by obtaining business data of the Target Enterprise in preset period of time, according to business data
Category of employment belonging to industry;The corresponding Credit Risk Assessment Model of category of employment is searched in the mapping relations constructed in advance;It presses
Preset data dimension extracts credit risk characteristic variable from business data, and the credit risk characteristic variable extracted is input to
Credit Risk Assessment Model obtains Enterprise Credit Risk Evaluation result;Target enterprise is generated according to Enterprise Credit Risk Evaluation result
Industry corresponding Enterprise Credit Risk Evaluation report, as be enterprise is first determined according to business data belonging to category of employment, then
Corresponding Credit Risk Assessment Model is searched according to the category of employment determined, then extracts credit risk feature from business data
Variable, and the credit risk characteristic variable extracted is input to Credit Risk Assessment Model and carries out assessing credit risks, thus
So that Enterprise Credit Risk Evaluation is more targeted, it is ensured that assessing credit risks result accuracy with higher and reliable
Property.
Detailed description of the invention
Fig. 1 is that the structure of the Enterprise Credit Risk Evaluation equipment for the hardware running environment that the embodiment of the present invention is related to is shown
It is intended to;
Fig. 2 is the flow diagram of Enterprise Credit Risk Evaluation method first embodiment of the present invention;
Fig. 3 is the flow diagram of Enterprise Credit Risk Evaluation method second embodiment of the present invention;
Fig. 4 is the flow diagram of Enterprise Credit Risk Evaluation method 3rd embodiment of the present invention;
Fig. 5 is the structural block diagram of Enterprise Credit Risk Evaluation device first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the Enterprise Credit Risk Evaluation equipment for the hardware running environment that the embodiment of the present invention is related to
Structural schematic diagram.
As shown in Figure 1, the Enterprise Credit Risk Evaluation equipment may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory
1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include display
Shield (Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also include that the wired of standard connects
Mouth, wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
(WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random access memory (Random of high speed
Access Memory, RAM) memory, be also possible to stable nonvolatile memory (Non-Volatile Memory,
), such as magnetic disk storage NVM.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted to Enterprise Credit Risk Evaluation equipment
Restriction, may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
As shown in Figure 1, as may include operating system, data storage mould in a kind of memory 1005 of storage medium
Block, network communication module, Subscriber Interface Module SIM and Enterprise Credit Risk Evaluation program.
In Enterprise Credit Risk Evaluation equipment shown in Fig. 1, network interface 1004 be mainly used for and network server into
Row data communication;User interface 1003 is mainly used for carrying out data interaction with user;Enterprise Credit Risk Evaluation equipment of the present invention
In processor 1001, memory 1005 can be set in Enterprise Credit Risk Evaluation equipment, the Credit Risk Assessment of Enterprise is commented
Estimate equipment and the Enterprise Credit Risk Evaluation program stored in memory 1005 is called by processor 1001, and executes of the invention real
The Enterprise Credit Risk Evaluation method of example offer is provided.
The embodiment of the invention provides a kind of Enterprise Credit Risk Evaluation methods, are enterprise of the present invention letter referring to Fig. 2, Fig. 2
With the flow diagram of methods of risk assessment first embodiment.
In the present embodiment, the Enterprise Credit Risk Evaluation method the following steps are included:
Step S10: obtaining business data of the Target Enterprise in preset period of time, is determined according to the business data described
Category of employment belonging to Target Enterprise;
It should be noted that the executing subject of the present embodiment method can be with network communication, data processing and journey
The calculating service equipment of sort run function, such as mobile phone, tablet computer, PC, server (are below to execute with server
Main body is illustrated).The Target Enterprise is the enterprise for needing to carry out Enterprise Credit Risk Evaluation, and the preset time period can be with
It is the self defined time section pre-entered, such as 30 days June -2018 years on the 30th June in 2015, the business data includes enterprise
The administration of justice, public sentiment, industry and commerce, finance, reference, the data of management etc..Correspondingly, category of employment described in the present embodiment
Including but not limited to real estate, non-silver, banking, service trade, manufacturing industry and other industries.
Wherein, judicial data can obtain the jurisdictional information of enterprise by justice system, and therefrom extract in judgement document
It relates to and tells whether the amount of money, enterprise are related to the data informations such as great economy class dispute;Public sentiment data can pass through internet channel searching enterprise
Public sentiment socially, filtering out the public in one period is positive, intermediate or passive feelings for the public sentiment that the enterprise occurs
Thread;Industrial and commercial data can by industrial and commercial system obtain enterprise registered capital whether be reduced, the situation of change of shareholder's shareholding ratio
Equal data informations;Financial data can be obtained by enterprise financial report, and the level of profitability, the payment of debts water of enterprise are analyzed with this
Flat, growth etc.;Collage-credit data can obtain enterprise's sign by the credit information basic database at People's Bank of China's reference center
Believe situation;Experience management data can be obtained by enterprise's investigation report.
In the concrete realization, server can obtain business data of the Target Enterprise in preset period of time, according to business data
In the information such as the type of business, enterprise name, trade mark determine category of employment belonging to the Target Enterprise.
Step S20: the corresponding Credit Risk Assessment Model of the category of employment is searched in the mapping relations constructed in advance;
It should be noted that before executing this step, needs first to be constructed according to the business data of different industries enterprise and be used for
Carry out (industry) Credit Risk Assessment Model of assessing credit risks to the enterprises of different industries, and server build it is each
After the corresponding Credit Risk Assessment Model of industry, a category of employment and the corresponding assessing credit risks of category of employment can be also established
Mapping relations or corresponding relationship between model, in order to which server can determine category of employment belonging to Target Enterprise
Afterwards, it realizes to the quick determining of target Credit Risk Assessment Model and obtains according to the mapping relations.In the mapping relations
In, mapping end source is category of employment, and target side source is Credit Risk Assessment Model.
In the concrete realization, server is after being determined to category of employment belonging to Target Enterprise, can construct in advance
The corresponding Credit Risk Assessment Model of the category of employment is searched in mapping relations.
Step S30: credit risk characteristic variable is extracted from the business data by preset data dimension, by what is extracted
Credit risk characteristic variable is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result;
It should be noted that the preset data dimension includes but is not limited to law, public sentiment, industrial and commercial information, financial information
And/or the data such as people's row reference extract dimension.
It should be understood that the credit risk characteristic variable is the letter extracted from business data by the default dimension
It ceases data (including quantized data and non-quantized data).It, can be according to default quantitative criteria to its amount of progress for non-quantized data
It is re-used as feature of risk variable after change, such as enterprise can be obtained by internet channel socially for the public sentiment data of enterprise
Then public sentiment carries out just negative marking to public sentiment according to preset scoring criterion (for example, advantage, empty profit, neutrality etc.), then
The quantity of the corresponding great just negative public sentiment of enterprise in a period of time is counted, to realize the quantization to public sentiment data.
In the concrete realization, server can be according to numbers such as law, public sentiment, industrial and commercial information, financial information and/or people's row references
Credit risk characteristic variable is extracted from business data according to dimension is extracted, and then inputs the credit risk characteristic variable extracted
To the Credit Risk Assessment Model constructed in advance, the Enterprise Credit Risk Evaluation result of Credit Risk Assessment Model output is obtained.
Step S40: the corresponding business standing wind of the Target Enterprise is generated according to the Enterprise Credit Risk Evaluation result
Dangerous assessment report.
In the concrete realization, server is in the Enterprise Credit Risk Evaluation result for getting Credit Risk Assessment Model output
Afterwards, the corresponding Enterprise Credit Risk Evaluation of Target Enterprise can be generated according to the result to report, specifically, server can believe enterprise
It is compared with the corresponding credit scoring of risk evaluation result with default risk threshold value, target is judged according to comparison result
Enterprise whether there is credit risk, and or be determined at the credit scoring according to preset credit risk grade
In which kind of risk class, and then judge Target Enterprise with the presence or absence of credit risk;Credit risk is then from business data if it exists
The risk data for leading to enterprise there are credit risk is filtered out, and generates the corresponding enterprise of Target Enterprise according to these risk datas
Assessing credit risks report.
The present embodiment determines target according to business data by obtaining business data of the Target Enterprise in preset period of time
Category of employment belonging to enterprise;The corresponding Credit Risk Assessment Model of category of employment is searched in the mapping relations constructed in advance;
Credit risk characteristic variable is extracted from business data by preset data dimension, and the credit risk characteristic variable extracted is inputted
To Credit Risk Assessment Model, Enterprise Credit Risk Evaluation result is obtained;Target is generated according to Enterprise Credit Risk Evaluation result
Enterprise's corresponding Enterprise Credit Risk Evaluation report, as be enterprise is first determined according to business data belonging to category of employment, so
Corresponding Credit Risk Assessment Model is searched according to the category of employment determined afterwards, then extracts credit risk spy from business data
Variable is levied, and the credit risk characteristic variable extracted is input to Credit Risk Assessment Model and carries out assessing credit risks, from
And make Enterprise Credit Risk Evaluation more targeted, it is ensured that assessing credit risks result accuracy with higher and can
By property.
With reference to Fig. 3, Fig. 3 is the flow diagram of Enterprise Credit Risk Evaluation method second embodiment of the present invention.
Based on above-mentioned first embodiment, in Enterprise Credit Risk Evaluation method provided in this embodiment in the step S10
Before, further includes:
Step S01: obtaining the company information of several enterprises, divides by default category of employment the company information
Class obtains the corresponding trade information sample of every profession and trade classification;
It should be noted that several described enterprises can be the enterprise or company of different industries classification, the default row
Industry classification can be real estate, non-silver, banking, six major class of service trade, manufacturing industry and other industries, certainly specific industry class
Other setting the present embodiment is with no restriction.It include enterprise's letter of several industry difference enterprises in the trade information sample
Breath.
In addition, in the present embodiment, server can first be believed according to enterprise after getting the company information of several enterprises
Breath is that each enterprise carries out user's portrait, to obtain the corresponding Credit Risk Assessment of Enterprise portrait of each enterprise;Then further according to described default
Category of employment classifies to Credit Risk Assessment of Enterprise portrait, to realize the classification to enterprise and company information, obtains each row
The corresponding trade information sample of industry classification.
It should be understood that so-called portrait, i.e. user (enterprise) information labels, be exactly by collecting and analysis user society
After the data of the main informations such as attribute, living habit, consumer behavior, the business overall picture of a user is ideally taken out.?
Credit risk portrait is carried out to enterprise in the present embodiment, i.e., in a large amount of business data (such as law, public sentiment, industrial and commercial information, finance letter
Breath and/or people's row reference etc.) comprehensive analysis is carried out to basic condition, behavior pattern of enterprise etc. on the basis of information, it is looked forward to
The credit label of industry.
In the concrete realization, server obtains the company information of several enterprises, by preset real estate, non-silver,
The categorys of employment such as banking, service trade, manufacturing industry and other industries classify to company information, obtain every profession and trade classification pair
The trade information sample answered.
Step S02: credit risk characteristic variable, and root are extracted from the trade information sample by preset data dimension
The corresponding Credit Risk Assessment Model of every profession and trade classification is established according to the credit risk characteristic variable extracted.
In the concrete realization, server, can be by preset data after obtaining the corresponding trade information sample of every profession and trade classification
Dimension extracts credit risk characteristic variable from the trade information sample;Then to the credit risk characteristic variable extracted
It carries out discretization and decomposes acquisition Variable Factors, and the Variable Factors are input to default neural network model and carry out model instruction
Practice, obtains the corresponding Credit Risk Assessment Model of every profession and trade classification.
It is understood that often accuracy is not high for initially training model out, therefore it is necessary to right in practical applications
Initially training model out is optimized to improve the accuracy of model output result.Specifically, can be by improving to credit wind
Precision when dangerous characteristic variable (training data) is extracted comes implementation model optimization, the i.e. accuracy of raising training data or effective
Property.Therefore, in the present embodiment server after obtaining Credit Risk Assessment Model, can also according to Credit Risk Assessment Model come
The efficient combination of each Variable Factors is selected, thus to obtain the incidence relation of high-order between Variable Factors, to improve to credit wind
Precision when dangerous characteristic variable is extracted, lift scheme performance.
Further, it to guarantee the credit risk characteristic variable precision with higher extracted, avoids extracting excessive
To the lesser characteristic variable of assessing credit risks influence degree, the calculation amount of server is caused to increase, server in the present embodiment
The corresponding variable information value of each Variable Factors in the initial credit risk evaluation model can be obtained;According to the variable information value
Screening for credit risk characteristic variable is extracted to described, obtains validity feature variable and the validity feature variable pair
The data type answered;Type extracts target credit risk characteristic variable from the trade information sample based on the data;It will
The target credit risk characteristic variable discretization is input to the recurrent neural networks model and carries out model training after decomposing, obtain
Obtain effective Credit Risk Assessment Model.
Wherein, the variable information value can be the corresponding variation coefficient of each Variable Factors;It is described to be believed according to the variable
The corresponding variable of each Variable Factors is believed specific may is that screen for extracting credit risk characteristic variable by breath value
Breath value is compared with preset threshold, obtains the useful variable factor that variable information value is higher than the preset threshold;Have described
The corresponding credit risk characteristic variable of Variable Factors is imitated as validity feature variable, and it is corresponding to obtain the validity feature variable
Data type.
It should be understood that the different corresponding variation coefficients of Variable Factors is not identical in a model, such as current assets
Debt ratio, the corresponding variation coefficient of the past 30 days this kind of Variable Factors of great negative public sentiment sum are theoretically greater than enterprise staff
Quantity, the corresponding variation coefficient of this kind of Variable Factors of enterprise's shareholder's number, therefore in the present embodiment, server can by each variable because
The corresponding variable information value of son is compared with preset threshold, then according to comparison result reject on model output result influence compared with
Small Variable Factors, to improve model computational efficiency.
In view of the Enterprise Credit Risk Evaluation method that the present embodiment proposes needs to become the credit risk feature filtered out
Amount fine or not label corresponding with each credit risk characteristic variable is input in model together to be trained, and each credit risk feature
Variable has certain relevance, is not necessarily mutually exclusive, and neural network model is preset described in the present embodiment and is preferably passed
Return neural network model, (also known as Recognition with Recurrent Neural Network model) (Recurrent Neural Network, RNN).
It should be understood that when carrying out assessing credit risks to enterprise, since the business data being related to is many kinds of, classification
It is many and diverse, it is trained if all business data are converged in a certain single model, is unfavorable for subsequent model optimization behaviour
Make, therefore, Enterprise Credit Risk Evaluation method provided in this embodiment is constructing the corresponding assessing credit risks mould of every profession and trade
After type, Credit Risk Assessment Model can also be split according to staff's preconfigured model decomposition rule, be obtained
The corresponding assessing credit risks submodel of each Credit Risk Assessment Model, in order to it is subsequent targetedly to each submodel into
Row optimization improves assessment accuracy rate to realize the global optimization to Credit Risk Assessment Model.
Specifically, server can read preset model decomposition rule from database, according to the model decomposition
Rule carries out model fractionation to the corresponding Credit Risk Assessment Model of every profession and trade classification, and it is corresponding to obtain each Credit Risk Assessment Model
Assessing credit risks submodel;Weight is carried out to the corresponding assessing credit risks submodel of each Credit Risk Assessment Model respectively
Configuration, obtains the corresponding default weighted value of each assessing credit risks submodel.
Wherein, the model decomposition rule can be configured to according to dimensions such as financial category, reference class and other classes to every profession and trade
Credit Risk Assessment Model carry out model fractionation, by Credit Risk Assessment Model be decomposed into financial category Credit Risk Assessment Model,
Three submodels such as reference class Credit Risk Assessment Model and other class Credit Risk Assessment Models, and phase is configured for each submodel
The default weighted value answered.
The present embodiment divides company information by default category of employment by the company information of several enterprises of acquisition
Class obtains the corresponding trade information sample of every profession and trade classification;Credit is extracted from trade information sample by preset data dimension
Feature of risk variable, and the corresponding assessing credit risks mould of every profession and trade classification is established according to the credit risk characteristic variable extracted
Type ensure that the accuracy with higher of the Enterprise credit risk of foundation.
With reference to Fig. 4, Fig. 4 is the flow diagram of Enterprise Credit Risk Evaluation method 3rd embodiment of the present invention.
Based on the various embodiments described above, in the present embodiment, the Credit Risk Assessment Model includes that multiple credit risks are commented
Estimate submodel.
Correspondingly, step S30 described in Enterprise Credit Risk Evaluation method provided in this embodiment may particularly include:
Step S301: credit risk characteristic variable is extracted from the business data by preset data dimension;
In the concrete realization, server can be according to numbers such as law, public sentiment, industrial and commercial information, financial information and/or people's row references
Credit risk characteristic variable is extracted from business data according to dimension is extracted.
Step S302: the credit risk feature is become according to the assessing credit risks submodel corresponding model classification
Amount is classified, and sorted credit risk characteristic variable is obtained;
It should be understood that the model classification as belonging to each assessing credit risks submodel is different, server from
When extracting credit risk characteristic variable in business data, need corresponding according to the assessing credit risks submodel split in advance
Model classification classify to credit risk characteristic variable, obtain sorted credit risk characteristic variable, such as will be industrial and commercial
The credit risk characteristic variable of the dimensions such as information, financial information is classified as financial category Credit Risk Assessment Model, by law, people's row
The credit risk characteristic variable of the dimensions such as reference is classified as reference class Credit Risk Assessment Model, by the credit risk of public sentiment dimension
Characteristic variable is classified as other class Credit Risk Assessment Models etc..
Step S303: the sorted credit risk characteristic variable is separately input into corresponding assessing credit risks
Model;
In the concrete realization, server, can be by sorted letter after completing to the classification of credit risk characteristic variable
Corresponding assessing credit risks submodel, which is separately input into, with feature of risk variable carries out assessing credit risks.
Step S304: the credit scoring of each assessing credit risks submodel output is obtained, according to the credit risk
Scoring obtains Enterprise Credit Risk Evaluation result.
In the concrete realization, server can by obtain the credit scoring of each assessing credit risks submodel output come
Obtain the Enterprise Credit Risk Evaluation result of Target Enterprise.
Specifically, the credit scoring that server can be exported by obtaining each assessing credit risks submodel, and in number
According to inquiring the corresponding default weighted value of each assessing credit risks submodel in library;Then according to the default weighted value, under
Formula is weighted summation to the credit scoring and obtains summed result, and using the summed result as Credit Risk Assessment of Enterprise
Assessment result;
In formula, S is summed result, YiFor the credit scoring of assessing credit risks submodel output, XiFor credit risk
Assess the corresponding default weighted value of submodel.
For example, if the corresponding default weighted value of financial category Credit Risk Assessment Model is 0.5, reference class assessing credit risks
The corresponding default weighted value of model is 0.35, and the corresponding default weighted value of other class Credit Risk Assessment Models is 0.15, then
When the credit scoring of financial category Credit Risk Assessment Model output is the letter that 80, reference class Credit Risk Assessment Model exports
Be 75 with risk score, the credit scoring of other class Credit Risk Assessment Models output is when being 90, to credit scoring
The summed result for being weighted summation is then 80*0.5+75*0.35+90*0.15=79.75.
Further, it is contemplated that can exist mostly between enterprise and enterprise certain business contact or direct investment, debt,
The relevances such as shareholder.Therefore an appearance of enterprise risk, affiliated enterprise may also will receive influences, thus consider enterprise it
Between relevance, for the accuracy for further increasing assessing credit risks, server can be according to enterprise's number in the present embodiment
It is investigated that looking for, there are the affiliated enterprises of incidence relation with the Target Enterprise, and inquiry whether there is the pass in the database
Join the corresponding affiliated enterprise's assessing credit risks of enterprise as a result, then obtaining affiliated enterprise's assessing credit risks knot if it exists
Fruit;Then according to affiliated enterprise's assessing credit risks result and the corresponding Enterprise Credit Risk Evaluation of the Target Enterprise
As a result the Enterprise Credit Risk Evaluation report of the Target Enterprise is generated.
The present embodiment from business data by extracting credit risk characteristic variable by preset data dimension;According to credit wind
Assessment submodel corresponding model classification in danger classifies to credit risk characteristic variable, obtains sorted credit risk feature
Variable;Sorted credit risk characteristic variable is separately input into corresponding assessing credit risks submodel;Obtain each credit
The credit scoring of risk assessment submodel output obtains Enterprise Credit Risk Evaluation as a result, having according to credit scoring
Improve to effect the flexibility and accuracy of Enterprise Credit Risk Evaluation.
In addition, the embodiment of the present invention also proposes a kind of storage medium, Credit Risk Assessment of Enterprise is stored on the storage medium
Appraisal procedure, the Enterprise Credit Risk Evaluation program realize that Credit Risk Assessment of Enterprise as described above is commented when being executed by processor
The step of estimating method.
It is the structural block diagram of Enterprise Credit Risk Evaluation device first embodiment of the present invention referring to Fig. 5, Fig. 5.
As shown in figure 5, the embodiment of the present invention propose Enterprise Credit Risk Evaluation device include: industry determining module 501,
Model searching module 502, risk evaluation module 503 and report generation module 504;
Wherein, the industry determining module 501, for obtaining business data of the Target Enterprise in preset period of time, according to
The business data determines category of employment belonging to the Target Enterprise;
The model searching module 502, it is corresponding for searching the category of employment in the mapping relations constructed in advance
Credit Risk Assessment Model;
The risk evaluation module 503, for extracting credit risk spy from the business data by preset data dimension
Variable is levied, the credit risk characteristic variable extracted is input to the Credit Risk Assessment Model, obtains Credit Risk Assessment of Enterprise
Assessment result;
The report generation module 504, for generating the Target Enterprise according to the Enterprise Credit Risk Evaluation result
Corresponding Enterprise Credit Risk Evaluation report.
The present embodiment determines target according to business data by obtaining business data of the Target Enterprise in preset period of time
Category of employment belonging to enterprise;The corresponding Credit Risk Assessment Model of category of employment is searched in the mapping relations constructed in advance;
Credit risk characteristic variable is extracted from business data by preset data dimension, and the credit risk characteristic variable extracted is inputted
To Credit Risk Assessment Model, Enterprise Credit Risk Evaluation result is obtained;Target is generated according to Enterprise Credit Risk Evaluation result
Enterprise's corresponding Enterprise Credit Risk Evaluation report, as be enterprise is first determined according to business data belonging to category of employment, so
Corresponding Credit Risk Assessment Model is searched according to the category of employment determined afterwards, then extracts credit risk spy from business data
Variable is levied, and the credit risk characteristic variable extracted is input to Credit Risk Assessment Model and carries out assessing credit risks, from
And make Enterprise Credit Risk Evaluation more targeted, it is ensured that assessing credit risks result accuracy with higher and can
By property.
Based on the above-mentioned Enterprise Credit Risk Evaluation device first embodiment of the present invention, propose that Credit Risk Assessment of Enterprise of the present invention is commented
Estimate the second embodiment of device.
In the present embodiment, the risk evaluation module 503 is also used to by preset data dimension from the business data
Extract credit risk characteristic variable;It is special to the credit risk according to the corresponding model classification of the assessing credit risks submodel
Sign variable is classified, and sorted credit risk characteristic variable is obtained;By the sorted credit risk characteristic variable point
It is not input to corresponding assessing credit risks submodel;The credit scoring of each assessing credit risks submodel output is obtained,
Enterprise Credit Risk Evaluation result is obtained according to the credit scoring.
Further, the risk evaluation module 503 is also used to obtain the credit of each assessing credit risks submodel output
Risk score, and the corresponding default weighted value of each assessing credit risks submodel is inquired in the database;According to the default power
Weight values, by following formula to the credit scoring be weighted summation obtain summed result, and using the summed result as
Enterprise Credit Risk Evaluation result;
In formula, S is summed result, YiFor the credit scoring of assessing credit risks submodel output, XiFor credit risk
Assess the corresponding default weighted value of submodel.
Further, the present embodiment Enterprise Credit Risk Evaluation device further includes model building module, the model foundation
Module classifies to the company information by default category of employment for obtaining the company information of several enterprises, obtains each
The corresponding trade information sample of category of employment;Credit risk spy is extracted from the trade information sample by preset data dimension
Variable is levied, and the corresponding Credit Risk Assessment Model of every profession and trade classification is established according to the credit risk characteristic variable extracted.
Further, the model building module is also used to mention from the trade information sample by preset data dimension
Take out credit risk characteristic variable;Discretization is carried out to the credit risk characteristic variable extracted and decomposes acquisition Variable Factors, and
The Variable Factors are input to default neural network model and carry out model training, obtain the corresponding credit risk of every profession and trade classification
Assessment models.
Further, the model building module is also used to read preset model decomposition rule from database,
Model fractionation is carried out to the corresponding Credit Risk Assessment Model of every profession and trade classification according to the model decomposition rule, obtains each credit
The corresponding risk assessment submodel of risk evaluation model;Respectively to the corresponding risk assessment submodel of each Credit Risk Assessment Model
Weight configuration is carried out, the corresponding default weighted value of each assessing credit risks submodel is obtained.
Further, the risk evaluation module 503 is also used to be searched and the Target Enterprise according to the business data
There are the affiliated enterprises of incidence relation, and inquiry whether there is corresponding affiliated enterprise, the affiliated enterprise in the database
Assessing credit risks result;If it exists, then affiliated enterprise's assessing credit risks result is obtained;Correspondingly, the report life
At module 504, it is also used to according to affiliated enterprise's assessing credit risks result and the corresponding enterprise's letter of the Target Enterprise
The Enterprise Credit Risk Evaluation report of the Target Enterprise is generated with risk evaluation result.
The other embodiments or specific implementation of Enterprise Credit Risk Evaluation device of the present invention can refer to above-mentioned each method
Embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as read-only memory/random access memory, magnetic disk, CD), including some instructions are used so that a terminal device (can
To be mobile phone, computer, server, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Enterprise Credit Risk Evaluation method, which is characterized in that the described method includes:
Obtain business data of the Target Enterprise in preset period of time, the Target Enterprise is determined according to the business data belonging to
Category of employment;
The corresponding Credit Risk Assessment Model of the category of employment is searched in the mapping relations constructed in advance;
Credit risk characteristic variable is extracted from the business data by preset data dimension, the credit risk feature that will be extracted
Variable is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result;
The corresponding Enterprise Credit Risk Evaluation report of the Target Enterprise is generated according to the Enterprise Credit Risk Evaluation result.
2. the method as described in claim 1, which is characterized in that the Credit Risk Assessment Model includes that multiple credit risks are commented
Estimate submodel;
It is described that credit risk characteristic variable, the credit risk that will be extracted are extracted from the business data by preset data dimension
The step of characteristic variable is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation result include:
Credit risk characteristic variable is extracted from the business data by preset data dimension;
Classified according to the corresponding model classification of the assessing credit risks submodel to the credit risk characteristic variable, is obtained
Obtain sorted credit risk characteristic variable;
The sorted credit risk characteristic variable is separately input into corresponding assessing credit risks submodel;
The credit scoring for obtaining each assessing credit risks submodel output obtains enterprise's letter according to the credit scoring
Use risk evaluation result.
3. method according to claim 2, which is characterized in that the credit for obtaining each assessing credit risks submodel output
Risk score, according to the credit scoring obtain Enterprise Credit Risk Evaluation result the step of, comprising:
The credit scoring of each assessing credit risks submodel output is obtained, and inquires each assessing credit risks in the database
The corresponding default weighted value of submodel;
According to the default weighted value, summation is weighted to the credit scoring by following formula and obtains summed result, and
Using the summed result as Enterprise Credit Risk Evaluation result;
In formula, S is summed result, YiFor the credit scoring of assessing credit risks submodel output, XiFor assessing credit risks
The corresponding default weighted value of submodel.
4. the method as described in claim 1, which is characterized in that the enterprise's number for obtaining Target Enterprise in preset period of time
According to, according to the business data determine the Target Enterprise belonging to category of employment the step of before, the method also includes:
The company information for obtaining several enterprises classifies to the company information by default category of employment, obtains every profession and trade
The corresponding trade information sample of classification;
Credit risk characteristic variable is extracted from the trade information sample by preset data dimension, and according to the letter extracted
The corresponding Credit Risk Assessment Model of every profession and trade classification is established with feature of risk variable.
5. method as claimed in claim 4, which is characterized in that the preset data dimension of pressing is from the trade information sample
Credit risk characteristic variable is extracted, and the corresponding credit of every profession and trade classification is established according to the credit risk characteristic variable extracted
The step of risk evaluation model, comprising:
Credit risk characteristic variable is extracted from the trade information sample by preset data dimension;
Discretization is carried out to the credit risk characteristic variable extracted and decomposes acquisition Variable Factors, and the Variable Factors are inputted
Model training is carried out to default neural network model, obtains the corresponding Credit Risk Assessment Model of every profession and trade classification.
6. method as claimed in claim 5, which is characterized in that the corresponding assessing credit risks mould of the acquisition every profession and trade classification
After the step of type, the method also includes:
Preset model decomposition rule is read from database, it is corresponding to every profession and trade classification according to the model decomposition rule
Credit Risk Assessment Model carry out model fractionation, obtain the corresponding assessing credit risks submodule of each Credit Risk Assessment Model
Type;
Weight configuration is carried out to the corresponding assessing credit risks submodel of each Credit Risk Assessment Model respectively, obtains each credit wind
The corresponding default weighted value of danger assessment submodel.
7. such as method of any of claims 1-6, which is characterized in that described according to the Enterprise Credit Risk Evaluation
As a result before generating the step of corresponding Enterprise Credit Risk Evaluation of the Target Enterprise is reported, the method also includes:
According to business data lookup, there are the affiliated enterprises of incidence relation with the Target Enterprise, and in the database
Inquiry whether there is the corresponding affiliated enterprise's assessing credit risks result of the affiliated enterprise;
If it exists, then affiliated enterprise's assessing credit risks result is obtained;
It is described that the corresponding Enterprise Credit Risk Evaluation report of the Target Enterprise is generated according to the Enterprise Credit Risk Evaluation result
The step of announcement, comprising:
According to affiliated enterprise's assessing credit risks result and the corresponding Enterprise Credit Risk Evaluation knot of the Target Enterprise
Fruit generates the Enterprise Credit Risk Evaluation report of the Target Enterprise.
8. a kind of Enterprise Credit Risk Evaluation device, which is characterized in that described device includes: industry determining module, model lookup
Module, risk evaluation module and report generation module;
Wherein, the industry determining module, for obtaining business data of the Target Enterprise in preset period of time, according to the enterprise
Data determine category of employment belonging to the Target Enterprise;
The model searching module, for searching the corresponding credit risk of the category of employment in the mapping relations constructed in advance
Assessment models;
The risk evaluation module, for extracting credit risk characteristic variable from the business data by preset data dimension,
The credit risk characteristic variable extracted is input to the Credit Risk Assessment Model, obtains Enterprise Credit Risk Evaluation knot
Fruit;
The report generation module, for generating the corresponding enterprise of the Target Enterprise according to the Enterprise Credit Risk Evaluation result
The report of industry assessing credit risks.
9. a kind of Enterprise Credit Risk Evaluation equipment, which is characterized in that the Enterprise Credit Risk Evaluation equipment includes: storage
Device, processor and it is stored in the Enterprise Credit Risk Evaluation program that can be run on the memory and on the processor, institute
It states Enterprise Credit Risk Evaluation program and is arranged for carrying out Enterprise Credit Risk Evaluation as described in any one of claims 1 to 7
The step of method.
10. a kind of storage medium, which is characterized in that Enterprise Credit Risk Evaluation program is stored on the storage medium, it is described
Enterprise Credit Risk Evaluation program realizes Credit Risk Assessment of Enterprise as described in any one of claim 1 to 7 when being executed by processor
The step of appraisal procedure.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811135377.2A CN109409677A (en) | 2018-09-27 | 2018-09-27 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
PCT/CN2018/123278 WO2020062660A1 (en) | 2018-09-27 | 2018-12-25 | Enterprise credit risk evaluation method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811135377.2A CN109409677A (en) | 2018-09-27 | 2018-09-27 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409677A true CN109409677A (en) | 2019-03-01 |
Family
ID=65465400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811135377.2A Pending CN109409677A (en) | 2018-09-27 | 2018-09-27 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109409677A (en) |
WO (1) | WO2020062660A1 (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961368A (en) * | 2019-03-18 | 2019-07-02 | 京东数字科技控股有限公司 | Data processing method and device based on machine learning |
CN110400215A (en) * | 2019-07-31 | 2019-11-01 | 浪潮软件集团有限公司 | Small micro- Enterprise Credit Rating Model construction method and system towards family, enterprise |
CN110417721A (en) * | 2019-03-07 | 2019-11-05 | 腾讯科技(深圳)有限公司 | Safety risk estimating method, device, equipment and computer readable storage medium |
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 |
CN110443489A (en) * | 2019-07-31 | 2019-11-12 | 北京明略软件系统有限公司 | Acquisition methods and device, storage medium, the electronic device of target industry |
CN110472680A (en) * | 2019-08-08 | 2019-11-19 | 京东城市(北京)数字科技有限公司 | Objective classification method, device and computer readable storage medium |
CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
CN110889589A (en) * | 2019-10-23 | 2020-03-17 | 今稠科技(上海)有限公司 | Online wind accuse service system of enterprise |
CN110930250A (en) * | 2020-02-12 | 2020-03-27 | 成都数联铭品科技有限公司 | Enterprise credit risk prediction method and system, storage medium and electronic equipment |
CN111191091A (en) * | 2019-12-30 | 2020-05-22 | 成都数联铭品科技有限公司 | Data classification method and system |
CN111260484A (en) * | 2020-01-14 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Data processing method, device, server and system for human injury identification |
CN111340365A (en) * | 2020-02-26 | 2020-06-26 | 深圳壹账通智能科技有限公司 | Enterprise data processing method and device, computer equipment and storage medium |
CN111369260A (en) * | 2020-03-10 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Privacy-protecting risk prediction method and device |
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 |
CN111915155A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Small and micro enterprise risk level identification method and device and computer equipment |
CN112561682A (en) * | 2020-12-10 | 2021-03-26 | 中信银行股份有限公司 | Bank credit granting risk assessment method and system for small micro-enterprise |
CN112613755A (en) * | 2020-12-25 | 2021-04-06 | 北京知因智慧科技有限公司 | Method and device for evaluating enterprise risk by using confidence coefficient and electronic equipment |
CN112633709A (en) * | 2020-12-26 | 2021-04-09 | 中国农业银行股份有限公司 | Enterprise credit investigation evaluation method and device |
CN112734598A (en) * | 2019-10-29 | 2021-04-30 | 北京国双科技有限公司 | Method for establishing outsourcing platform model, outsourcing party searching method and device |
CN112734099A (en) * | 2020-12-31 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise risk prediction method and device and server |
CN112734559A (en) * | 2020-12-30 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise credit risk evaluation method and device and electronic equipment |
CN112801773A (en) * | 2021-01-20 | 2021-05-14 | 招商银行股份有限公司 | Enterprise risk early warning method, device, equipment and storage medium |
CN112907351A (en) * | 2021-02-05 | 2021-06-04 | 中国工商银行股份有限公司 | Financial message abnormity identification method and device |
CN112990707A (en) * | 2021-03-12 | 2021-06-18 | 深圳工盟科技有限公司 | Construction risk assessment method, device, equipment and storage medium |
CN113177701A (en) * | 2021-04-15 | 2021-07-27 | 国任财产保险股份有限公司 | User credit assessment method and device |
CN114004212A (en) * | 2021-12-30 | 2022-02-01 | 深圳希施玛数据科技有限公司 | Data processing method, device and storage medium |
US20220147817A1 (en) * | 2020-11-10 | 2022-05-12 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
CN114757783A (en) * | 2022-04-26 | 2022-07-15 | 深圳平安综合金融服务有限公司 | Information identification method, device, equipment and storage medium |
CN114781937A (en) * | 2022-06-20 | 2022-07-22 | 华网领业(杭州)软件有限公司 | Method and device for pre-paid card enterprise risk early warning and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050119961A1 (en) * | 2003-12-02 | 2005-06-02 | Dun & Bradstreet, Inc. | Enterprise risk assessment manager system |
CN104966227A (en) * | 2015-06-11 | 2015-10-07 | 安徽融信金模信息技术有限公司 | Enterprise risk assessment system based on a plurality of operating data |
CN104992234A (en) * | 2015-06-11 | 2015-10-21 | 安徽融信金模信息技术有限公司 | Enterprise risk assessment method based on various kinds of operation data |
CN106779755A (en) * | 2016-12-31 | 2017-05-31 | 湖南文沥征信数据服务有限公司 | A kind of network electric business borrows or lends money methods of risk assessment and model |
-
2018
- 2018-09-27 CN CN201811135377.2A patent/CN109409677A/en active Pending
- 2018-12-25 WO PCT/CN2018/123278 patent/WO2020062660A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050119961A1 (en) * | 2003-12-02 | 2005-06-02 | Dun & Bradstreet, Inc. | Enterprise risk assessment manager system |
CN104966227A (en) * | 2015-06-11 | 2015-10-07 | 安徽融信金模信息技术有限公司 | Enterprise risk assessment system based on a plurality of operating data |
CN104992234A (en) * | 2015-06-11 | 2015-10-21 | 安徽融信金模信息技术有限公司 | Enterprise risk assessment method based on various kinds of operation data |
CN106779755A (en) * | 2016-12-31 | 2017-05-31 | 湖南文沥征信数据服务有限公司 | A kind of network electric business borrows or lends money methods of risk assessment and model |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110417721A (en) * | 2019-03-07 | 2019-11-05 | 腾讯科技(深圳)有限公司 | Safety risk estimating method, device, equipment and computer readable storage medium |
CN109961368A (en) * | 2019-03-18 | 2019-07-02 | 京东数字科技控股有限公司 | Data processing method and device based on machine learning |
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 |
CN110400215A (en) * | 2019-07-31 | 2019-11-01 | 浪潮软件集团有限公司 | Small micro- Enterprise Credit Rating Model construction method and system towards family, enterprise |
CN110443489A (en) * | 2019-07-31 | 2019-11-12 | 北京明略软件系统有限公司 | Acquisition methods and device, storage medium, the electronic device of target industry |
CN110400215B (en) * | 2019-07-31 | 2023-11-03 | 浪潮软件集团有限公司 | Method and system for constructing enterprise family-oriented small micro enterprise credit assessment model |
CN110472680A (en) * | 2019-08-08 | 2019-11-19 | 京东城市(北京)数字科技有限公司 | Objective classification method, device and computer readable storage medium |
CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
CN110889589A (en) * | 2019-10-23 | 2020-03-17 | 今稠科技(上海)有限公司 | Online wind accuse service system of enterprise |
CN112734598A (en) * | 2019-10-29 | 2021-04-30 | 北京国双科技有限公司 | Method for establishing outsourcing platform model, outsourcing party searching method and device |
CN111191091A (en) * | 2019-12-30 | 2020-05-22 | 成都数联铭品科技有限公司 | Data classification method and system |
CN111260484A (en) * | 2020-01-14 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Data processing method, device, server and system for human injury identification |
CN110930250A (en) * | 2020-02-12 | 2020-03-27 | 成都数联铭品科技有限公司 | Enterprise credit risk prediction method and system, storage medium and electronic equipment |
CN111340365A (en) * | 2020-02-26 | 2020-06-26 | 深圳壹账通智能科技有限公司 | Enterprise data processing method and device, computer equipment and storage medium |
CN111369260A (en) * | 2020-03-10 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Privacy-protecting risk prediction method and device |
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 |
CN111915155A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Small and micro enterprise risk level identification method and device and computer equipment |
US11960993B2 (en) * | 2020-11-10 | 2024-04-16 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
US20220147817A1 (en) * | 2020-11-10 | 2022-05-12 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
CN112561682A (en) * | 2020-12-10 | 2021-03-26 | 中信银行股份有限公司 | Bank credit granting risk assessment method and system for small micro-enterprise |
CN112613755A (en) * | 2020-12-25 | 2021-04-06 | 北京知因智慧科技有限公司 | Method and device for evaluating enterprise risk by using confidence coefficient and electronic equipment |
CN112633709A (en) * | 2020-12-26 | 2021-04-09 | 中国农业银行股份有限公司 | Enterprise credit investigation evaluation method and device |
CN112734559A (en) * | 2020-12-30 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise credit risk evaluation method and device and electronic equipment |
CN112734559B (en) * | 2020-12-30 | 2024-04-30 | 北京知因智慧科技有限公司 | Enterprise credit risk evaluation method and device and electronic equipment |
CN112734099A (en) * | 2020-12-31 | 2021-04-30 | 北京知因智慧科技有限公司 | Enterprise risk prediction method and device and server |
CN112801773A (en) * | 2021-01-20 | 2021-05-14 | 招商银行股份有限公司 | Enterprise risk early warning method, device, equipment and storage medium |
CN112907351A (en) * | 2021-02-05 | 2021-06-04 | 中国工商银行股份有限公司 | Financial message abnormity identification method and device |
CN112990707A (en) * | 2021-03-12 | 2021-06-18 | 深圳工盟科技有限公司 | Construction risk assessment method, device, equipment and storage medium |
CN113177701A (en) * | 2021-04-15 | 2021-07-27 | 国任财产保险股份有限公司 | User credit assessment method and device |
CN114004212A (en) * | 2021-12-30 | 2022-02-01 | 深圳希施玛数据科技有限公司 | Data processing method, device and storage medium |
CN114757783A (en) * | 2022-04-26 | 2022-07-15 | 深圳平安综合金融服务有限公司 | Information identification method, device, equipment and storage medium |
CN114781937A (en) * | 2022-06-20 | 2022-07-22 | 华网领业(杭州)软件有限公司 | Method and device for pre-paid card enterprise risk early warning and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2020062660A1 (en) | 2020-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409677A (en) | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium | |
CN109492945A (en) | Business risk identifies monitoring method, device, equipment and storage medium | |
CN109657894A (en) | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium | |
Du et al. | CUS-heterogeneous ensemble-based financial distress prediction for imbalanced dataset with ensemble feature selection | |
CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
Chen | Classifying credit ratings for Asian banks using integrating feature selection and the CPDA-based rough sets approach | |
CN104321794B (en) | A kind of system and method that the following commercial viability of an entity is determined using multidimensional grading | |
CN108648074A (en) | Loan valuation method, apparatus based on support vector machines and equipment | |
CN113095927B (en) | Method and equipment for identifying suspected transactions of backwashing money | |
CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
CN108492001A (en) | A method of being used for guaranteed loan network risk management | |
CN111882420A (en) | Generation method of response rate, marketing method, model training method and device | |
CN113449046A (en) | Model training method, system and related device based on enterprise knowledge graph | |
CN107609771A (en) | A kind of supplier's value assessment method | |
CN110782349A (en) | Model training method and system | |
CN117235633A (en) | Mechanism classification method, mechanism classification device, computer equipment and storage medium | |
CN116720118A (en) | Label quality intelligent analysis method and device, electronic equipment and storage medium | |
CN113988878B (en) | Graph database technology-based anti-fraud method and system | |
Dhabe et al. | Stock Market Trend Prediction Along with Twitter Sentiment Analysis | |
CN114092057A (en) | Project model construction method and device, terminal equipment and storage medium | |
CN113706258A (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
Lee et al. | Application of machine learning in credit risk scorecard | |
Kitajima et al. | Relationship between management policies and profitability for second section-listed manufacturing companies of the tokyo stock exchange (2016 results) | |
CN118095270B (en) | Construction method and device of logic analysis graph, electronic equipment and storage medium | |
CN117994016A (en) | Method for constructing retail credit risk prediction model and consumer credit business Scorebeta model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40002551 Country of ref document: HK |
|
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |
|
RJ01 | Rejection of invention patent application after publication |