CN110246031A - Appraisal procedure, system, equipment and the storage medium of business standing - Google Patents
Appraisal procedure, system, equipment and the storage medium of business standing Download PDFInfo
- Publication number
- CN110246031A CN110246031A CN201910548413.6A CN201910548413A CN110246031A CN 110246031 A CN110246031 A CN 110246031A CN 201910548413 A CN201910548413 A CN 201910548413A CN 110246031 A CN110246031 A CN 110246031A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- assessed
- variable data
- data
- business standing
- 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 68
- 238000011156 evaluation Methods 0.000 claims description 29
- 230000008569 process Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 description 42
- 230000000875 corresponding effect Effects 0.000 description 29
- 238000004458 analytical method Methods 0.000 description 14
- 241001269238 Data Species 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 3
- 230000035800 maturation Effects 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 239000013068 control sample Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of appraisal procedure of business standing, system, equipment and storage medium, the appraisal procedure of the business standing includes: to obtain each target variable data of enterprise to be assessed, and match the corresponding default calculating weight of each target variable data；Based on each target variable data and each default calculating weight, the Default Probability of the enterprise to be assessed is calculated；It is scored according to business standing of the Default Probability to presently described enterprise to be assessed.The invention enables the assessment to business standing is more comprehensive, it is ensured that the accuracy that data calculate, and then promote the confidence level of assessment result.
Description
Technical field
The present invention relates to financial technology (Fintech) technical field more particularly to a kind of appraisal procedure of business standing, it is
System, equipment and storage medium.
Background technique
Along with financial technology (Fitech), the especially fast development of internet financial technology, have more and more
Technology be applied to financial field, in financial technology field, bank for a certain enterprise lending before, need to the enterprise into
Before row is borrowed therefore credit evaluation, accurately and comprehensively carries out enterprise to ensure that current loan can obtain basic safety guarantee
Credit evaluation has become increasingly important in financial technology field.However, the model that existing rating business credit method is not only applicable in
It is with limit, and enterprise's related data is acquired based on traditional reference mode, is only capable of the management state based on enterprise to Default Probability
It is identified, can not comprehensively carry out rating business credit, cause assessment result confidence level lower.
Summary of the invention
The main purpose of the present invention is to provide a kind of appraisal procedure of business standing, system, equipment and storage medium, purports
Making the assessment to business standing more comprehensive, it is ensured that the accuracy that data calculate, and then promote the confidence level of assessment result.
To achieve the above object, the present invention provides a kind of appraisal procedure of business standing, the assessment side of the business standing
Method the following steps are included:
Each target variable data of enterprise to be assessed are obtained, and match the corresponding default calculating of each target variable data
Weight；
Based on each target variable data and each default calculating weight, the promise breaking for calculating the enterprise to be assessed is general
Rate；
It is scored according to business standing of the Default Probability to presently described enterprise to be assessed.
Optionally, in each target variable data for obtaining enterprise to be assessed, and each target variable data are matched
Before the step of corresponding default calculating weight, further includes:
The enterprise to be assessed is extracted from enterprise's sample to be assessed, and determines each finger of the enterprise to be assessed
Mark variable data.
Optionally, described the step of extracting the enterprise to be assessed from enterprise's sample to be assessed, includes:
Obtain the trade classification information of all enterprise's samples to be assessed；
According to the trade classification information, belongs in the whole enterprise's samples to be assessed of detection and preset non-assessment industry
Non- assessment enterprise sample；
The non-assessment enterprise sample is purged, and described to be assessed after removing non-assessment enterprise's sample
In enterprise's sample, the enterprise to be assessed is extracted.
Optionally, the step of each target variable data of the determination enterprise to be assessed include:
It detects the enterprise to be assessed and whole index classifications of each target variable data is provided；
In all index classifications, the correlativity between each index classification is analyzed, is needed described in acquisition with determining
The target indicator classification of target variable data；
In each variable data under the target indicator classification, filtering out effective variable data is the target variable
Data.
Optionally, after the step of determination obtains the target indicator classification of the target variable data, further includes:
Legal person's credit data of the enterprise to be assessed is obtained, and using legal person's credit data as the target indicator
The one type of classification.
Optionally, each target variable data for obtaining enterprise to be assessed, and match each target variable data pair
The step of default calculating weight answered includes:
The cooperation data that the enterprise to be assessed provides are detected, each target variable number is extracted from the cooperation data
According to；
Each target variable data are subjected to stepping processing, are based on industry practice experience, are each target variable number
According to the corresponding default calculating weight of matching.
Optionally, described to be based on each target variable data and each default calculating weight, it calculates described to be assessed
The step of Default Probability of enterprise includes:
Logical model recurrence is carried out to each default calculating weight of each target variable data, with calculate it is described to
Assess the Default Probability of enterprise.
Optionally, the step to be scored according to business standing of the Default Probability to presently described enterprise to be assessed
Suddenly include:
Grading calibration is carried out to the Default Probability based on conversion process；
According to the Default Probability after grading calibration, score the business standing of the enterprise to be assessed.
In addition, the present invention also provides a kind of assessment system of business standing, the assessment system of the business standing includes:
Data acquisition module for obtaining each target variable data of enterprise to be assessed, and matches each target variable
The corresponding default calculating weight of data；
Probability evaluation entity, for being based on each target variable data and each default calculating weight, described in calculating
The Default Probability of enterprise to be assessed；
Evaluation module, for being scored according to business standing of the Default Probability to presently described enterprise to be assessed.
Optionally, the assessment system of the business standing further include:
Data determining module, for extracting the enterprise to be assessed from enterprise's sample to be assessed, and determine it is described to
Assess each target variable data of enterprise.
Optionally, the data determining module includes:
Index extra cell obtains legal person's credit data of the enterprise to be assessed, and legal person's credit data is made
For the one type of the target indicator classification.
In addition, the assessment equipment of the business standing includes: to deposit the present invention also provides a kind of assessment equipment of business standing
Reservoir, processor and the appraisal procedure for being stored in the business standing that can be run on the memory and on the processor, institute
State the step of realizing the appraisal procedure of business standing as described above when the appraisal procedure of business standing is executed by the processor.
In addition, being applied to computer the present invention also provides a kind of storage medium, enterprise's letter is stored on the storage medium
The appraisal procedure of appraisal procedure, the business standing realizes the assessment of business standing as described above when being executed by processor
The step of method.
The present invention is by from the trade classification information for obtaining all enterprise's samples to be assessed, and according to trade classification information,
The non-assessment enterprise sample for presetting non-assessment industry will be belonged to be purged, the enterprise to be assessed after removing non-assessment enterprise's sample
Enterprise to be assessed is determined in industry sample；The whole index classifications for detecting each target variable data that enterprise to be assessed provides, complete
In portion's index classification, the correlativity between each index classification is analyzed, to determine the target indicator class for obtaining target variable data
Not, and under the target indicator classification, the indices variable data that evaluation needs to obtain is determined；It is mentioned from enterprise to be assessed
Indices variable data is extracted in whole cooperation data of confession, each target variable data are subjected to stepping processing, and be stepping
The corresponding default calculating weight of each target variable Data Matching after processing；To each pre-designed of each target variable data
It calculates weight and carries out logical model recurrence, to calculate the Default Probability of enterprise to be assessed；Promise breaking based on conversion process to calculating
Probability carries out grading calibration, according to the Default Probability after grading calibration, scores the business standing of enterprise to be assessed.
It realizes, in whole index variable datas of the enterprise to be assessed of acquisition, in conjunction with the assessment experience of previous maturation,
Corresponding default calculating weight is matched for indices variable data, the indices data and the default weight that calculates are based on machine
Device learning method (logistic regression) is calculated, to obtain the Default Probability of current enterprise to be assessed, and according to calculated
Default Probability is converted, to obtain the final business standing scoring of enterprise to be assessed, as a result, the assessment to business standing
More comprehensively, it and ensures the accuracy that data calculate, and then improves the confidence level of assessment result.
Detailed description of the invention
Fig. 1 is the structural schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of the appraisal procedure first embodiment of business standing of the present invention；
Fig. 3 is the refinement step schematic diagram of step S100 in Fig. 2；
Fig. 4 is the flow diagram of the appraisal procedure second embodiment of business standing 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 the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the structural schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
It should be noted that Fig. 1 can be the structural schematic diagram of the hardware running environment of the assessment equipment of business standing.This
The assessment equipment of inventive embodiments business standing can be PC, the terminal devices such as portable computer.
As shown in Figure 1, the assessment equipment of the business standing may include: processor 1001, such as CPU, network interface
1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 for realizing these components it
Between connection communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard),
Optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include
Standard wireline interface and wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to steady
Fixed memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of
The storage device of aforementioned processor 1001.
It will be understood by those skilled in the art that the assessment equipment structure of business standing shown in Fig. 1 is not constituted to enterprise
The restriction of the assessment equipment of industry credit may include perhaps combining certain components or not than illustrating more or fewer components
Same component layout.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe the appraisal procedure of module, Subscriber Interface Module SIM and business standing.Wherein, operating system is to manage and control sample companies letter
The program of assessment equipment hardware and software resource supports the appraisal procedure of business standing and the fortune of other softwares or program
Row.
In the assessment equipment of business standing shown in Fig. 1, user interface 1003 is mainly used for being counted with each terminal
According to communication；Network interface 1004 is mainly used for connecting background server, carries out data communication with background server；And processor
1001 can be used for calling the appraisal procedure of the business standing stored in memory 1005, and execute following operation:
Each target variable data of enterprise to be assessed are obtained, and match the corresponding default calculating of each target variable data
Weight；
Based on each target variable data and each default calculating weight, the promise breaking for calculating the enterprise to be assessed is general
Rate；
It is scored according to business standing of the Default Probability to presently described enterprise to be assessed.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence is executing each target variable data for obtaining enterprise to be assessed, and it is corresponding pre- to match each target variable data
Before the step of weight is calculated in design, following steps are executed:
The enterprise to be assessed is extracted from enterprise's sample to be assessed, and determines each finger of the enterprise to be assessed
Mark variable data.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, and execute following steps:
Obtain the trade classification information of all enterprise's samples to be assessed；
According to the trade classification information, belongs in the whole enterprise's samples to be assessed of detection and preset non-assessment industry
Non- assessment enterprise sample；
The non-assessment enterprise sample is purged, and described to be assessed after removing non-assessment enterprise's sample
In enterprise's sample, the enterprise to be assessed is extracted.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, and execute following steps:
It detects the enterprise to be assessed and whole index classifications of each target variable data is provided；
In all index classifications, the correlativity between each index classification is analyzed, is needed described in acquisition with determining
The target indicator classification of target variable data；
In each variable data under the target indicator classification, filtering out effective variable data is the target variable
Data.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, it is described from all index classifications executing, determine the step for obtaining the target indicator classification of the target variable data
After rapid, following steps are executed:
Legal person's credit data of the enterprise to be assessed is obtained, and using legal person's credit data as the target indicator
The one type of classification.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, and execute following steps:
The cooperation data that the enterprise to be assessed provides are detected, each target variable number is extracted from the cooperation data
According to；
Each target variable data are subjected to stepping processing, are based on existing expertise, are each target variable
The corresponding default calculating weight of Data Matching.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, and execute following steps:
Logical model recurrence is carried out to each default calculating weight of each target variable data, with calculate it is described to
Assess the Default Probability of enterprise.
Further, processor 1001 can be also used for calling the assessment journey of the business standing stored in memory 1005
Sequence, and execute following steps:
Grading calibration is carried out to the Default Probability based on conversion process；
According to the Default Probability after grading calibration, score the business standing of the enterprise to be assessed.
Based on above-mentioned structure, each embodiment of the appraisal procedure of business standing of the present invention is proposed.
Referring to figure 2., Fig. 2 is the flow diagram of the appraisal procedure first embodiment of business standing of the present invention.
The embodiment of the invention provides the embodiments of the appraisal procedure of business standing, it should be noted that although in process
Logical order is shown in figure, but in some cases, it can be to be different from shown or described by sequence execution herein
Step.
The appraisal procedure of business standing of the embodiment of the present invention is applied to the assessment equipment of business standing, enterprise of the embodiment of the present invention
The assessment equipment of industry credit can be PC, and the terminal devices such as portable computer are not particularly limited herein.
The appraisal procedure of the present embodiment business standing includes:
Step S100, obtains each target variable data of enterprise to be assessed, and it is corresponding to match each target variable data
Default calculating weight.
From whole achievement datas that enterprise to be assessed provides, indices variable data needed for obtaining evaluation,
And combining mature practical experience is the respective corresponding default calculating weight of indices variable data matching extracted.
In the present embodiment, presetting and calculating weight is to call expertise scorecard model, based on credit evaluation practice
Through mature experience, the indices variable data for needing to analyze when carrying out credit evaluation to current enterprise to be assessed is set in advance
Each target variable data set weighted value shared in calculation formula.
Specifically, for example, in the present embodiment, expert is based on passing examination & approval experience provided by the current enterprise to be assessed
All in cooperation data source, extracts and indices variable number required for rating business credit is carried out to current enterprise to be assessed
According to such as shareholder's strength and support, business circumstance, prestige situation, pricing power, management stability, operation ability analysis, lever ratio
It is each under the indices classifications such as example analysis, analysis of clearing off debts ability, growth analysis, liquidity analysis and Analyzing profitability
Item variable data, and the experience mature based on credit evaluation practice, to indices variable data in indices classification
Under handled, for carrying out credit evaluation to current enterprise to be assessed.
Further, referring to figure 3., Fig. 3 be Fig. 2 in step S100 refinement step schematic diagram, step S100, obtain to
Each target variable data of enterprise are assessed, and matches the corresponding default calculating weight of each target variable data and includes:
Step S101 detects the cooperation data that the enterprise to be assessed provides, and extracts from the cooperation data each described
Target variable data.
From cooperation data source provided by current enterprise to be assessed, detecting current enterprise to be assessed is to carry out business standing
All cooperation data, and the index classification for needing to extract from whole cooperation data provided by assessment, and passed through according to expert
It tests under each index classification and extracts indices variable data required for carrying out rating business credit.
Specifically, for example, each data entry form provided from current enterprise to be assessed -- general taxpayer declare detail list,
Enterprise's upstream and downstream tables of data, balance sheet in profit flow table, determine that current enterprise to be assessed carries out needed for rating business credit
Want-financial category index and non-financial class index major class under each variable data index classification, such as shareholder's strength and support, manage
Situation, prestige situation, pricing power, management stability, operation ability analysis, lever proportion grading, analysis of clearing off debts ability, growth
Property analysis, 12 class index of liquidity analysis and Analyzing profitability, and combine by rating business credit practice at
Ripe expertise, from the indices variable number obtained in balance sheet and profit flow table under every financial category index classification
According to, and the indices obtained under non-financial target classification in detail list and enterprise's upstream and downstream tables of data are declared from general taxpayer
Variable data.
In the present embodiment, it by expertise, is provided in all cooperation data from current enterprise to be assessed, determining pair
Current enterprise to be assessed carries out each under items financial category index and non-financial class index major class required for rating business credit
Variable data index classification, and determine the indices variable data under every variable data index classification.
Each target variable data are carried out stepping processing, are based on industry practice experience, are each finger by step S102
It marks variable data and matches corresponding default calculating weight.
Indices data needed for carrying out rating business credit to current enterprise to be assessed to what is got carry out discrete
Change stepping processing, and calculate weight to the indices variable data matching after progress discretization stepping processing is default, that is, ties
The indices variable data that conjunction is in advance based on the mature experience setting of credit evaluation practice is shared in calculation formula
Weighted value, when for carrying out credit evaluation to current enterprise to be assessed, the weighted value according to indices variable data is carried out
It calculates.
It in another embodiment, can be direct by not carrying out the processing of discretization stepping to indices variable data
After carrying out simple normalized based on each original index variable data, respectively corresponding default calculating weight is matched.
Step S200 is based on each target variable data and each default calculating weight, calculates the enterprise to be assessed
The Default Probability of industry.
In the expertise according to indices variable data and corresponding every default calculating weight, to the current of acquisition
The indices variable data of enterprise to be assessed is calculated, to obtain the Default Probability of current enterprise to be assessed.
Further, step S200 includes:
Step S201 carries out logical model recurrence to each default calculating weight of each target variable data, with
Calculate the Default Probability of the enterprise to be assessed.
Specifically, for example, the indices variable data for the current enterprise to be assessed that will acquire, respective corresponding presets
Weight is calculated, i.e., the indices variable data for being in advance based on the mature experience setting of credit evaluation practice will be combined to count
Shared weighted value in calculation formula, and what is obtained refer to items needed for current enterprise's progress rating business credit to be assessed
Variable data is marked as input, is input in expertise scorecard model, according to linear regression formula to indices variable
Data are calculated, to obtain the Default Probability of current enterprise to be assessed.
Step S300 scores according to business standing of the Default Probability to presently described enterprise to be assessed.
Existing external model is called, to indices variable data and indices variable based on current enterprise to be assessed
The respective corresponding default calculating weight of data, the Default Probability of calculated current enterprise to be assessed is adjusted, and is based on
The Default Probability adjusted is aided with expertise and scores the business standing of current enterprise to be assessed.
Specifically, for example, obtain current criteria variable data where business indicators variable data to be assessed grouping in, when
Ratio ratio shared by the Default Probability of the Default Probability of preceding enterprise to be assessed and other each target variable data, and call external model
The ratio ratio reversely solve again after seeking logarithm, is adjusted, is based on the Default Probability to current enterprise to be assessed
The Default Probability adjusted is aided with the practical experience of expert's maturation, scores the business standing of current enterprise to be assessed.
In the present embodiment, the target variable data grouping of current enterprise to be assessed is, to the more of current enterprise to be assessed
A continuous target variable data are grouped merging, with the target variable data grouping of obtained current enterprise to be assessed.
Further, step S300, comprising:
Step S301 carries out grading calibration to the Default Probability based on conversion process.
Specifically, for example, in the present embodiment, since the codomain of Default Probability is between 0 to 1, expertise scorecard
Model needs to guarantee that codomain is converted (cannot simply use linear transformation) accordingly from the calibration that must assign to probability, therefore
0-1 probability seeks the laggard line of logarithm by ratio ratio (Odds ratio) classical in Logistic linear regression analysis model
Conversion, and reversely solve the Default Probability after being calibrated.
Specifically, each target variable data of the current enterprise to be assessed used when for example, being modeled based on external model,
The laggard line of logarithm is asked to turn using ratio ratio (Odds ratio) classical in above-mentioned Logistic linear regression analysis model
Change, and reversely solve the promise breaking index classification in the score that is calculated and current enterprise's indices variable data to be assessed into
Row single argument Logistic is returned, to obtain the estimates of parameters of a and b in following formula, formula such as: Log (PDt/ (1-PDt))
=a+b*score can be derived by the formula: PDt=exp (a+b*score)/(1+exp (a+b*score)), wherein PDt is
Default Probability estimated value, the default specific score value for calculating weight of score；It then calculates in external modeling training sample, index classification
The ratio for ratio ratio (rate of violation is divided by non-rate of violation) and CT (standard Default Probability ratio) value ratio ratio of breaking a contract, is denoted as k, passes through
The Default Probability estimated value of training sample is calibrated to through standard Default Probability Default Probability value adjusted by nonlinear change, with
PDa indicate, formula such as: PDa=exp (a+b*score)/(k+exp (a+b*score)), be based on formula PDt=exp (a+b*
The indices data and the default weight that calculates are based on machine learning (logistic regression) by score)/(1+exp (a+b*score))
Calculated, and according to formula PDa=exp (a+b*score)/(k+exp (a+b*score)) to the Default Probability estimated value into
Row adjustment finally converts Default Probability, obtains final enterprise to obtain the current accurate Default Probability of enterprise to be assessed
Industry credit scoring, thus, it is ensured that the accuracy that data calculate, and then promote the confidence level of assessment result.
Step S302 carries out the business standing of the enterprise to be assessed according to the Default Probability after grading calibration
Scoring.
The Default Probability of current enterprise's indices variable data to be assessed after being adjusted based on grading calibration, root
According to expertise, Default Probability is input to the model, to be converted to the business standing scoring of current enterprise to be assessed, base
In the scoring and analysis is carried out in conjunction with expertise obtain assessment result, and predict current enterprise to be assessed in 1 year following
Default risk.
The present invention is by from whole achievement datas that enterprise to be assessed provides, indices needed for obtaining evaluation
Variable data, and combining mature practical experience is that the indices variable data matching that extracts is respectively corresponding pre-designed
Calculate weight；Weight is being calculated according to indices variable data and corresponding every preset, to the current enterprise to be assessed of acquisition
Indices variable data calculated, to obtain the Default Probability of current enterprise to be assessed；Using scorecard model, to base
In current enterprise to be assessed indices variable data and indices variable data respectively corresponding to default calculating weight,
The Default Probability of calculated current enterprise to be assessed is adjusted, and is aided with expertise based on the Default Probability adjusted
It scores the business standing of current enterprise to be assessed.
It realizes, based on stepping processing is carried out to target variable data, reduces individual event variable data for total evaluation
As a result degree of influence leads to the problem of assessment result inaccuracy so as to avoid the error because of a certain item variable data, is promoted
Assessment efficiency；It is each in conjunction with the assessment experience of previous maturation in whole index variable datas of the enterprise to be assessed of acquisition
The indices data and the default weight that calculates are based on engineering by the corresponding default calculating weight of item target variable Data Matching
It practises (logistic regression) to be calculated, to obtain the Default Probability of current enterprise to be assessed, and according to calculated Default Probability
It is converted, to obtain the final business standing scoring of enterprise to be assessed, as a result, the assessment to business standing is more complete
Face, and ensure the accuracy that data calculate, and then improve the confidence level of assessment result.
Further, propose that the present invention is based on the characteristic analysis method second embodiments of machine learning model.
Referring to figure 4., Fig. 4 is the flow diagram of the appraisal procedure second embodiment of business standing of the present invention, based on upper
It states the appraisal procedure first embodiment of business standing, in the present embodiment, in above-mentioned steps S100, obtains each finger of enterprise to be assessed
Variable data is marked, and before the step of matching each target variable data corresponding default calculatings weight, enterprise of the present invention believes
Appraisal procedure further include:
Step S400 extracts the enterprise to be assessed from enterprise's sample to be assessed, and determines the enterprise to be assessed
Each target variable data.
In the present embodiment, due to the present invention does not have enterprise's sample to be assessed that is any corresponding or having similarity can be with
Use, therefore by expertise scorecard model, in the model, test sample be provide nearly ten thousand of cooperation data source to
Assess enterprise's sample.
Further, in step S400, the step of extracting the enterprise to be assessed from enterprise's sample to be assessed, includes:
Step S401 obtains the trade classification information of all enterprise's samples to be assessed.
Step S402, according to the trade classification information, detection all belong in enterprise's samples to be assessed preset it is non-
Assess the non-assessment enterprise sample of industry.
Based on the experience that credit evaluation practice is mature, obtained in cooperation data source data about all enterprises to be assessed
The trade classification information of industry sample, and detected in current enterprise's sample all to be assessed and belonged to such as gold according to the sector classification information
Melt, educate, social class, special entity, two high one specific industries such as surplus preset non-assessment industry.
The non-assessment enterprise sample is purged by step S403, and after removing the non-assessment enterprise sample
In enterprise's sample to be assessed, the enterprise to be assessed is extracted.
Such as finance that will test, education, social class, special entity, two high one surplus specific industries preset non-assessment
Industry is rejected, from reject determined in each remaining enterprise's sample to be assessed preset after non-assessment industry it is final to be assessed
Enterprise's sample, and determined based on definition standard and carry out the target variable number that credit evaluation needs to obtain for different enterprises to be assessed
According to.
Specifically, for example, in the development process of scorecard model, need to provide the credit risk bad sample of bank's identification
Definition credit risk bad sample definition is distinctly claimed, and essential condition defined in it is in new capital agreement
Client's capital, interest and the overdue number of days of any amount of money of default interest reach 90 days, and the present embodiment defines the good sample of enterprise to be assessed
Are as follows: there is refund behavior expression in same wealth year and there is no overdue enterprise, enterprise's bad samples to be assessed is defined as: there is refund to go
For and maximum overdue degree reach 30/60/90 day client, according to good, bad sample belonging to determining current enterprise to be assessed
The different brackets that standard or affiliated bad sample define is determined and is carried out required for rating business credit to current enterprise to be assessed
Each target variable data under the index classification of acquisition and each index classification.
Further, in step S400, the step of determining each target variable data of the enterprise to be assessed, includes:
Step S404 detects the enterprise to be assessed and provides whole index classifications of each target variable data.
When determining to current enterprise's progress rating business credit to be assessed after the index classification of required acquisition, detection
Current enterprise to be assessed whole index variable datas provided in cooperation data source, in current criteria classification belonging to it is complete
Portion's index classification.
Specifically, for example, being defined in standard based on bad sample belonging to current enterprise to be assessed " has refund behavior and most
Big overdue degree reaches 30 days standards ", it determines and carries out the finger obtained required for rating business credit for current enterprise to be assessed
Marking classification includes: 6 financial index major class: operation ability, Leveraged rate, debt paying ability, growth, mobility, profitability；
And 6 non-financial class index major class: shareholder's strength and support, business circumstance, prestige situation, pricing power, management stability,
Then detect current enterprise to be assessed whole index variable datas provided in cooperation data source, indices variable data institute
Whether whole index classifications of category include 12 index major class.
Step S405 analyzes the correlativity between each index classification in all index classifications, is needed with determining
Obtain the target indicator classification of the target variable data.
Current enterprise to be assessed whole index variable datas provided in cooperation data source are being determined, in current criteria
After whole index classifications belonging in classification, correlation analysis gradually is carried out to current whole index classifications, with complete from currently
It is determined in portion's index classification and rating business credit is carried out to current enterprise to be assessed, the required target for obtaining target variable data refers to
Mark classification.
In the present embodiment, according to the experience of model development, since the high-positive correlation that is unable between each index major class closes
System or middle high negative correlation relationship, wherein high-positive correlation relationship will lead to model index dimension and excessively concentrate and generate shakiness
Fixed situation, middle high negative correlation relationship then have the counteracting of score aggregation based on the Efficacy Problem of model itself, such as negative correlation
Effect, therefore in the expertise scorecard model of the present embodiment, using common high-positive correlation relationship > 70% and middle height
It spends negative correlativing relation < -40% and is used as alert standard, obtained by analysis in all currently each index classifications of enterprises to be assessed
In related coefficient, in addition to -71% negatively correlated triggering early warning occur in pricing power and business circumstance, between other index classifications
Correlativity performance it is good, it is thus determined that in whole index classifications of current enterprise to be assessed, to current enterprise to be assessed into
Obtain needed for row rating business credit target variable data target indicator classification be operation ability, Leveraged rate, debt paying ability,
Growth, mobility, profitability, shareholder's strength and support, business circumstance, prestige situation, management stability.
Step S406 filters out effective variable data in each variable data under the target indicator classification as institute
State target variable data.
It is determined from current whole index classifications and rating business credit, required acquisition index is carried out to current enterprise to be assessed
After the target indicator classification of variable data, by whole variable datas input under each target indicator classification by combining practice warp
It tests and expert adjusts carrying out in the expertise scorecard model of selection to enterprise to be assessed for generation, be based on the expertise
The set screening principle of scorecard model filters out from whole variable datas of input and carries out enterprise to current enterprise to be assessed
Credit evaluation, the useful variable data of required acquisition are as indices variable data.
Specifically, for example, determining in whole index classifications of current enterprise to be assessed, current enterprise to be assessed is looked forward to
The target indicator classification that target variable data are obtained needed for industry credit evaluation is operation ability, Leveraged rate, debt paying ability, growth
Property, mobility, profitability, after shareholder's strength and support, business circumstance, prestige situation, management stability, will be current to be evaluated
Multiple variable datas corresponding to each index classification in the cooperation data source of enterprise's offer are provided, are fully entered existing by combining
Industry practice experience and expert adjustment and generate enterprise to be assessed is carried out in the expertise scorecard model of selection,
Based on the screening principle that the expertise scorecard model is set, from the operation ability of input, Leveraged rate, debt paying ability, at
The each single item index such as long property, mobility, profitability, shareholder's strength and support, business circumstance, prestige situation, management stability
In multiple variable datas corresponding to classification, each single item target indicator when to current enterprise's progress credit evaluation to be assessed is filtered out
The corresponding useful variable data of classification, and using the useful variable data filtered out as the corresponding finger of the objectives index classification
Mark variable data.
In the present embodiment, such as operation ability, Leveraged rate, debt paying ability, growth belong to the mesh of financial category index
It marks in target variable data corresponding to index classification, specifically includes that financial data, tax data of enterprise to be assessed etc..
Further, in step S405, after the step of determining the target indicator classification for obtaining the target variable data,
The appraisal procedure of business standing of the present invention further include:
Step S407 obtains legal person's credit data of the enterprise to be assessed, and using legal person's credit data as institute
State the one type of target indicator classification.
The credit data of the business entity individual of current enterprise to be assessed is detected and obtained, and combines expertise by the method
The personal credit data of people carry out rating business credit as to current enterprise to be assessed, required acquisition target variable data
A kind of target indicator classification.
Specifically, for example, detecting current every credit data of the business entity to be assessed based on personal refund behavior, in conjunction with
Industry practice experience is by the credit data of business entity individual, when increasing to carry out credit evaluation to current enterprise to be assessed,
One type in the required target indicator classification for obtaining target variable data is carrying out enterprise to current enterprise to be assessed
The target indicator classification that target variable data are obtained needed for credit evaluation is operation ability, Leveraged rate, debt paying ability, growth
Property, mobility, profitability, except shareholder's strength and support, business circumstance, prestige situation, management stability, increase newly currently to
The legal person's credit for assessing enterprise is a target indicator classification.
The present invention is based on expertise scorecard models, are obtained in cooperation data source data about all enterprises to be assessed
The trade classification information of sample, and detected in current enterprise's sample all to be assessed and belonged to such as gold according to the sector classification information
Melt, educate, social class, special entity, two high one specific industries such as surplus preset non-assessment industry；Will test as finance,
Education, social class, special entity, two high one specific industries such as surplus non-assessment industry of presetting rejected, from rejecting each preset
Final enterprise's sample to be assessed is determined in remaining enterprise's sample to be assessed after non-assessment industry, and true based on definition standard
It is fixed that the target variable data that credit evaluation needs to obtain are carried out for different enterprises to be assessed；It is determining to current enterprise to be assessed
It carries out when rating business credit after the index classification of required acquisition, detects institute in cooperation data source, current enterprise to be assessed
Whole index variable datas of offer, affiliated whole index classifications in current criteria classification；And gradually to currently all referring to
It marks classification and carries out correlation analysis, to determine that carrying out business standing to current enterprise to be assessed comments from current whole index classifications
Estimate, the required target indicator classification for obtaining target variable data；According to target variable selection expertise scorecard model from
Under each target indicator classification, filters out and rating business credit, the effective items of required acquisition are carried out to current enterprise to be assessed
Target variable data；In addition, detecting and obtaining the credit data of the business entity individual of current enterprise to be assessed, and combine expert
Experience carries out rating business credit, required acquisition index by the personal credit data of the legal person, as to current enterprise to be assessed
A kind of target indicator classification of variable data.
It realizes, the various aspects of enterprise more to be assessed is accounted for, be applicable not only to original to be assessed
Each enterprise to be assessed in enterprise's sample carries out rating business credit, apply also for other be not belonging to it is new to be assessed in original sample
Enterprise enriches the use scope that credit evaluation is carried out to enterprise；In addition, by combining expertise scorecard model to be evaluated
The cooperation data for estimating enterprise's offer are screened, and are avoided enterprise to be assessed and are interfered that normally assesses to take advantage of by providing false data
Cheat risk；Also, it by increasing business entity's personal credit data as evaluation index, realizes enterprise operation and legal person's credit
It combines, enriches and the comprehensive of rating business credit is carried out to current enterprise to be assessed, further improve assessment result
Confidence level.
In addition, the embodiment of the present invention also proposes a kind of assessment system of business standing, the assessment system of the business standing
Include:
Data acquisition module for obtaining each target variable data of enterprise to be assessed, and matches each target variable
The corresponding default calculating weight of data；
Probability evaluation entity, for being based on each target variable data and each default calculating weight, described in calculating
The Default Probability of enterprise to be assessed；
Evaluation module, for being scored according to business standing of the Default Probability to presently described enterprise to be assessed.
Preferably, the assessment system of the business standing further include:
Data determining module for extracting the enterprise to be assessed from all enterprise's samples to be assessed, and determines institute
State each target variable data of enterprise to be assessed.
Preferably, data determining module, comprising:
Index extra cell obtains legal person's credit data of the enterprise to be assessed, and legal person's credit data is made
For the one type of the target indicator classification.
Business standing as described above is realized when the assessment system modules operation for the business standing that the present embodiment proposes
Appraisal procedure the step of, details are not described herein.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is applied to computer, i.e., the described storage medium is to calculate
Machine readable storage medium storing program for executing, the appraisal procedure of business standing is stored on the medium, and the appraisal procedure of the business standing is located
The step of reason device realizes the appraisal procedure of business standing as described above when executing.
Wherein, the appraisal procedure of the business standing run on the processor is performed realized method and can refer to
The present invention is based on each embodiments of the appraisal procedure of business standing, and 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 device 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 device 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 device.
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 ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Business device, 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 (13)
1. a kind of appraisal procedure of business standing, which is characterized in that the appraisal procedure of the business standing the following steps are included:
Each target variable data of enterprise to be assessed are obtained, and match the corresponding default calculating power of each target variable data
Weight；
Based on each target variable data and each default calculating weight, the Default Probability of the enterprise to be assessed is calculated；
It is scored according to business standing of the Default Probability to presently described enterprise to be assessed.
2. the appraisal procedure of business standing as described in claim 1, which is characterized in that obtain each of enterprise to be assessed described
Target variable data, and before the step of matching each target variable data corresponding default calculating weight, further includes:
The enterprise to be assessed is extracted from enterprise's sample to be assessed, and determines that each index of the enterprise to be assessed becomes
Measure data.
3. the appraisal procedure of business standing as claimed in claim 2, which is characterized in that described to be mentioned from enterprise's sample to be assessed
The step of taking out the enterprise to be assessed include:
Obtain the trade classification information of all enterprise's samples to be assessed；
According to the trade classification information, detection, which all belongs in enterprise's samples to be assessed, to be preset non-assessment the non-of industry and comments
Estimate enterprise's sample；
The non-assessment enterprise sample is purged, and the enterprise to be assessed after removing non-assessment enterprise's sample
In sample, the enterprise to be assessed is extracted.
4. the appraisal procedure of business standing as claimed in claim 3, which is characterized in that the determination enterprise to be assessed
The step of each target variable data includes:
It detects the enterprise to be assessed and whole index classifications of each target variable data is provided；
In all index classifications, the correlativity between each index classification is analyzed, needs to obtain the index with determination
The target indicator classification of variable data；
In each variable data under the target indicator classification, filtering out effective variable data is the target variable number
According to.
5. the appraisal procedure of business standing as claimed in claim 4, which is characterized in that become in the determining acquisition index
After the step of measuring the target indicator classification of data, further includes:
Legal person's credit data of the enterprise to be assessed is obtained, and using legal person's credit data as the target indicator classification
One type.
6. the appraisal procedure of business standing as described in claim 1, which is characterized in that each finger for obtaining enterprise to be assessed
Variable data is marked, and the step of matching each target variable data corresponding default calculating weight includes:
The cooperation data that the enterprise to be assessed provides are detected, each target variable data are extracted from the cooperation data；
Each target variable data are subjected to stepping processing, are based on industry practice experience, are each target variable data
With corresponding default calculating weight.
7. the appraisal procedure of business standing as described in claim 1, which is characterized in that described to be based on each target variable number
According to each default calculating weight, the step of calculating the Default Probability of the enterprise to be assessed, includes:
Logical model recurrence is carried out to each default calculating weight of each target variable data, it is described to be assessed to calculate
The Default Probability of enterprise.
8. the appraisal procedure of business standing as described in claim 1, which is characterized in that it is described according to the Default Probability to working as
The step of business standing of the preceding enterprise to be assessed is scored include:
Grading calibration is carried out to the Default Probability based on conversion process；
According to the Default Probability after grading calibration, score the business standing of the enterprise to be assessed.
9. a kind of assessment system of business standing, which is characterized in that the assessment system of the business standing includes:
Data acquisition module for obtaining each target variable data of enterprise to be assessed, and matches each target variable data
Corresponding default calculating weight；
Probability evaluation entity calculates described to be evaluated for being based on each target variable data and each default calculating weight
Estimate the Default Probability of enterprise；
Evaluation module, for being scored according to business standing of the Default Probability to presently described enterprise to be assessed.
10. the assessment system of business standing as claimed in claim 9, which is characterized in that before the data acquisition module,
Further include:
Data determining module, for extracting the enterprise to be assessed from enterprise's sample to be assessed, and determination is described to be assessed
Each target variable data of enterprise.
11. the assessment system of business standing as claimed in claim 10, which is characterized in that the data determining module includes:
Index extra cell obtains legal person's credit data of the enterprise to be assessed, and using legal person's credit data as institute
State the one type of target indicator classification.
12. a kind of assessment equipment of business standing, which is characterized in that the assessment equipment of the business standing includes: memory, place
Reason device and the appraisal procedure for being stored in the business standing that can be run on the memory and on the processor, enterprise's letter
The assessment such as business standing described in any item of the claim 1 to 8 is realized when appraisal procedure is executed by the processor
The step of method.
13. a kind of storage medium, which is characterized in that be applied to computer, be stored with commenting for business standing on the storage medium
Estimate program, such as enterprise described in any item of the claim 1 to 8 is realized when the appraisal procedure of the business standing is executed by processor
The step of appraisal procedure of industry credit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910548413.6A CN110246031A (en) | 2019-06-21 | 2019-06-21 | Appraisal procedure, system, equipment and the storage medium of business standing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910548413.6A CN110246031A (en) | 2019-06-21 | 2019-06-21 | Appraisal procedure, system, equipment and the storage medium of business standing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110246031A true CN110246031A (en) | 2019-09-17 |
Family
ID=67888987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910548413.6A Pending CN110246031A (en) | 2019-06-21 | 2019-06-21 | Appraisal procedure, system, equipment and the storage medium of business standing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110246031A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796539A (en) * | 2019-10-31 | 2020-02-14 | 中国工商银行股份有限公司 | Credit investigation evaluation method and device |
| CN111222774A (en) * | 2019-12-30 | 2020-06-02 | 广州博士信息技术研究院有限公司 | Enterprise data analysis method and device and server |
| CN111626844A (en) * | 2020-05-11 | 2020-09-04 | 北京联行信用管理服务有限公司 | Enterprise credit assessment method and device based on big data analysis |
| CN111652504A (en) * | 2020-06-01 | 2020-09-11 | 泰康保险集团股份有限公司 | Data processing apparatus |
| CN111899086A (en) * | 2020-06-15 | 2020-11-06 | 东方微银科技(北京)有限公司 | Client credit classification method |
| CN112016806A (en) * | 2020-07-28 | 2020-12-01 | 上海发电设备成套设计研究院有限责任公司 | Method, system, medium and device for overhauling state of power station equipment |
| CN112037006A (en) * | 2020-07-21 | 2020-12-04 | 苏宁金融科技(南京)有限公司 | Credit risk identification method and device for small and micro enterprises |
| CN112308294A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
| CN112529477A (en) * | 2020-12-29 | 2021-03-19 | 平安普惠企业管理有限公司 | Credit evaluation variable screening method, device, computer equipment and storage medium |
| CN112686498A (en) * | 2020-12-11 | 2021-04-20 | 天津中科智能识别产业技术研究院有限公司 | Enterprise credit rating method based on deep convolutional network |
| CN113313570A (en) * | 2021-05-25 | 2021-08-27 | 深圳前海微众银行股份有限公司 | Method, system, computer program product and storage medium for determining default rate |
| CN113536395A (en) * | 2021-07-16 | 2021-10-22 | 四川新网银行股份有限公司 | Bank trusted data verification method |
| CN113743734A (en) * | 2021-08-10 | 2021-12-03 | 南京星云数字技术有限公司 | Credit score processing method and device and electronic equipment |
| CN113888278A (en) * | 2021-10-14 | 2022-01-04 | 黑龙江省范式智能技术有限公司 | Data analysis method and device based on enterprise credit line analysis model |
| CN115511506A (en) * | 2022-09-30 | 2022-12-23 | 中国电子科技集团公司第十五研究所 | Enterprise credit rating method, device, terminal equipment and storage medium |
| TWI805880B (en) * | 2019-12-17 | 2023-06-21 | 臺灣銀行股份有限公司 | Internal system of bank for creidt risk evluation and methohd thereof |
| CN117575784A (en) * | 2024-01-17 | 2024-02-20 | 深度(山东)数字科技集团有限公司 | Enterprise credit rating method and system for bill big data based on big data management |
-
2019
- 2019-06-21 CN CN201910548413.6A patent/CN110246031A/en active Pending
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796539A (en) * | 2019-10-31 | 2020-02-14 | 中国工商银行股份有限公司 | Credit investigation evaluation method and device |
| TWI805880B (en) * | 2019-12-17 | 2023-06-21 | 臺灣銀行股份有限公司 | Internal system of bank for creidt risk evluation and methohd thereof |
| CN111222774A (en) * | 2019-12-30 | 2020-06-02 | 广州博士信息技术研究院有限公司 | Enterprise data analysis method and device and server |
| CN111626844A (en) * | 2020-05-11 | 2020-09-04 | 北京联行信用管理服务有限公司 | Enterprise credit assessment method and device based on big data analysis |
| CN111652504A (en) * | 2020-06-01 | 2020-09-11 | 泰康保险集团股份有限公司 | Data processing apparatus |
| CN111899086A (en) * | 2020-06-15 | 2020-11-06 | 东方微银科技(北京)有限公司 | Client credit classification method |
| CN112037006A (en) * | 2020-07-21 | 2020-12-04 | 苏宁金融科技(南京)有限公司 | Credit risk identification method and device for small and micro enterprises |
| CN112016806A (en) * | 2020-07-28 | 2020-12-01 | 上海发电设备成套设计研究院有限责任公司 | Method, system, medium and device for overhauling state of power station equipment |
| CN112308294A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
| CN112686498A (en) * | 2020-12-11 | 2021-04-20 | 天津中科智能识别产业技术研究院有限公司 | Enterprise credit rating method based on deep convolutional network |
| CN112529477A (en) * | 2020-12-29 | 2021-03-19 | 平安普惠企业管理有限公司 | Credit evaluation variable screening method, device, computer equipment and storage medium |
| CN113313570A (en) * | 2021-05-25 | 2021-08-27 | 深圳前海微众银行股份有限公司 | Method, system, computer program product and storage medium for determining default rate |
| CN113313570B (en) * | 2021-05-25 | 2024-05-10 | 深圳前海微众银行股份有限公司 | Method, system, computer program product and storage medium for determining the rate of breach |
| CN113536395A (en) * | 2021-07-16 | 2021-10-22 | 四川新网银行股份有限公司 | Bank trusted data verification method |
| CN113743734A (en) * | 2021-08-10 | 2021-12-03 | 南京星云数字技术有限公司 | Credit score processing method and device and electronic equipment |
| CN113888278A (en) * | 2021-10-14 | 2022-01-04 | 黑龙江省范式智能技术有限公司 | Data analysis method and device based on enterprise credit line analysis model |
| CN115511506A (en) * | 2022-09-30 | 2022-12-23 | 中国电子科技集团公司第十五研究所 | Enterprise credit rating method, device, terminal equipment and storage medium |
| CN117575784A (en) * | 2024-01-17 | 2024-02-20 | 深度(山东)数字科技集团有限公司 | Enterprise credit rating method and system for bill big data based on big data management |
| CN117575784B (en) * | 2024-01-17 | 2024-04-12 | 深度(山东)数字科技集团有限公司 | Enterprise credit rating method and system for bill big data based on big data management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110246031A (en) | Appraisal procedure, system, equipment and the storage medium of business standing | |
| Hang et al. | Measurement matters—A meta-study of the determinants of corporate capital structure | |
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| CN107993143A (en) | A kind of Credit Risk Assessment method and system | |
| CN109657894A (en) | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium | |
| CN109492945A (en) | Business risk identifies monitoring method, device, equipment and storage medium | |
| CN109409677A (en) | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium | |
| WO2004061714A1 (en) | Technique evaluating device, technique evaluating program, and technique evaluating method | |
| CN107633030A (en) | Credit estimation method and device based on data model | |
| WO2010037030A1 (en) | Evaluating loan access using online business transaction data | |
| US11556807B2 (en) | Automated account opening decisioning using machine learning | |
| CN110472884A (en) | ESG index monitoring method, device, terminal device and storage medium | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN107437227A (en) | Stock investment analysis apparatus and method | |
| CN107633455A (en) | Credit estimation method and device based on data model | |
| CN111709826A (en) | Target information determination method and device | |
| CN111090833A (en) | Data processing method, system and related equipment | |
| AU2019101158A4 (en) | A method of analyzing customer churn of credit cards by using logistics regression | |
| CN112037006A (en) | Credit risk identification method and device for small and micro enterprises | |
| TW201327453A (en) | Small enterprise financing risk assessment method | |
| CN115631029A (en) | Method and device for evaluating risk of scientific loan | |
| Azadeh et al. | Optimization of human resources and industrial banks with ambiguous inputs using intelligent fuzzy mathematical programming approach | |
| Tavakoli Baghdadabad et al. | The efficiency evaluation of mutual fund managers based on DARA, CARA, IARA | |
| KR102334923B1 (en) | Loan expansion hypothesis testing system using artificial intelligence and method using the same | |
| JP5592861B2 (en) | Claim evaluation support system, claim evaluation support method and claim evaluation support program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |