CN110135700A - Credit Risk Assessment method and device based on expandtabs data - Google Patents
Credit Risk Assessment method and device based on expandtabs data Download PDFInfo
- Publication number
- CN110135700A CN110135700A CN201910330366.8A CN201910330366A CN110135700A CN 110135700 A CN110135700 A CN 110135700A CN 201910330366 A CN201910330366 A CN 201910330366A CN 110135700 A CN110135700 A CN 110135700A
- Authority
- CN
- China
- Prior art keywords
- credit
- assessment
- data
- expandtabs
- scoring
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 6
- 241000406668 Loxodonta cyclotis Species 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 7
- 235000013399 edible fruits Nutrition 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides a kind of Credit Risk Assessment method and devices based on expandtabs data, wherein the Credit Risk Assessment method based on expandtabs data includes: the assessment data obtained to credit assessment object；The assessment data are analyzed based on expandtabs credit scoring model, to obtain the credit scoring to credit assessment object, wherein, the expandtabs credit scoring model is borrowed or lent money constructed by the training of data based on the user to basic credit data and third party's loan platform；According to the credit scoring to credit assessment object, determine to the assessment result to credit assessment object.According to the technical solution of the present invention, Credit Risk Assessment accurately can be comprehensively carried out, the accuracy of assessment result is improved.
Description
Technical field
The present invention relates to internet credit financing technical field, in particular to a kind of based on expandtabs data
Credit Risk Assessment method and a kind of Credit Risk Assessment device based on expandtabs data.
Background technique
Credit refers in the form of the value movement for condition of repaying and pay interest, and generally includes the credits such as cash in banks, loan
Activity, credit are that socialist state mobilizes important form with the distribution of fund with paid mode, are the strong thick sticks developed the economy
Bar.The generation of loan is necessarily accompanied with risk, before the payback period expires, the great unfavorable change of the commercial situation of borrower's finance
Change is likely to influence its contractual capacity, so that the risks such as bad accounts, bad credit occur, therefore, in order to which the generation for reducing such risk is general
Rate needs to carry out risk assessment to borrower.
Conventional banking facilities are for Credit Risk Assessment mainly according to two ways: one is artificial assessments, rely primarily on
It is manually empirically assessed, on the one hand increases cost of labor, the probability on the other hand generating erroneous judgement is very high, assessment result
Inaccuracy；Another kind be according to personal credit points-scoring system, in the prior art personal credit points-scoring system when being assessed according to
The some basic datas of Lai Yu, assessment dimension is single, causes assessment result not accurate enough.In this regard, there is presently no effective solutions
Scheme.
Summary of the invention
The present invention is based at least one above-mentioned technical problem, proposes a kind of new letter based on expandtabs data
Risk assessment scheme is borrowed, Credit Risk Assessment accurately can be comprehensively carried out, improve the accuracy of assessment result.
In view of this, the invention proposes a kind of new Credit Risk Assessment methods based on expandtabs data, comprising:
Obtain the assessment data to credit assessment object；The assessment data are analyzed based on expandtabs credit scoring model,
To obtain the credit scoring to credit assessment object, wherein the expandtabs credit scoring model is based on to basis
The user of credit data and third party's loan platform borrows or lends money constructed by the training of data；According to described to credit assessment object
Credit scoring is determined to the assessment result to credit assessment object.
In the technical scheme, when treating credit assessment object progress Credit Risk Assessment, expandtabs letter is introduced
With Rating Model, the building of the model is not merely based on basic credit data, and the user for also adding third party's loan platform borrows
Data are borrowed, assessment dimension is increased, it is ensured that it is comprehensive when to assessment data analysis, improve the accurate of assessment result
Property.
In the above-mentioned technical solutions, it is preferable that it is described obtain to credit assessment object assessment data the step of before,
Further include: extract the basic credit data in database；The user for obtaining third party's loan platform borrows or lends money data；To what is got
User borrows or lends money data and carries out analysis calibration, to obtain expandtabs data；Based on to the basic credit data and the expansion
The machine learning simulated training that label data carries out, constructs the expandtabs credit scoring model.
In the technical scheme, it usually needs to choose sample when carrying out machine learning simulated training, certain ratio can be chosen
" the hospitable family " and " bad client " of example can be related to the statistics of characteristic item during the selection of " hospitable family " and " bad client ",
And often will appear the unknown in the statistics of characteristic item, when there is the unknown to occur, corresponding sample is likely to be rejected,
It is not available, user can be introduced at this time and borrow or lend money data to carry out classification calibration, labelled with label expansion to the unknown, thus
The loss for avoiding some samples increases the diversity of data, it is ensured that the reasonability of constructed expandtabs credit scoring model.
In any of the above-described technical solution, it is preferable that in the determination to the assessment knot to credit assessment object
Before the step of fruit, further includes: each letter being pre-stored in multiple credit scoring sections and the multiple credit scoring section
With the incidence relation between scoring section and loan product；The credit scoring according to credit assessment object, determines
It the step of to the assessment result to credit assessment object, specifically includes: determining that the credit to credit assessment object is commented
Target credit scoring section locating for point；According to the incidence relation, search corresponding with target credit scoring section
Loan product, and as the assessment result to credit assessment object.
In the technical scheme, the division in credit scoring section can be adjusted according to actual design demand, be stored in advance
Incidence relation between each credit scoring section and loan product, to provide a favorable security for subsequent assessment, the base in assessment
In pre-stored incidence relation, assessment result can be quickly determined, it is ensured that the accuracy of evaluating result.
In any of the above-described technical solution, it is preferable that in the determination to the assessment knot to credit assessment object
Before the step of fruit, further includes: whether the judgement credit scoring to credit assessment object is more than or equal to threshold value；If it is described to
The credit scoring of credit assessment object is more than or equal to threshold value, then executes the credit according to credit assessment object and comment
Point, the step of determination to the assessment result to credit assessment object；If the credit scoring to credit assessment object is small
In threshold value, then the assessment data to credit assessment object and credit scoring are uploaded to monitor supervision platform.
In the technical scheme, compare the credit scoring to credit assessment object and the size of threshold value, test and assess when to credit
When the credit scoring of object is more than or equal to threshold value, illustrate that the credit to credit assessment object is preferable, it can further progress assessment knot
The determination of fruit, when credit assessment object credit scoring be less than threshold value when, illustrate to credit assessment object credit relatively
The related data of the object is sent to monitor supervision platform at this time by difference, by related personnel further come determine the need for its into
Row make loans, effectively avoid it is bad to credit assessment object occupy resource, also can avoid the loss of some potential resources.
In any of the above-described technical solution, it is preferable that the assessment data include the base to credit assessment object
Plinth credit data and user borrow or lend money data.
In any of the above-described technical solution, it is preferable that the step of borrowing or lending money data to the user of credit assessment object is obtained,
It specifically includes: obtaining the debt-credit data of each debt-credit software to the held terminal record of credit assessment object；It is respectively borrowed to described
The debt-credit data for borrowing software carry out confluence analysis, borrow or lend money data to obtain the user.
In any of the above-described technical solution, it is preferable that in the expandtabs credit scoring model that is based on to the survey
Before the step of commenting data to be analyzed, further includes: obtain the identity characteristic information to credit assessment object；Based on described
To the identity characteristic information of credit assessment object, whether judgement is described is located in blacklist to credit assessment object；When determining
It states when credit assessment object is not in blacklist, executes the expandtabs credit scoring model that is based on to the assessment data
The step of being analyzed；It is described when credit assessment object is in blacklist when determining, to described to credit assessment object output
Alarm prompt.
In the technical scheme, there are various " Lao Lai " information in blacklist, these information can from network or special letter
Demonstrate,prove channel to obtain, and be recorded in blacklist, in blacklist information can real-time update, test and assess treating credit assessment object
When, the identity characteristic information to credit assessment object is obtained, and determine based on the identity characteristic information to credit assessment object
The object, if directly carrying out alarm prompt if, and does not go on assessment whether in blacklist, thus avoidable to bad
To the invalid assessment of credit assessment object, the operating load of whole system is effectively reduced.
In any of the above-described technical solution, it is preferable that it is described to credit assessment object identity characteristic information include with
Under any or a variety of combination: identification card number, finger print information, facial image information, iris information.
In any of the above-described technical solution, it is preferable that it is described to described to credit assessment object outputting alarm prompt
Step specifically includes: presetting prompt information to credit assessment Object Push to described with written form；And/or with speech form
Prompt information is preset to credit assessment Object Push to described.
According to the second aspect of the invention, a kind of Credit Risk Assessment device based on expandtabs data is proposed, is wrapped
It includes: first acquisition unit, for obtaining the assessment data to credit assessment object；First analytical unit, for based on expansion mark
Label credit scoring model analyzes the assessment data, to obtain the credit scoring to credit assessment object, wherein
The expandtabs credit scoring model is to borrow or lend money data based on the user to basic credit data and third party's loan platform
Constructed by training；Processing unit, for determining and being surveyed to described to credit according to the credit scoring to credit assessment object
Comment the assessment result of object.
In the technical scheme, when treating credit assessment object progress Credit Risk Assessment, expandtabs letter is introduced
With Rating Model, the building of the model is not merely based on basic credit data, and the user for also adding third party's loan platform borrows
Data are borrowed, assessment dimension is increased, it is ensured that it is comprehensive when to assessment data analysis, improve the accurate of assessment result
Property.
In the above-mentioned technical solutions, it is preferable that further include: second acquisition unit, for extracting the basis letter in database
Use data；Third acquiring unit, the user for obtaining third party's loan platform borrow or lend money data；Second analytical unit, for pair
The user got borrows or lends money data and carries out analysis calibration, to obtain expandtabs data；Creating unit, for based on to the base
The machine learning simulated training that plinth credit data and the expandtabs data carry out, constructs the expandtabs credit scoring mould
Type.
In the technical scheme, it usually needs to choose sample when carrying out machine learning simulated training, certain ratio can be chosen
" the hospitable family " and " bad client " of example can be related to the statistics of characteristic item during the selection of " hospitable family " and " bad client ",
And often will appear the unknown in the statistics of characteristic item, when there is the unknown to occur, corresponding sample is likely to be rejected,
It is not available, user can be introduced at this time and borrow or lend money data to carry out classification calibration, labelled with label expansion to the unknown, thus
The loss for avoiding some samples increases the diversity of data, it is ensured that the reasonability of constructed expandtabs credit scoring model.
In any of the above-described technical solution, it is preferable that further include: storage unit, for being pre-stored multiple credit scorings
The incidence relation between each credit scoring section and loan product in section and the multiple credit scoring section；Institute
Processing unit is stated, is specifically used for: determining target credit scoring section locating for the credit scoring to credit assessment object；Root
According to the incidence relation, loan product corresponding with target credit scoring section is searched, and as described wait believe
Borrow the assessment result of assessment object.
In the technical scheme, the division in credit scoring section can be adjusted according to actual design demand, be stored in advance
Incidence relation between each credit scoring section and loan product, to provide a favorable security for subsequent assessment, the base in assessment
In pre-stored incidence relation, assessment result can be quickly determined, it is ensured that the accuracy of evaluating result.
In any of the above-described technical solution, it is preferable that further include: the first judging unit, it is described to credit for judging
Whether the credit scoring of assessment object is more than or equal to threshold value；The processing unit is specifically used for true in first judging unit
It is fixed described when the credit scoring of credit assessment object is more than or equal to threshold value, it is commented according to the credit to credit assessment object
Point, it determines to the assessment result to credit assessment object；Transmission unit, described in being determined in first judging unit
Credit scoring to credit assessment object is less than threshold value, and the assessment data to credit assessment object and credit scoring are uploaded
To monitor supervision platform.
In the technical scheme, compare the credit scoring to credit assessment object and the size of threshold value, test and assess when to credit
When the credit scoring of object is more than or equal to threshold value, illustrate that the credit to credit assessment object is preferable, it can further progress assessment knot
The determination of fruit, when credit assessment object credit scoring be less than threshold value when, illustrate to credit assessment object credit relatively
The related data of the object is sent to monitor supervision platform at this time by difference, by related personnel further come determine the need for its into
Row make loans, effectively avoid it is bad to credit assessment object occupy resource, also can avoid the loss of some potential resources.
In any of the above-described technical solution, it is preferable that the assessment data include the base to credit assessment object
Plinth credit data and user borrow or lend money data.
In any of the above-described technical solution, it is preferable that the first acquisition unit is specifically used for: obtaining described wait believe
Borrow the debt-credit data of each debt-credit software of the held terminal record of assessment object；The debt-credit data of each debt-credit software are carried out whole
Analysis is closed, borrows or lends money data to obtain the user.
In any of the above-described technical solution, it is preferable that further include: the 4th acquiring unit, it is described to credit for obtaining
The identity characteristic information of assessment object；Second judgment unit, for based on it is described to credit assessment object identity characteristic information,
Whether judgement is described is located in blacklist to credit assessment object；First analytical unit, specifically for sentencing described second
Disconnected unit is determining described when credit assessment object is not in blacklist, based on expandtabs credit scoring model to the assessment
Data are analyzed；Alarm Unit, for the second judgment unit determine it is described to credit assessment object in blacklist
When, to described to credit assessment object outputting alarm prompt.
In the technical scheme, there are various " Lao Lai " information in blacklist, these information can from network or special letter
Demonstrate,prove channel to obtain, and be recorded in blacklist, in blacklist information can real-time update, test and assess treating credit assessment object
When, the identity characteristic information to credit assessment object is obtained, and determine based on the identity characteristic information to credit assessment object
The object, if directly carrying out alarm prompt if, and does not go on assessment whether in blacklist, thus avoidable to bad
To the invalid assessment of credit assessment object, the operating load of whole system is effectively reduced.
In any of the above-described technical solution, it is preferable that it is described to credit assessment object identity characteristic information include with
Under any or a variety of combination: identification card number, finger print information, facial image information, iris information.
In any of the above-described technical solution, it is preferable that the Alarm Unit is specifically used for: with written form to described
Prompt information is preset to credit assessment Object Push, and/or is mentioned with speech form to described preset to credit assessment Object Push
Show information.
According to the third aspect of the invention we, a kind of computer equipment is proposed, comprising: processor；And with the processing
The memory of device communication connection；Wherein, the memory is stored with readable instruction, and the readable instruction is by the processor
The method as described in any one of above-mentioned technical proposal is realized when execution.
According to the fourth aspect of the invention, a kind of computer readable storage medium is proposed, computer is stored thereon with
Program, the computer program realize the method as described in any one of above-mentioned technical proposal when executed.
By above technical scheme, Credit Risk Assessment accurately can be comprehensively carried out, the accuracy of assessment result is improved.
Detailed description of the invention
Fig. 1 shows the signal of the Credit Risk Assessment method based on expandtabs data of embodiment according to the present invention
Flow chart；
Fig. 2 shows the signals of the Credit Risk Assessment device based on expandtabs data of embodiment according to the present invention
Block diagram；
Fig. 3 shows the schematic block diagram of the computer equipment of embodiment according to the present invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Below in conjunction with Fig. 1 to Fig. 3, technical scheme is described further:
Fig. 1 shows the signal of the Credit Risk Assessment method based on expandtabs data of embodiment according to the present invention
Flow chart.
As shown in Figure 1, the Credit Risk Assessment method based on expandtabs data of embodiment according to the present invention, specifically
The following steps are included:
Step S102 obtains the assessment data to credit assessment object.
Wherein, assessment data include borrowing or lending money data to the basic credit data of credit assessment object and user.Basic credit
Data include kinsfolk, occupation, age, industry (including house, valuable collection etc.), public accumulation fund data, bank's flowing water
Data etc., it includes each loan platform data that user, which borrows or lends money data, such as " so-and-so by means of " data, so-and-so informal voucher.
Wherein, it is obtaining when the user of credit assessment object borrows or lends money data, can specifically obtain to credit assessment object institute
The debt-credit data of each debt-credit software of terminal record are held, and confluence analysis is carried out to the debt-credit data of each debt-credit software, with
Data are borrowed or lent money to user.In addition, including my held terminal to credit assessment the held terminal of object, it might even be possible to including with its phase
The debt-credit data of each debt-credit software of the terminal of pass, such as user-association, people holds terminal.
Step S104 analyzes assessment data based on expandtabs credit scoring model, to obtain testing and assessing to credit
The credit scoring of object.
Further, expandtabs credit scoring model can be constructed in advance, specifically, extract the basic credit in database
Data, the user for obtaining third party's loan platform borrow or lend money data, borrow or lend money data to the user got and carry out analysis calibration, with
To expandtabs data, based on the machine learning simulated training to basic credit data and the progress of expandtabs data, building is expanded
Fill label credit scoring model.It usually needs to choose sample when carrying out machine learning simulated training, can choose a certain proportion of
" hospitable family " and " bad client " can be related to the statistics of characteristic item during the selection of " hospitable family " and " bad client ", and past
Toward will appear the unknown in the statistics of characteristic item, when there is the unknown to occur, corresponding sample is likely to be rejected, can not
It uses, user can be introduced at this time and borrow or lend money data to carry out classification calibration, labelled with label expansion to the unknown, such as user
So-and-so borrow make loans without overdue or so-and-so informal voucher without overdue etc., can mark as hospitable family ", to avoid the stream of some samples
It loses, increases the diversity of data, it is ensured that the reasonability of constructed expandtabs credit scoring model.
Step S106 determines the assessment result for treating credit assessment object according to the credit scoring to credit assessment object.
Specifically, before determining the assessment result for treating credit assessment object, multiple credit scoring sections can be pre-stored,
And each credit scoring section in multiple credit scoring sections and the incidence relation between loan product, then determine wait believe
Target credit scoring section locating for the credit scoring of assessment object is borrowed, according to incidence relation, is searched and target credit scoring area
Between corresponding loan product, and as to credit assessment object assessment result.Wherein, loan product includes but unlimited
In small amount, wholesale, have mortgage, without mortgage, credit card by stages, insurance, finance product etc..
Further, it is contemplated that only it is creditable it is good to credit assessment object can just have continue assessment meaning,
The height of credit scoring can be used as the standard judged to credit assessment object credit quality, so can first judge to credit assessment pair
Whether the credit scoring of elephant is more than or equal to threshold value, if the credit scoring to credit assessment object is more than or equal to threshold value, illustrates wait believe
The credit for borrowing assessment object is preferable, can determine according to the credit scoring to credit assessment object and treat commenting for credit assessment object
The step of estimating result illustrates that the credit to credit assessment object is opposite if the credit scoring to credit assessment object is less than threshold value
It is poor, it will be uploaded to monitor supervision platform to the assessment data of credit assessment object and credit scoring at this time, it is further by related personnel
Determine the need for making loans to it, effectively avoid it is bad occupy resource to credit assessment object, also can avoid some latent
In the loss of traveller.
Further, in order to reduce the operating load of whole system, it is contemplated that preparatory filtration fraction is bad to test and assess to credit
Object specifically can obtain the identity characteristic information to credit assessment object, based on the identity characteristic letter to credit assessment object
Breath judges whether be located in blacklist to credit assessment object, when determining when credit assessment object is not in blacklist, then base
Assessment data are analyzed in expandtabs credit scoring model, when determining when credit assessment object is in blacklist, to
To credit assessment object outputting alarm prompt.
Wherein, the identity characteristic information to credit assessment object includes following any or a variety of combination: identification card number,
Finger print information, facial image information, iris information.Have various " Lao Lai " information in blacklist, these information can from network or
Special letter card channel obtains, and is recorded in blacklist, in blacklist information can real-time update, treating credit assessment object
When being tested and assessed, the identity characteristic information to credit assessment object is obtained, and based on the identity characteristic letter to credit assessment object
It ceases to determine that the object, specifically can be with written form to wait believe if directly carrying out alarm prompt if whether in blacklist
It borrows assessment Object Push and presets prompt information, and/or prompt information is preset to credit assessment Object Push with speech form, and
Assessment is not gone on, to can avoid that the fortune of whole system is effectively reduced to the bad invalid assessment to credit assessment object
Row load.
Fig. 2 shows the schematic block diagrams of the Credit Risk Assessment device of embodiment according to the present invention；
As shown in Fig. 2, the Credit Risk Assessment device 200 based on expandtabs data of embodiment according to the present invention,
It include: first acquisition unit 202, the first analytical unit 204 and processing unit 206.
Wherein, first acquisition unit 202 be used for obtains to credit test and assess object assessment data (specifically, data are commented in side
Including the basic credit data and user's debt-credit data to credit assessment object)；Analytical unit 204 is used to believe based on expandtabs
Assessment data are analyzed with Rating Model, to obtain the credit scoring to credit assessment object, wherein expandtabs credit
Rating Model is borrowed or lent money constructed by the training of data based on the user to basic credit data and third party's loan platform；Processing
Unit 206 is used to determine the assessment result for treating credit assessment object according to the credit scoring to credit assessment object.It is treating
When credit assessment object carries out Credit Risk Assessment, expandtabs credit scoring model is introduced, the building of the model is not only
Based on basic credit data, the user for also adding third party's loan platform borrows or lends money data, increases assessment dimension, it is ensured that
It is comprehensive when to assessment data analysis, improve the accuracy of assessment result.
Further, based on the Credit Risk Assessment device 200 of expandtabs data further include: second acquisition unit 208
For extracting the basic credit data in database；The user that third acquiring unit 210 is used to obtain third party's loan platform borrows
Borrow data；Second analytical unit 212, which is used to borrow or lend money data to the user got, carries out analysis calibration, to obtain expandtabs number
According to；Creating unit 214 is used for based on the machine learning simulated training to basic credit data and the progress of expandtabs data, building
Expandtabs credit scoring model.It usually needs to choose sample when carrying out machine learning simulated training, certain proportion can be chosen
" hospitable family " and " bad client ", " hospitable family " and " bad client " selection during can be related to the statistics of characteristic item, and
Often it will appear the unknown in the statistics of characteristic item, when there is the unknown to occur, corresponding sample is likely to be rejected, nothing
Method uses, and can introduce user at this time and borrow or lend money data to carry out classification calibration, be labelled with label expansion to the unknown, to keep away
The loss for exempting from some samples increases the diversity of data, it is ensured that the reasonability of constructed expandtabs credit scoring model.
Further, based on the Credit Risk Assessment device 200 of expandtabs data further include: storage unit 216 is used for
Between each credit scoring section being pre-stored in multiple credit scoring sections and multiple credit scoring sections and loan product
Incidence relation；Processing unit 206 is specifically used for: determining target credit scoring locating for the credit scoring to credit assessment object
Section；According to incidence relation, loan product corresponding with target credit scoring section is searched, and is tested and assessed as to credit
The assessment result of object.
The division in credit scoring section can be adjusted according to actual design demand, and each credit scoring section is stored in advance
Incidence relation between loan product is closed in assessment based on pre-stored association with providing a favorable security for subsequent assessment
System, can quickly determine assessment result, it is ensured that the accuracy of evaluating result.
Further, based on the Credit Risk Assessment device 200 of expandtabs data further include: the first judging unit 218,
For judging whether the credit scoring to credit assessment object is more than or equal to threshold value；Processing unit 206 is specifically used for sentencing first
Disconnected unit 218 determines when the credit scoring of credit assessment object is more than or equal to threshold value, according to the credit to credit assessment object
Scoring determines the assessment result for treating credit assessment object；Transmission unit 220, for determining in the first judging unit 218 wait believe
The credit scoring for borrowing assessment object is less than threshold value, flat by monitoring is uploaded to the assessment data of credit assessment object and credit scoring
Platform.
By comparing the size of credit scoring and threshold value to credit assessment object, when the credit to credit assessment object is commented
Point be more than or equal to threshold value when, illustrate to credit assessment object credit it is preferable, can further progress evaluating result determination, when to
When the credit scoring of credit assessment object is less than threshold value, illustrate that the credit to credit assessment object is relatively poor, it is at this time that this is right
The related data of elephant is sent to monitor supervision platform, further determines the need for making loans to it by related personnel, effectively keep away
Exempt from it is bad to credit assessment object occupy resource, also can avoid the loss of some potential resources.
Further, first acquisition unit 202 is specifically used for: obtaining respectively borrowing to credit assessment the held terminal record of object
Borrow the debt-credit data of software；Confluence analysis is carried out to the debt-credit data of each debt-credit software, borrows or lends money data to obtain user.
Further, based on the Credit Risk Assessment device 200 of expandtabs data further include: the 4th acquiring unit 222,
For obtaining the identity characteristic information to credit assessment object；Second judgment unit 224, for based on to credit assessment object
Identity characteristic information judges whether be located in blacklist to credit assessment object；First analytical unit 204 is specifically used for second
Judging unit 224 determines when credit assessment object is not in blacklist, based on expandtabs credit scoring model to assessment number
According to being analyzed；Alarm Unit 226 is used in the determination of second judgment unit 224 when credit assessment object is in blacklist, to
To credit assessment object outputting alarm prompt.
Wherein, the identity characteristic information to credit assessment object includes following any or a variety of combination: identification card number,
Finger print information, facial image information, iris information.Have various " Lao Lai " information in blacklist, these information can from network or
Special letter card channel obtains, and is recorded in blacklist, in blacklist information can real-time update, treating credit assessment object
When being tested and assessed, the identity characteristic information to credit assessment object is obtained, and based on the identity characteristic letter to credit assessment object
Breath determines that the object whether in blacklist, if the direct progress alarm prompt if, and does not go on assessment, so as to keep away
Exempt from that the operating load of whole system is effectively reduced to the bad invalid assessment to credit assessment object.
Further, Alarm Unit 226 is specifically used for: with written form to the default prompt letter of credit assessment Object Push
Breath, and/or prompt information is preset to credit assessment Object Push with speech form.
As shown in figure 3, the computer equipment 300 of embodiment according to the present invention, comprising: memory 302, processor 304
And communication bus 306.Wherein, memory 302 is configured to storage executable instruction；Processor 304 is configured to execute the finger of storage
It enables to realize such as the step of above-mentioned any embodiment the method, thus has whole technical effects of the data analysing method,
Details are not described herein.
Specifically, above-mentioned memory 302 may include the mass storage for data or instruction.For example rather than
Limitation, memory 302 may include hard disk drive (Hard Disk Drive, HDD), floppy disk drive, flash memory, CD, magneto-optic
Disk, tape or universal serial bus (Universal Serial Bus, USB) driver or two or more the above
Combination.In a suitable case, memory 302 may include the medium of removable or non-removable (or fixed).Suitable
In the case of, memory 302 can be inside or outside synthesized gateway disaster tolerance equipment.In a particular embodiment, 302 right and wrong of memory
Volatile solid-state.In a particular embodiment, memory 302 includes read-only memory (ROM).In a suitable case,
The ROM can be the ROM of masked edit program, programming ROM (PROM), erasable PROM (EPROM), electric erasable PROM
(EEPROM), electrically-alterable ROM (EAROM) or the combination of flash memory or two or more the above.Processor 304 can be with
Including central processing unit (CPU) or specific integrated circuit (Application Specific Integrated Circuit,
ASIC), or may be configured to implement the embodiment of the present invention one or more integrated circuits.Communication bus 306 is for real
Connection communication between existing signal processor 304 and memory 302.Communication bus 306 can be industry standard architecture
(Industry Standard Architecture, ISA) bus, external equipment interconnection (Peripheral Component
Interconnect, PCI) bus or extension standards architecture (Extended Industry Standard
Architecture, EISA) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..
The embodiment of fourth aspect present invention provides a kind of computer readable storage medium, is stored thereon with computer journey
Sequence is realized when computer program is executed by processor such as the step of any of the above-described technical solution the method, thus has the number
According to whole technical effects of analysis method, details are not described herein.Computer readable storage medium may include that can store or pass
Any medium of defeated information.The example of computer readable storage medium includes electronic circuit, semiconductor memory devices, ROM, sudden strain of a muscle
It deposits, erasable ROM (EROM), floppy disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link etc..Code segment can be with
It is downloaded via the computer network of internet, Intranet etc..
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, and technical solution of the present invention proposes a kind of new
Credit Risk Assessment scheme based on expandtabs data accurately can comprehensively carry out Credit Risk Assessment, improve assessment knot
The accuracy of fruit.
It is merely a preferred embodiment of the present invention, is not intended to restrict the invention, for the technology of this field described in upper
For personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of Credit Risk Assessment method based on expandtabs data characterized by comprising
Obtain the assessment data to credit assessment object；
The assessment data are analyzed based on expandtabs credit scoring model, it is described to credit assessment object to obtain
Credit scoring, wherein the expandtabs credit scoring model is based on to basic credit data and third party's loan platform
User borrows or lends money constructed by the training of data；
According to the credit scoring to credit assessment object, determine to the assessment result to credit assessment object.
2. the Credit Risk Assessment method according to claim 1 based on expandtabs data, which is characterized in that described
Before the step of obtaining the assessment data to credit assessment object, further includes:
Extract the basic credit data in database；
The user for obtaining third party's loan platform borrows or lends money data；
Data are borrowed or lent money to the user got and carry out analysis calibration, to obtain expandtabs data；
Based on the machine learning simulated training carried out to the basic credit data and the expandtabs data, the expansion is constructed
Fill label credit scoring model.
3. the Credit Risk Assessment method according to claim 1 based on expandtabs data, which is characterized in that described
Before the step of determining to the assessment result to credit assessment object, further includes:
The each credit scoring section being pre-stored in multiple credit scoring sections and the multiple credit scoring section and loan
Incidence relation between product；
The credit scoring according to credit assessment object is determined to the assessment result to credit assessment object
Step specifically includes:
Determine target credit scoring section locating for the credit scoring to credit assessment object；
According to the incidence relation, loan product corresponding with target credit scoring section is searched, and as institute
State the assessment result to credit assessment object.
4. the Credit Risk Assessment method according to any one of claim 1 to 3 based on expandtabs data, feature
It is, before the step of determination is to the assessment result to credit assessment object, further includes:
Whether the judgement credit scoring to credit assessment object is more than or equal to threshold value；
If it is described to credit assessment object credit scoring be more than or equal to threshold value, execute it is described according to credit assessment pair
The credit scoring of elephant, the step of determination to the assessment result to credit assessment object；
If it is described to credit assessment object credit scoring be less than threshold value, by it is described to credit assessment object assessment data and
Credit scoring is uploaded to monitor supervision platform.
5. a kind of Credit Risk Assessment device based on expandtabs data characterized by comprising
First acquisition unit, for obtaining the assessment data to credit assessment object；
First analytical unit, for being analyzed based on expandtabs credit scoring model the assessment data, to obtain
State the credit scoring to credit assessment object, wherein the expandtabs credit scoring model is based on to basic credit data
It is borrowed or lent money constructed by the training of data with the user of third party's loan platform；
Processing unit, for what is according to the credit scoring to credit assessment object, determined to described to credit assessment object
Assessment result.
6. the Credit Risk Assessment device according to claim 5 based on expandtabs data, which is characterized in that also wrap
It includes:
Second acquisition unit, for extracting the basic credit data in database；
Third acquiring unit, the user for obtaining third party's loan platform borrow or lend money data；
Second analytical unit carries out analysis calibration for borrowing or lending money data to the user got, to obtain expandtabs data；
Creating unit, for simulating instruction based on the machine learning carried out to the basic credit data and the expandtabs data
Practice, constructs the expandtabs credit scoring model.
7. the Credit Risk Assessment device according to claim 5 based on expandtabs data, which is characterized in that also wrap
It includes:
Storage unit, each credit for being pre-stored in multiple credit scoring sections and the multiple credit scoring section
The incidence relation to score between section and loan product；
The processing unit, is specifically used for:
Determine target credit scoring section locating for the credit scoring to credit assessment object；
According to the incidence relation, loan product corresponding with target credit scoring section is searched, and as institute
State the assessment result to credit assessment object.
8. the Credit Risk Assessment device according to any one of claims 5 to 7 based on expandtabs data, feature
It is, further includes:
First judging unit, for judging whether the credit scoring to credit assessment object is more than or equal to threshold value；
The processing unit, specifically for determining that the credit scoring to credit assessment object is big in first judging unit
When being equal to threshold value, according to the credit scoring to credit assessment object, determine to the assessment to credit assessment object
As a result；
Transmission unit, for determining that the credit scoring to credit assessment object is less than threshold value in first judging unit,
The assessment data to credit assessment object and credit scoring are uploaded to monitor supervision platform.
9. a kind of computer equipment characterized by comprising
Processor；And
The memory being connect with the processor communication；
Wherein, the memory is stored with readable instruction, and the readable instruction is realized when being executed by the processor as weighed
Benefit require any one of 1 to 4 described in method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer journey
Sequence realizes method according to any one of claims 1 to 4 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330366.8A CN110135700A (en) | 2019-04-23 | 2019-04-23 | Credit Risk Assessment method and device based on expandtabs data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330366.8A CN110135700A (en) | 2019-04-23 | 2019-04-23 | Credit Risk Assessment method and device based on expandtabs data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135700A true CN110135700A (en) | 2019-08-16 |
Family
ID=67570794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910330366.8A Pending CN110135700A (en) | 2019-04-23 | 2019-04-23 | Credit Risk Assessment method and device based on expandtabs data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135700A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111489254A (en) * | 2020-04-14 | 2020-08-04 | 上海数喆数据科技有限公司 | Credit risk assessment intelligent engine system based on historical credit big data |
| CN113724058A (en) * | 2020-05-21 | 2021-11-30 | 中国移动通信有限公司研究院 | Credit and loan limit evaluation method, device, equipment and storage medium |
| CN113724058B (en) * | 2020-05-21 | 2024-11-08 | 中国移动通信有限公司研究院 | Credit and loan amount evaluation method, device, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| 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 |
| CN106780012A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of internet credit methods and system |
| CN107392755A (en) * | 2017-07-07 | 2017-11-24 | 南京甄视智能科技有限公司 | Credit risk merges appraisal procedure and system |
| CN107748952A (en) * | 2017-10-09 | 2018-03-02 | 深圳广联赛讯有限公司 | Prestige checking method, device and storage medium based on consumer's risk control |
| CN107909461A (en) * | 2017-09-27 | 2018-04-13 | 上海维信荟智金融科技有限公司 | Credit data unify method of calibration and system |
| CN108961040A (en) * | 2018-06-29 | 2018-12-07 | 重庆富民银行股份有限公司 | Loan limit assessment system and method for credit extension loan |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
| CN109410032A (en) * | 2018-09-26 | 2019-03-01 | 深圳壹账通智能科技有限公司 | A kind of information processing method, server and computer storage medium |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
-
2019
- 2019-04-23 CN CN201910330366.8A patent/CN110135700A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN106780012A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of internet credit methods and system |
| 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 |
| CN107392755A (en) * | 2017-07-07 | 2017-11-24 | 南京甄视智能科技有限公司 | Credit risk merges appraisal procedure and system |
| CN107909461A (en) * | 2017-09-27 | 2018-04-13 | 上海维信荟智金融科技有限公司 | Credit data unify method of calibration and system |
| CN107748952A (en) * | 2017-10-09 | 2018-03-02 | 深圳广联赛讯有限公司 | Prestige checking method, device and storage medium based on consumer's risk control |
| CN108961040A (en) * | 2018-06-29 | 2018-12-07 | 重庆富民银行股份有限公司 | Loan limit assessment system and method for credit extension loan |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
| CN109410032A (en) * | 2018-09-26 | 2019-03-01 | 深圳壹账通智能科技有限公司 | A kind of information processing method, server and computer storage medium |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111489254A (en) * | 2020-04-14 | 2020-08-04 | 上海数喆数据科技有限公司 | Credit risk assessment intelligent engine system based on historical credit big data |
| CN113724058A (en) * | 2020-05-21 | 2021-11-30 | 中国移动通信有限公司研究院 | Credit and loan limit evaluation method, device, equipment and storage medium |
| CN113724058B (en) * | 2020-05-21 | 2024-11-08 | 中国移动通信有限公司研究院 | Credit and loan amount evaluation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Silva et al. | Network structure analysis of the Brazilian interbank market | |
| WO2017143919A1 (en) | Method and apparatus for establishing data identification model | |
| Campello et al. | The firm-level credit multiplier | |
| CN111507822A (en) | Enterprise risk assessment method based on feature engineering | |
| Hilbers et al. | New tools for assessing financial system soundness | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| CN110008336B (en) | Public opinion early warning method and system based on deep learning | |
| CN112037038A (en) | Bank credit risk prediction method and device | |
| CN110827143A (en) | Method, device and equipment for training credit scoring model | |
| CN113554228A (en) | Repayment rate prediction model training method and repayment rate prediction method | |
| CN115082225A (en) | Enterprise financing risk assessment method and device | |
| CN110135700A (en) | Credit Risk Assessment method and device based on expandtabs data | |
| CN113919432A (en) | Classification model construction method, data classification method and device | |
| CN110110970A (en) | Virtual resource risk rating method, system, computer equipment and storage medium | |
| CN109308660B (en) | Credit assessment scoring model evaluation method, apparatus, device and storage medium | |
| CN117688455A (en) | Meta-task small sample classification method based on data quality and reinforcement learning | |
| Gautam et al. | An empirical investigation about relationship between international trade and tourist arrival: Evidence from India | |
| CN112508684A (en) | Joint convolutional neural network-based collection risk rating method and system | |
| CN116993484A (en) | Credit model generation method and device, electronic equipment and storage medium | |
| De Freitas et al. | Currency substitution, portfolio diversification, and money demand | |
| Ben Rejeb | Volatility Spillover between Islamic and conventional stock markets: evidence from Quantile Regression analysis | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| Li | An economic measure of diversification benefits | |
| Saxa 1 | Learning-by-exporting or managerial quality? Evidence from the Czech Republic | |
| CN118379132B (en) | Processing method and system for automobile financial service platform |
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 |