CN108053310A - Credit scoring method, apparatus, computer equipment and storage medium - Google Patents
Credit scoring method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108053310A CN108053310A CN201711190094.3A CN201711190094A CN108053310A CN 108053310 A CN108053310 A CN 108053310A CN 201711190094 A CN201711190094 A CN 201711190094A CN 108053310 A CN108053310 A CN 108053310A
- Authority
- CN
- China
- Prior art keywords
- client
- credit
- gauge type
- snap gauge
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to a kind of credit scoring method, apparatus, computer equipment and storage medium, including:Obtain the essential information of client, essential information is inputted into credit scoring snap gauge type, it is scored according to credit scoring snap gauge type the credit of client, obtain the corresponding credit score of client, filter out the second client that credit score is higher than the second preset value less than the first client of the first preset value and credit score, it exports the approval results of the first client to examine for refusal, the approval results of the second client of output pass through for examination & approval.It scores the credit of client due to the use of credit scoring snap gauge type, and client is screened according to credit score, so as to fast and accurately provide indicating risk.
Description
Technical field
The present invention relates to field of computer technology, are set more particularly to a kind of credit scoring method, apparatus, computer
Standby and storage medium.
Background technology
Internet finance greatly develops the lending and borrowing business development for also bringing internet platform, with traditional bank credit
It compares, the amount higher of internet credit is examined faster.In traditional credit examination & approval mode, credit approving person passes through face
What is said or talked about, telephone verification check applicant's material etc. to carry out the evaluation based on subjective credit risk grade to client, and based on pair
The overall impression of client gives client one corresponding accrediting amount according to related working experience.
Traditional examination & approval mechanism, which remains unchanged, rests on the level of bank credit, and subjective thought is based on to the overall control of client,
It is more that working experience is relied on to carry out risk test and appraisal to client.This examination & approval mode not only lacks scientific basis, and timeliness
Property it is poor, required human cost is high, also, when a large amount of clients pour in, it is impossible to really fast and accurately provide indicating risk.
The content of the invention
Based on this, it is necessary to really cannot fast and accurately provide indicating risk for above-mentioned traditional examination & approval mode
Problem provides a kind of credit scoring method, apparatus, computer equipment and storage medium.
A kind of credit scoring method, the described method includes:
The essential information of client is obtained, the essential information is inputted into credit scoring snap gauge type;
It is scored according to the credit scoring snap gauge type the credit of the client, obtains the corresponding credit of the client
Fraction;
It is default higher than second less than the first client of the first preset value and the credit score to filter out the credit score
Second client of value;
The approval results of first client are exported to examine for refusal;
The approval results of second client are exported for examination & approval to pass through.
In one embodiment, the essential information is inputted credit scoring snap gauge by the essential information for obtaining client
Type, including:
The identity of client is obtained, the identity is corresponding with the essential information of the client;
The credit index of client is extracted from the essential information;
The credit index is inputted into credit scoring snap gauge type.
In one embodiment, it is described to be scored according to the credit scoring snap gauge type the credit of the client, it obtains
To credit score, including:
The credit probability of client is calculated according to the credit index;
The credit probability is converted into credit score.
In one embodiment, training obtains the credit scoring snap gauge type in the following manner:
The sample data in the essential information of client is obtained, the sample data is the credit index of the client;
Quantification treatment is carried out to the credit index, obtains credit achievement data collection;
The credit achievement data collection is calculated by logistic regression algorithm, until the creditable achievement data collection meter of institute
It finishes, obtains trained credit scoring snap gauge type.
In one embodiment, it is described to filter out first client of the credit score less than the first preset value and the letter
It is higher than with fraction after the second client of the second preset value, including:
After filtering out first client and second client, according to the credit score of remaining client to remaining described visitor
Family carries out manual examination and verification.
In one embodiment, it is described that the credit of the client is carried out scoring it according to the credit scoring snap gauge type
Before, including:
The essential information of the client is screened, obtains the credit information of client;
The credit information is converted into character, by the character input credit scoring snap gauge type.
A kind of credit scoring device, described device include:
The essential information due to obtaining the essential information of client, is inputted credit scoring snap gauge type by MIM message input module;
Credit scoring module for being scored according to the credit scoring snap gauge type the credit of the client, obtains
The corresponding credit score of the client;
Fraction screening module, for filtering out first client of the credit score less than the first preset value and the credit
Fraction is higher than the second client of the second preset value;
First result output module is examined for exporting the approval results of first client for refusal;
Second result output module passes through for exporting the approval results of second client for examination & approval.
In one embodiment, described information input module includes:
Identifier acquisition module, for obtaining the identity of client, the identity is corresponding with the basic of the client
Information;
Index extraction module, for extracting the credit index of client from the essential information;
Index input module, for the credit index to be inputted credit scoring snap gauge type.
A kind of computer equipment including memory, processor and is stored in the memory and can be in the processing
The step of computer program run on device, the processor realizes method as described above when performing the computer program.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
The step of calculation machine program realizes method as described above when being executed by processor.
Above-mentioned credit scoring method, apparatus, computer equipment and storage medium, by the basic letter for obtaining client
Essential information is inputted credit scoring snap gauge type, is scored according to credit scoring snap gauge type the credit of client, obtain visitor by breath
It is default higher than second less than the first client of the first preset value and credit score to filter out credit score for the corresponding credit score in family
Second client of value, the approval results of the first client of output are examined for refusal, and the approval results of the second client of output are logical for examination & approval
It crosses.It scores the credit of client due to the use of credit scoring snap gauge type, and client is screened according to credit score,
So as to fast and accurately provide indicating risk.
Description of the drawings
Fig. 1 is the applied environment figure of credit scoring method in one embodiment;
Fig. 2 is the cut-away view of terminal in Fig. 1 in one embodiment;
Fig. 3 is the flow chart of credit scoring method in one embodiment;
Fig. 4 is the method flow diagram that client's essential information is obtained in one embodiment;
Fig. 5 is the method flow diagram of training credit scoring snap gauge type in one embodiment;
Fig. 6 is the structure diagram of credit scoring device in one embodiment;
Fig. 7 is the structure diagram of MIM message input module in one embodiment.
Specific embodiment
To enable objects, features and advantages of the present invention more obvious understandable, below in conjunction with the accompanying drawings to the tool of the present invention
Body embodiment is described in detail.Many details are elaborated in the following description in order to fully understand the present invention.
But the invention can be embodied in many other ways as described herein, those skilled in the art can without prejudice to
Similar improvement is done in the case of intension of the present invention, therefore the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 is the applied environment figure of credit scoring method in one embodiment.As shown in Figure 1, the application environment bag
Terminal 110 and server 120 are included, wherein, it is communicated between terminal 110 and server 120 by network.
Terminal 110 can be laptop, desktop computer, individual digital computer, portable laptop computer etc., but simultaneously
It is not limited to this.Terminal 110 obtains the essential information of client by server 120, and essential information is inputted credit scoring card
Model scores for the credit to client.Terminal 110 scores to the credit of client by credit scoring snap gauge type
Afterwards, the corresponding credit score of client can be obtained.Terminal 110 can filter out first visitor of the credit score less than the first preset value
Family and credit score are higher than the second client of the second preset value.After filtering out the first client and the second client, terminal 110 can be with
The approval results of the first client and the second client are exported, wherein, the approval results of the first client are refusal examination & approval, the second client's
Approval results are that examination & approval pass through.
In one embodiment, a kind of computer equipment is provided, which can be terminal 110, in Fig. 1
The internal structure of terminal 110 is as shown in Fig. 2, the terminal 110 is included through the processor of system bus connection, storage medium, interior
It deposits, display and network interface.Wherein, the storage medium of terminal 110 is stored with operating system, database, further includes for real
The computer program of existing credit scoring method and apparatus.For the processor for providing calculating and control ability, support is entire
The operation of terminal 110.Display in terminal 110 filters out the first client and the second client for showing information, for example, working as
When, display can show that the approval results of the first client are refusal examination & approval, and the approval results of the second client are that examination & approval pass through.It is interior
The operation for saving as the computer program that credit scoring method and apparatus are realized in storage medium provides environment, and network interface is used
In carrying out network communication with server 120, for example, network interface can get the essential information of client from server 120,
Essential information is inputted into credit scoring snap gauge type again.Structure shown in Figure 2, only relevant with application scheme part knot
The block diagram of structure, does not form the restriction for the terminal being applied thereon to application scheme, and specific terminal can be included than figure
Shown in more or fewer components either combine some components or arranged with different component.
In one embodiment, a kind of credit scoring method is provided, to be applied to the end in above application environment
End is come for example, as shown in figure 3, including the following steps:
Step S302 obtains the essential information of client, and essential information is inputted credit scoring snap gauge type.
Wherein, the essential information of client can include name, age, gender, educational background, wage, loaning bill situation, the letter of client
With data information etc..The collection of customers' credit data information is in credit consuming, is filled in by inquiry or by client
Data information understands the credit information of client.
Credit scoring snap gauge type is a kind of credit history data according to client, using certain credit scoring model by visitor
Family is divided into different grades, and scores the credit of client, and the credit risk of client is known that according to this fraction.
The essential information for the client being collected into is stored in server, when the credit to client is needed to score, terminal
The essential information of client can be got from server, then the essential information of the client got is input to credit scoring snap gauge
Type.
Step S304 scores to the credit of client according to credit scoring snap gauge type, obtains the corresponding credit score of client
Number.
When credit card Rating Model scores to the credit of client, height and the risk level of fraction are inversely proportional, credit
It scores as the fractionation of the overdue rate prediction index of client, will directly react the overdue horizontal forecast value in client's future.Credit scoring
Snap gauge type can export the fraction of client after scoring the credit of client, fraction is higher, represent that customer risk is lower, on the contrary,
Fraction is lower, represents that customer risk is higher.
It is default higher than second less than the first client of the first preset value and credit score to filter out credit score by step S306
Second client of value.
Wherein, the first preset value and the second preset value are all the numerical value of one pre-set, for example, the first preset value
Can be 20, the second preset value can be 70, this preset value be not it is fixed, can according to client's essential information of input with
And it needs to change the different credit scorings of client.
The essential information of each client, which is input to after credit scoring snap gauge type, can all export a credit score, obtain letter
After fraction, client can be screened according to different credit scores, wherein it is possible to filter out credit score less than first
First client of preset value and credit score are higher than the second client of the second preset value, for example, when the first preset value is 20, second
When preset value is 70, the second client of first client of the credit score less than 20 and credit score higher than 70 can be filtered out.
Step S308, the approval results of the first client of output are examined for refusal.
Since the credit score of the first client is less than the first preset value, the credit risk of the first client be it is high,
It for the high client of such credit risk, can directly refuse to examine, that is, export approval results and examined for refusal.
Step S310, the approval results of the second client of output pass through for examination & approval.
The credit score of second client is higher than the second preset value, and the second client belongs to extremely low risk client, for such pole
The client of low-risk can be taken all by way of, the approval results that output examination & approval pass through.
By obtaining the essential information of client, essential information is inputted into credit scoring snap gauge type, according to credit scoring snap gauge
Type scores to the credit of client, obtains the corresponding credit score of client, filters out credit score less than the first preset value
First client and credit score are higher than the second client of the second preset value, and the approval results of the first client of output are examined for refusal,
The approval results of the second client are exported for examination & approval to pass through.It scores due to the use of credit scoring snap gauge type the credit of client,
And client is screened according to credit score, so as to fast and accurately provide indicating risk.
In one embodiment, a kind of credit scoring method provided further includes the mistake for obtaining client's essential information
Journey, as shown in figure 4, specifically including:
Step S402, obtains the identity of client, and identity is corresponding with the essential information of client.
Wherein, obtaining the identity of client can be acquired by identity card, for example, scanning identity card.Each visitor
The identity at family is all unique, when obtaining the identity of client, since identity is corresponding with the essential information of client,
Terminal can get the essential information of client by obtaining the identity of client.For example, by scanning identity card
Mode can get name, age, gender, loan information and credit information information of client etc..
Step S404 extracts the credit index of client from essential information.
The information for inputting the client of credit scoring snap gauge type is the useful information to score customers' credit, and terminal can
The credit index of client is extracted from the essential information of client by algorithm.For example, the essential information of client can include visitor
Name, age, gender, loan information and the credit information information at family, terminal can be by algorithms from numerous essential informations
In extract the information influential on customers' credit such as loan information, credit information information, these information are exactly credit index.
Credit index is inputted credit scoring snap gauge type by step S406.
After the credit index of client is extracted, these credit indexs can be inputted credit scoring snap gauge type to phase by terminal
The client answered carries out credit scoring.
Step S408 calculates the credit probability of client according to credit index.
After the credit index input credit scoring snap gauge type of client, credit scoring card can apply logistic regression algorithm,
Credit probability is calculated to the credit of client according to the credit index of input.
Credit probability is converted into credit score by step S410.
After credit scoring snap gauge type calculates credit probability, credit probability can be converted into credit score.For example, credit
Probability is 0.7, and credit probability can be converted into 70 credit score by credit scoring snap gauge type, and credit score is general compared with credit
Rate can more intuitively react the credit risk of client.After credit score is obtained by credit scoring snap gauge type, terminal can
To go out the specific credit score of client by showing interface.
By obtaining the identity of client, identity is corresponding with the essential information of client, is extracted from essential information
Credit index is inputted credit scoring snap gauge type, the credit probability of client is calculated according to credit index by the credit index of client, will
Credit probability is converted into credit score.Since credit scoring snap gauge type according to algorithm calculates credit probability, then by credit probability
Credit score is converted into, this process all carries out in credit scoring snap gauge type, and obtained credit score is more objective, more
Add neutral, more efficient.
As shown in figure 5, in one embodiment, a kind of credit scoring method provided further includes trained credit scoring
The process of snap gauge type, specifically includes:
Step S502, obtains the sample data in the essential information of client, and sample data is the credit index of client.
Can all there be sample data when training pattern, the basic information content of client is relatively more, in training credit scoring
When snap gauge type, it is impossible to all input into all essential informations.Therefore, some information are had to input as sample data
Into credit scoring snap gauge type, sample data here can be the credit index of client.The namely loan information of client, letter
With data information etc. on the influential information of the credit of client.
Step S504 carries out quantification treatment to credit index, obtains credit achievement data collection.
Include loan information, credit information information of client etc. in credit index.Terminal can carry out these information
Quantification treatment, and obtain corresponding data set.For example, loaning bill number in the loan information of client and date of refunding are quantified
Processing can obtain the data set of charge to a customer's account number and the overdue refund of client.
Step S506 calculates credit achievement data collection by logistic regression algorithm, until the creditable index number of institute
It calculates and finishes according to collection, obtain trained credit scoring snap gauge type.
Logistic regression algorithm is a kind of common algorithm in model, and logistic regression algorithm is a kind of Method of The Classification Analysis,
It is usually applied to this disaggregated model of credit scoring snap gauge type.
The credit achievement data collection of client is calculated using logistic regression algorithm, the credit achievement data collection of client can
Multiple to have, logistic regression algorithm can one by one calculate the credit achievement data collection of client, by all data sets all
After calculating, it is possible to obtain trained credit scoring snap gauge type.
In one embodiment, a kind of credit scoring method provided further includes the process of manual examination and verification, specific to wrap
It includes:
After filtering out the first client and the second client, remaining client is manually examined according to the credit score of remaining client
Core.
The approval results of first client are refusal examination & approval, and the approval results of the second client are that examination & approval pass through, this two parts visitor
The approval results at family are specific, need not enter back into the manual examination and verification stage.The first client and the second client are removed, remaining visitor
Family approval results are indefinite, it is necessary to carry out manual examination and verification to this portions of client.
All clients have passed through credit scoring snap gauge type and calculate credit probability, therefore all there are one right by all clients
The credit score answered.For this portions of client, client can manually be examined according to this portions of client corresponding credit score
Core obtains the approval results that refusal examination & approval or examination & approval pass through.
Due to all creditable fraction of all clients, to the first client filtered out and the second client using directly by or
The examination & approval mode directly refused need not carry out manual examination and verification to this portions of client again, greatly reduce the work of manual examination and verification
Amount.And for need carry out manual examination and verification client, since client has corresponding credit score, according to credit score to client into
Row manual examination and verification add the statistics foundation of science, make the more objective neutrality of approval results.
In one embodiment, a kind of credit scoring method provided is further included at the credit information to client
The process of reason, specifically includes:
The essential information of client is screened, obtains the credit information of client;Credit information is converted into character, by word
Symbol input credit scoring snap gauge type.
The essential information of client is huge information, is limited be subject to credit scoring snap gauge type calculating processing ability, can not
All client's essential informations can all be inputted credit scoring snap gauge type.Terminal can screen the essential information of client,
Obtain the credit information of client.It is inputted by the credit information of client before credit scoring snap gauge type, it is necessary to which credit information is converted
For character, then input characters into credit scoring snap gauge type.
It is screened by the essential information to client, obtains the credit information of client, credit information is converted into character,
Input characters into credit scoring snap gauge type.The information first inputted to needs is screened, then the information filtered out is converted to word
Symbol, processing procedure of the credit scoring snap gauge type to information can be reduced by inputting characters into credit scoring snap gauge type, can be more rapidly
Obtain the credit score of client.
In one embodiment, a kind of credit scoring method is provided, realizes that this method is as follows:
Firstly, it is necessary to training credit scoring snap gauge type.Terminal can obtain the sample data in the essential information of client, sample
Notebook data is the credit index of client.Can all there be sample data when training pattern, the basic information content of client is relatively more,
When training credit scoring snap gauge type, it is impossible to which all essential informations are all inputted into.Therefore, some information work is had
It is input to for sample data in credit scoring snap gauge type, sample data here can be the credit index of client.It is namely objective
Loan information, the credit information information at family etc. are on the influential information of the credit of client.Quantification treatment is carried out to credit index again,
Obtain credit achievement data collection.Include loan information, credit information information of client etc. in credit index.Terminal can be to this
A little information carry out quantification treatment, and obtain corresponding data set.For example, by loaning bill number and repayment date in the loan information of client
Phase carries out quantification treatment, can obtain the data set of charge to a customer's account number and the overdue refund of client.Pass through logistic regression algorithm pair
Credit achievement data collection is calculated, and is finished until the creditable achievement data collection of institute calculates, is obtained trained credit scoring card
Model.Logistic regression algorithm is a kind of common algorithm in model, and logistic regression algorithm is a kind of Method of The Classification Analysis, usually
Applied to this disaggregated model of credit scoring snap gauge type.The credit achievement data collection of client is counted using logistic regression algorithm
It calculates, the credit achievement data collection of client can have multiple, and logistic regression algorithm can be one by one to the credit achievement data collection of client
It is calculated, after all data sets are all calculated, it is possible to obtain trained credit scoring snap gauge type.
Secondly, it is necessary to obtain the essential information of client, essential information is inputted into credit scoring snap gauge type.It can specifically wrap
It includes:The identity of client is obtained, identity is corresponding with the essential information of client.Wherein, the identity for obtaining client can
To be acquired by identity card, for example, scanning identity card.The identity of each client is unique, obtains client's
During identity, since identity is corresponding with the essential information of client, terminal can be by obtaining the identity of client
And then get the essential information of client.For example, can be got by way of scanning identity card the name of client, the age,
Gender, loan information and credit information information etc..The credit index of client is extracted from essential information.Input credit scoring card
The information of the client of model is the useful information to score customers' credit, and terminal can be by algorithm from the basic of client
The credit index of client is extracted in information.For example, the essential information of client can the name including client, age, gender, debt-credit
Information and credit information information, terminal can extract loan information, credit money by algorithm from numerous essential informations
Expect that information influential on customers' credit, these information such as information are exactly credit index, then credit index is inputted into credit scoring
Snap gauge type.
Then, the essential information of client is screened, obtains the credit information of client;Credit information is converted into word
Symbol, inputs characters into credit scoring snap gauge type.The essential information of client is huge information, and credit scoring snap gauge type is subject to calculate
The limitation of processing capacity, it is impossible to which all client's essential informations are all inputted into credit scoring snap gauge type.Terminal can be to client
Essential information screened, obtain the credit information of client.Before the credit information of client is inputted credit scoring snap gauge type,
It needs credit information being converted to character, then inputs characters into credit scoring snap gauge type.
Then, scored according to credit scoring snap gauge type the credit of client, obtain the corresponding credit score of client.Letter
When being scored with card Rating Model the credit of client, height and the risk level of fraction are inversely proportional, and credit scoring is client
The fractionation of overdue rate prediction index will directly react the overdue horizontal forecast value in client's future.Credit scoring snap gauge type is to visitor
The credit at family can export the fraction of client after being scored, fraction is higher, represent that customer risk is lower, on the contrary, fraction is lower, table
Show that customer risk is higher.Terminal can calculate the credit probability of client according to credit index, then credit probability is converted into credit
Fraction.
Then, terminal can filter out credit score less than the first client of the first preset value and credit score higher than second
Second client of preset value.Wherein, the first preset value and the second preset value are all the numerical value of one pre-set, for example,
First preset value can be 20, and the second preset value can be 70, this preset value be not it is fixed, can be according to the client of input
It essential information and needs to change the different credit scorings of client.The essential information of each client is input to credit scoring
A credit score can be all exported after snap gauge type, after obtaining credit score, client can be carried out according to different credit scores
Screening, wherein it is possible to which filter out credit score is higher than the second preset value less than the first client of the first preset value and credit score
The second client, for example, when the first preset value is 20, and the second preset value is 70, credit score can be filtered out less than 20
First client and credit score are higher than 70 the second client.
Then, after filtering out the first client and the second client, remaining client is carried out according to the credit score of remaining client
Manual examination and verification.The approval results of first client are refusal examination & approval, and the approval results of the second client are that examination & approval pass through, this two parts visitor
The approval results at family are specific, need not enter back into the manual examination and verification stage.The first client and the second client are removed, remaining visitor
Family approval results are indefinite, it is necessary to carry out manual examination and verification to this portions of client.All clients have passed through credit scoring snap gauge
Type calculates credit probability, therefore all there are one corresponding credit scores by all clients.It, can be according to this for this portions of client
The corresponding credit score of portions of client carries out manual examination and verification to client, obtains the approval results that refusal examination & approval or examination & approval pass through.
Finally, the approval results of the first client are exported to examine for refusal.Since the credit score of the first client is less than first
Preset value, therefore, the credit risk of the first client is high, for the high client of such credit risk, can directly be refused
Examination & approval absolutely export approval results and are examined for refusal.The approval results of the second client are exported for examination & approval to pass through.The letter of second client
With fraction higher than the second preset value, the second client belongs to extremely low risk client, can be taken for the client of so extremely low risk
All by way of, the approval results passed through are examined in output.
As shown in fig. 6, in one embodiment, a kind of credit scoring device is provided, including:
Essential information for obtaining the essential information of client, is inputted credit scoring snap gauge type by MIM message input module 610.
Credit scoring module 620 for scoring according to credit scoring snap gauge type the credit of client, obtains client couple
The credit score answered.
Fraction screening module 630, for filtering out first client of the credit score less than the first preset value and credit score
Higher than the second client of the second preset value.
First result output module 640 is examined for exporting the approval results of the first client for refusal.
Second result output module 650 passes through for exporting the approval results of the second client for examination & approval.
In one embodiment, as shown in fig. 7, MIM message input module 610 includes:
Identifier acquisition module 612, for obtaining the identity of client, identity is corresponding with the essential information of client.
Index extraction module 614, for extracting the credit index of client from essential information.
Index input module 616, for credit index to be inputted credit scoring snap gauge type.
In one embodiment, credit scoring module 620 can be also used for according to credit index calculate client credit it is general
Credit probability is converted into credit score by rate.
In one embodiment, a kind of credit scoring device provided further includes credit scoring card model training mould
Block.Credit scoring card model training module can be used for obtaining the sample data in the essential information of client, and sample data is visitor
The credit index at family.It can be also used for carrying out quantification treatment to credit index, obtain credit achievement data collection.It can be also used for leading to
It crosses logistic regression algorithm to calculate credit achievement data collection, finishes, instructed until the creditable achievement data collection of institute calculates
The credit scoring snap gauge type perfected.
In one embodiment, a kind of credit scoring device provided can also include manual examination and verification module.Manually
Auditing module is for after filtering out the first client and the second client, according to the credit score of remaining client to remaining client into pedestrian
Work is audited.
In one embodiment, a kind of credit scoring device provided can also include information sifting module, information
Screening module obtains the credit information of client for being screened to the essential information of client.Credit scoring device may be used also
To include info conversion module, info conversion module is used to credit information being converted to character, inputs characters into credit scoring card
Model.
In one embodiment, a kind of computer readable storage medium is also provided, the computer-readable recording medium storage
There is computer program, which realizes following steps when being executed by processor:The essential information of client is obtained, it will be basic
Information inputs credit scoring snap gauge type;It is scored according to credit scoring snap gauge type the credit of client, it is corresponding to obtain client
Credit score;It filters out credit score and is higher than the second of the second preset value less than the first client of the first preset value and credit score
Client;The approval results of the first client are exported to examine for refusal;The approval results of the second client are exported for examination & approval to pass through.
In one embodiment, computer program is executed by processor the essential information for obtaining client, and essential information is defeated
Enter credit scoring snap gauge type, including:The identity of client is obtained, identity is corresponding with the essential information of client;From basic
The credit index of client is extracted in information;Credit index is inputted into credit scoring snap gauge type;Calculate client's according to credit index
Credit probability;Credit probability is converted into credit score.
In one embodiment, computer program is executed by processor trained credit scoring snap gauge type, including:Obtain client
Essential information in sample data, sample data be client credit index;Quantification treatment is carried out to credit index, obtains letter
With achievement data collection;Credit achievement data collection is calculated by logistic regression algorithm, until the creditable achievement data collection of institute
Calculating finishes, and obtains trained credit scoring snap gauge type.
In one embodiment, computer program is executed by processor manual examination and verification, including:Filter out the first client and
After two clients, manual examination and verification are carried out to remaining client according to the credit score of remaining client.
In one embodiment, following steps are also realized when computer program is executed by processor:To the basic letter of client
Breath is screened, and obtains the credit information of client;Credit information is converted into character, inputs characters into credit scoring snap gauge type.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, it is non-volatile computer-readable that the program can be stored in one
It takes in storage medium, in the embodiment of the present invention, which can be stored in the non-volatile memory medium of computer system, and
It is performed by least one processor in the computer system, to realize the flow for including the embodiment such as above-mentioned each method.Its
In, the storage medium can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) or random storage
Memory body (Random Access Memory, RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and description is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that come for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
- A kind of 1. credit scoring method, which is characterized in that the described method includes:The essential information of client is obtained, the essential information is inputted into credit scoring snap gauge type;It is scored according to the credit scoring snap gauge type the credit of the client, obtains the corresponding credit score of the client Number;The credit score is filtered out less than the first client of the first preset value and the credit score higher than the second preset value Second client;The approval results of first client are exported to examine for refusal;The approval results of second client are exported for examination & approval to pass through.
- 2. according to the method described in claim 1, it is characterized in that, it is described obtain client essential information, by the basic letter Breath input credit scoring snap gauge type, including:The identity of client is obtained, the identity is corresponding with the essential information of the client;The credit index of client is extracted from the essential information;The credit index is inputted into credit scoring snap gauge type.
- 3. according to the method described in claim 2, it is characterized in that, it is described according to the credit scoring snap gauge type to the client Credit score, obtain credit score, including:The credit probability of client is calculated according to the credit index;The credit probability is converted into credit score.
- 4. according to the method described in claim 1, it is characterized in that, the credit scoring snap gauge type is trained in the following manner It arrives:The sample data in the essential information of client is obtained, the sample data is the credit index of the client;Quantification treatment is carried out to the credit index, obtains credit achievement data collection;The credit achievement data collection is calculated by logistic regression algorithm, until the creditable achievement data collection of institute has been calculated Finish, obtain trained credit scoring snap gauge type.
- 5. according to the method described in claim 1, it is characterized in that, described filter out the credit score less than the first preset value The first client and the credit score higher than the second preset value the second client after, including:After filtering out first client and second client, according to the credit score of remaining client to remaining described client into Row manual examination and verification.
- 6. according to the method described in claim 1, it is characterized in that, it is described according to the credit scoring snap gauge type to the client Credit scored before, including:The essential information of the client is screened, obtains the credit information of client;The credit information is converted into character, by the character input credit scoring snap gauge type.
- 7. a kind of credit scoring device, which is characterized in that described device includes:The essential information for obtaining the essential information of client, is inputted credit scoring snap gauge type by MIM message input module;Credit scoring module for being scored according to the credit scoring snap gauge type the credit of the client, obtains described The corresponding credit score of client;Fraction screening module, for filtering out first client of the credit score less than the first preset value and the credit score Higher than the second client of the second preset value;First result output module is examined for exporting the approval results of first client for refusal;Second result output module passes through for exporting the approval results of second client for examination & approval.
- 8. device according to claim 7, which is characterized in that described information input module includes:Identifier acquisition module, for obtaining the identity of client, the identity is corresponding with the essential information of the client;Index extraction module, for extracting the credit index of client from the essential information;Index input module, for the credit index to be inputted credit scoring snap gauge type.
- 9. a kind of computer equipment, including memory, processor and it is stored in the memory and can be in the processor The computer program of upper operation, which is characterized in that the processor realized when performing the computer program as claim 1 to The step of any one of 6 the method.
- 10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists In when the computer program is executed by processor the step of realization such as any one of claim 1 to 6 the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711190094.3A CN108053310A (en) | 2017-11-24 | 2017-11-24 | Credit scoring method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711190094.3A CN108053310A (en) | 2017-11-24 | 2017-11-24 | Credit scoring method, apparatus, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108053310A true CN108053310A (en) | 2018-05-18 |
Family
ID=62120720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711190094.3A Pending CN108053310A (en) | 2017-11-24 | 2017-11-24 | Credit scoring method, apparatus, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053310A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921707A (en) * | 2018-06-05 | 2018-11-30 | 中国平安人寿保险股份有限公司 | Core protects processing method, device, computer equipment and storage medium |
CN108960111A (en) * | 2018-06-26 | 2018-12-07 | 深圳市买买提信息科技有限公司 | Face identification method, system and terminal device |
CN109034502A (en) * | 2018-09-04 | 2018-12-18 | 中国光大银行股份有限公司信用卡中心 | Anti- Fraud Prediction method and device |
CN109146132A (en) * | 2018-07-11 | 2019-01-04 | 深圳市买买提信息科技有限公司 | Field miss rate method for early warning, server, storage medium and computer program |
CN109461016A (en) * | 2018-09-10 | 2019-03-12 | 平安科技(深圳)有限公司 | Data methods of marking, device, computer equipment and storage medium |
CN109726242A (en) * | 2018-12-29 | 2019-05-07 | 陕西西部资信股份有限公司 | Data processing method and system |
CN109816509A (en) * | 2018-12-14 | 2019-05-28 | 平安科技(深圳)有限公司 | Generation method, terminal device and the medium of scorecard model |
CN109840699A (en) * | 2019-01-23 | 2019-06-04 | 深圳壹账通智能科技有限公司 | Appraisal procedure, device, computer equipment and storage medium on qualified investor's line |
CN111382909A (en) * | 2020-03-12 | 2020-07-07 | 上海携程商务有限公司 | Rejection inference method based on survival analysis model expansion bad sample and related equipment |
CN111639102A (en) * | 2020-06-01 | 2020-09-08 | 阳光保险集团股份有限公司 | Client data resource sharing method and device and electronic equipment |
CN112419025A (en) * | 2020-11-20 | 2021-02-26 | 泰康保险集团股份有限公司 | User data processing method and device, storage medium and electronic equipment |
CN112700321A (en) * | 2020-12-31 | 2021-04-23 | 重庆富民银行股份有限公司 | Multi-rule anti-fraud prediction method and system based on user behavior data |
CN113191873A (en) * | 2021-04-23 | 2021-07-30 | 武汉赢联数据技术股份有限公司 | Bank credit card customer risk early warning system based on cloud data management |
CN113298639A (en) * | 2021-05-14 | 2021-08-24 | 中证鹏元资信评估股份有限公司 | Credit rating system with high risk screening function |
CN113516547A (en) * | 2021-04-23 | 2021-10-19 | 武汉赢联数据技术股份有限公司 | Voice broadcast type graded credit card client risk early warning system |
CN113537666A (en) * | 2020-04-16 | 2021-10-22 | 马上消费金融股份有限公司 | Evaluation model training method, evaluation and business auditing method, device and equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106779457A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of rating business credit method and system |
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 |
CN107369095A (en) * | 2017-06-15 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method of vehicle insurance business, apparatus and system |
-
2017
- 2017-11-24 CN CN201711190094.3A patent/CN108053310A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106779457A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of rating business credit method and system |
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 |
CN107369095A (en) * | 2017-06-15 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method of vehicle insurance business, apparatus and system |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921707A (en) * | 2018-06-05 | 2018-11-30 | 中国平安人寿保险股份有限公司 | Core protects processing method, device, computer equipment and storage medium |
CN108960111B (en) * | 2018-06-26 | 2020-11-13 | 深圳市融壹买信息科技有限公司 | Face recognition method, face recognition system and terminal equipment |
CN108960111A (en) * | 2018-06-26 | 2018-12-07 | 深圳市买买提信息科技有限公司 | Face identification method, system and terminal device |
CN109146132A (en) * | 2018-07-11 | 2019-01-04 | 深圳市买买提信息科技有限公司 | Field miss rate method for early warning, server, storage medium and computer program |
CN109034502A (en) * | 2018-09-04 | 2018-12-18 | 中国光大银行股份有限公司信用卡中心 | Anti- Fraud Prediction method and device |
CN109461016A (en) * | 2018-09-10 | 2019-03-12 | 平安科技(深圳)有限公司 | Data methods of marking, device, computer equipment and storage medium |
CN109461016B (en) * | 2018-09-10 | 2023-05-05 | 平安科技(深圳)有限公司 | Data scoring method, device, computer equipment and storage medium |
CN109816509A (en) * | 2018-12-14 | 2019-05-28 | 平安科技(深圳)有限公司 | Generation method, terminal device and the medium of scorecard model |
CN109726242A (en) * | 2018-12-29 | 2019-05-07 | 陕西西部资信股份有限公司 | Data processing method and system |
CN109840699A (en) * | 2019-01-23 | 2019-06-04 | 深圳壹账通智能科技有限公司 | Appraisal procedure, device, computer equipment and storage medium on qualified investor's line |
CN111382909A (en) * | 2020-03-12 | 2020-07-07 | 上海携程商务有限公司 | Rejection inference method based on survival analysis model expansion bad sample and related equipment |
CN113537666A (en) * | 2020-04-16 | 2021-10-22 | 马上消费金融股份有限公司 | Evaluation model training method, evaluation and business auditing method, device and equipment |
CN113537666B (en) * | 2020-04-16 | 2024-05-03 | 马上消费金融股份有限公司 | Evaluation model training method, evaluation and business auditing method, device and equipment |
CN111639102A (en) * | 2020-06-01 | 2020-09-08 | 阳光保险集团股份有限公司 | Client data resource sharing method and device and electronic equipment |
CN111639102B (en) * | 2020-06-01 | 2024-04-05 | 阳光保险集团股份有限公司 | Client data resource sharing method and device and electronic equipment |
CN112419025A (en) * | 2020-11-20 | 2021-02-26 | 泰康保险集团股份有限公司 | User data processing method and device, storage medium and electronic equipment |
CN112700321A (en) * | 2020-12-31 | 2021-04-23 | 重庆富民银行股份有限公司 | Multi-rule anti-fraud prediction method and system based on user behavior data |
CN113191873A (en) * | 2021-04-23 | 2021-07-30 | 武汉赢联数据技术股份有限公司 | Bank credit card customer risk early warning system based on cloud data management |
CN113516547A (en) * | 2021-04-23 | 2021-10-19 | 武汉赢联数据技术股份有限公司 | Voice broadcast type graded credit card client risk early warning system |
CN113516547B (en) * | 2021-04-23 | 2023-10-03 | 武汉赢联数据技术股份有限公司 | Voice broadcast type hierarchical credit card customer risk early warning system |
CN113298639A (en) * | 2021-05-14 | 2021-08-24 | 中证鹏元资信评估股份有限公司 | Credit rating system with high risk screening function |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108053310A (en) | Credit scoring method, apparatus, computer equipment and storage medium | |
CN108648074A (en) | Loan valuation method, apparatus based on support vector machines and equipment | |
CN106296389A (en) | The appraisal procedure of a kind of user credit degree and device | |
CN108256691A (en) | Refund Probabilistic Prediction Model construction method and device | |
CN116342259A (en) | Automatic user credit rating method and device, electronic equipment and medium | |
CN109063931A (en) | A kind of model method for predicting freight logistics driver Default Probability | |
CN106651570A (en) | System and method for real-time loan approval | |
CN108596495A (en) | A kind of retail credit business points-scoring system and method | |
CN111523996A (en) | Approval method and system | |
CN112102073A (en) | Credit risk control method and system, electronic device and readable storage medium | |
CN106570753A (en) | Method and server for controlling default risk | |
CN112734247A (en) | Method, system, storage medium and electronic device for automatic approval of guarantee and credit | |
CN112163944A (en) | Loan qualification scoring method and device for customer, computer equipment and storage medium | |
CN111951093A (en) | Personal credit score scoring method | |
CN108629508A (en) | Credit risk sorting technique, device, computer equipment and storage medium | |
Dimitras et al. | Evaluation of empirical attributes for credit risk forecasting from numerical data | |
CN109146667B (en) | Method for constructing external interface comprehensive application model based on quantitative statistics | |
CN114418748A (en) | Vehicle credit evaluation method, device, equipment and storage medium | |
CN114004691A (en) | Line scoring method, device, equipment and storage medium based on fusion algorithm | |
CN112308698A (en) | WeChat end loan product management method and system supporting second-level legal person | |
CN116823442A (en) | Prediction method for fraud risk in credit business | |
DE202022107234U1 (en) | Online banking fraud detection system using blockchain and artificial intelligence through backlogging | |
CN115564591A (en) | Financing product determination method and related equipment | |
CN112101950B (en) | Suspicious transaction monitoring model feature extraction method and suspicious transaction monitoring model feature extraction device | |
CN113724061A (en) | Consumer financial product credit scoring method and device based on customer grouping |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180518 |