CN110728568A - Credit credit line method and system for credit investigation blank client - Google Patents
Credit credit line method and system for credit investigation blank client Download PDFInfo
- Publication number
- CN110728568A CN110728568A CN201910827561.1A CN201910827561A CN110728568A CN 110728568 A CN110728568 A CN 110728568A CN 201910827561 A CN201910827561 A CN 201910827561A CN 110728568 A CN110728568 A CN 110728568A
- Authority
- CN
- China
- Prior art keywords
- credit
- applicant
- student
- line
- money
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009825 accumulation Methods 0.000 claims description 9
- 238000000151 deposition Methods 0.000 claims description 9
- 239000000047 product Substances 0.000 description 11
- 230000002265 prevention Effects 0.000 description 9
- 238000012502 risk assessment Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Economics (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a credit line granting method for credit investigation blank customers, which receives loan application data of an applicant; reviewing loan application data; after the examination is passed, if the applicant is a student, the information of the student is inquired through an education system; if the applicant is a non-student, inquiring the information of the social human resource system; setting the credit line according to the loan application data and the inquired data; the invention also provides a credit line system facing credit investigation blank customers, which effectively classifies and identifies the credit investigation blank customers, reduces the risk of personal online credit service and simultaneously provides better financial service for students at school.
Description
Technical Field
The invention relates to a credit line granting method and system for credit investigation blank clients.
Background
Today, the internet finance is rapidly developing, the pure online loan service has gradually replaced the traditional offline loan, and in the online loan approval process, the automatic examination rules of each financial institution become the key point for controlling the credit risk due to the lack of offline investigation of the financial institution employees. At present, partial risk cases appear, customers have the convenience of online loan by using banks, and partial student groups are organized to apply for loan and then move the loan. To avoid such risk from reoccurring. The method is characterized in that a risk identification means for the credit investigation blank users is established, the credit investigation blank users are customers who do not have business transaction with banks and carry out credit investigation on personal information blanks or non-credit information, most of the customers are online student groups and graduates just entering the society, and an accurate credit line control method is not provided.
The research scope for credit risk identification is also more extensive, and the related documents for credit investigation and risk assessment are as follows:
1. a bank credit system risk assessment method and apparatus (CN 105550927A). This document discloses a bank credit system risk assessment method and apparatus, which not only considers the conventional indicators such as enterprise profitability and assets, but also comprehensively considers the activity of business traffic and the condition of fund flow between enterprises when performing enterprise credit risk assessment. And by utilizing mass data, potential useful new evaluation indexes are mined, and the current novel technologies such as data mining, social networks and the like are integrated into the evaluation process, so that the accuracy of the evaluation result is improved.
2. A credit risk assessment method and system (CN 107993143A). The cloud computing ERP system is used for acquiring the multidimensional data of the enterprise and analyzing the multidimensional data to obtain an analysis result, and the provided credit risk assessment method can improve the accuracy and efficiency of credit risk assessment and has high practicability.
3. A personal credit risk assessment method and system (CN 107993140A). The document inputs the real information of the user to be evaluated into the trained evaluation model, and obtains the risk evaluation information of the user to be evaluated. The invention also discloses a personal credit risk assessment system which can improve the assessment efficiency and accuracy.
4. Credit risk control method and system, storage medium (CN 108510282B). And respectively collecting target type information and a target identity authentication result of the borrower based on the target information requirement and the target identity authentication process, and determining the credit line of the borrower based on the target type information and the target identity authentication result.
The first and second documents are facing credit customers as enterprise customers; the third document does not set up a corresponding credit granting model for a specific customer group and credit investigation blank users, and the fourth document only authenticates personal information of the customer, so that credit risk of the customer is difficult to find when credit related information of the customer is missing.
Disclosure of Invention
The invention aims to solve the technical problem of providing a credit line granting method and system for credit investigation blank clients, which can effectively classify and identify the credit investigation blank clients, reduce the risk of personal online credit service and provide better financial service for students at school.
One of the present invention is realized by: a credit line granting method for credit investigation blank clients comprises the following steps:
step 1, receiving loan application data of an applicant;
step 2, checking loan application data;
step 3, after examination, if the applicant is a student, inquiring information of the student through an education system; if the applicant is a non-student, inquiring the information of the social human resource system;
step 4, setting the credit line according to the loan application data and the inquired data;
and 5, wholesale the money to the applicant according to the credit line.
Further, the step 3 is further specifically: after the examination is passed, if the applicant is a student, inquiring information of the student through an education system, wherein the information comprises whether the student is poverty or poverty, reward and punishment in school, score in school and credit in line of associated people; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
Further, the step 4 is further specifically: setting the credit line according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
Further, the step 5 is further specifically: before depositing money, obtaining the data of the applicant again, and if the risk exists, refusing to batch the money to the applicant; if no risk exists, money is batched to the applicant according to the credit limit.
Further, the step 5 is further specifically: before depositing money, obtaining the data of the applicant again, if the applicant is a student and the applicant appears a set place, the class escaping time exceeds the limited time or the average score is reduced to a limited score, refusing to batch the money to the applicant; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
The second invention is realized by the following steps: a credit line system facing credit investigation blank clients comprises:
a receiving module for receiving loan application data of an applicant;
the examination module is used for examining the loan application data;
the inquiry module inquires the information of the applicant through the education system if the applicant is a student after the examination is passed; if the applicant is a non-student, inquiring the information of the social human resource system;
the limit setting module is used for setting the credit limit according to the loan application data and the inquired data;
and the money paying module is used for paying money to the applicant according to the credit line.
Further, the query module is further specifically: after the examination is passed, if the applicant is a student, inquiring information of the student through an education system, wherein the information comprises whether the student is poverty or poverty, reward and punishment in school, score in school and credit in line of associated people; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
Further, the limit setting module further specifically comprises: setting the credit line according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
Further, the deposit module is further specifically: before depositing money, obtaining the data of the applicant again, and if the risk exists, refusing to batch the money to the applicant; if no risk exists, money is batched to the applicant according to the credit limit.
Further, the deposit module is further specifically: before depositing money, obtaining the data of the applicant again, if the applicant is a student and the applicant appears a set place, the class escaping time exceeds the limited time or the average score is reduced to a limited score, refusing to batch the money to the applicant; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
The invention has the following advantages: the invention can effectively classify and identify credit investigation blank users, reduce the risk of personal online credit service and provide better financial service for students at school.
(I) economic benefits
Through effective pre-loan wind control means and real-time risk transaction risk separation, bad account risk of a bank can be effectively reduced, and then credit wind control level is improved, and interest income of loans is guaranteed. Meanwhile, the client viscosity is gradually improved, and high-quality clients of banks are cultivated.
(II) social benefits
The method provides better and guaranteed financial service for school students and young people just walking into the society, and better establishes credit systems of the school and the society.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a diagram of the intra-row architecture for credit investigation and white-user credit granting and wind control according to the present invention.
FIG. 3 is a diagram illustrating the docking of the in-line and out-of-line data query system according to the present invention.
Fig. 4 is a flow chart of loan application of the invention.
FIG. 5 is a flowchart illustrating the flow of the invention for the outbound confirmation.
FIG. 6 is a flowchart illustrating how to build a model of credit in accordance with the present invention.
Fig. 7 is a flow chart of the loan wind control of the invention.
Detailed Description
As shown in fig. 1, the credit line granting method for credit investigation blank client of the present invention includes:
step 1, receiving loan application data of an applicant;
step 2, checking loan application data;
step 3, after examination, if the applicant is a student, inquiring information of the student through an education system, wherein the information comprises whether the student is poverty or poverty, reward and punishment in school, score in school and credit record in association with the student; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
Step 4, setting the credit line according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
Step 5, before depositing money, obtaining the data of the applicant again, if the applicant is a student and the set point appears, the class escaping time exceeds the limited time or the average score is reduced to the limited score, refusing to batch the money to the applicant; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
The invention relates to a credit line granting system for credit investigation blank clients, which comprises:
a receiving module for receiving loan application data of an applicant;
the examination module is used for examining the loan application data;
the inquiry module inquires information of the applicant, including whether the applicant is poverty and poverty, reward and punishment in school, score in school and credit record in association with people, through the education system if the applicant is a student after the examination is passed; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
The limit setting module is used for setting the credit limit according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
The money paying module acquires the data of the applicant again before paying, and refuses to batch money to the applicant if the applicant is a student and the given time is over or the average score is reduced by a limited score when the given time is over, the class escaping class is over or the average score is reduced; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
The invention realizes a risk identification method for credit investigation blank users, which carries out scene analysis on a bank personal loan process, carries out classification analysis on clients when personal credit investigation of the clients is blank in online loan service, and records the result in a client relationship management system in a row for subsequent client management. The specific information is as follows:
1. and carrying out data interface with the education system, and identifying whether the credit investigation blank user is a student at a school or not.
2. Different risk identification schemes are used for the client groups at school and not at school.
3. And identifying the risks of the associated persons of the clients by utilizing the inline and out-of-line data, and judging whether the loan is in suspicion of appropriation.
4. And carrying out risk identification on loan applications of the same related client in a short time.
The system function of the invention specifically comprises the following contents:
1. according to the general younger characteristics of credit investigation blank users, the clients are divided into two types of clients, namely, school students and non-school students. The method comprises the steps of establishing an information sharing mechanism with a regional education system, pushing the information to the education system for inquiry when a client initiates a credit application, confirming whether students are students at school, acquiring information such as whether the students are poverty students or not, and pushing the information of the clients for using credit and subsequent repayment to the education system after giving credit financial services to the client. And the bank and the school together control the credit risk of the students by utilizing the related information and the information sharing mechanism of the education system.
2. For the clients who are not at school or have graduated and cannot obtain information from the education system, the resources sharing mechanism is established with the social human resource system to obtain data such as working data of the clients, the third-party data company is connected to obtain whether the clients have online loan and associated client risks, and the data is imported into the inline big data platform to carry out comprehensive judgment so as to identify the credit risks of the clients.
3. And obtaining the comprehensive default risk of the customer by using a Bayesian model and a big data platform according to the analysis result of different risk factor combinations.
(I) Integrated System architecture
As shown in fig. 2, the overall system architecture of the present patent combines inline data, campus data, and social human resource data of a client as risk factors of a client trust model. And a customer relationship management system, a customer information system, a retail credit system, a big data platform and a mobile phone bank as a loan application channel in the associated line are used as system supports of patents. And combining a flow calculation engine and big data modeling, and screening and blocking the risks before, during and after the loan of the client.
(II) information sharing mechanism with educational system and social human resources
According to the ' notice about further strengthening the campus loan standard management work ' issued by the China banking and supervising department, the education department, the human resource department and the social security department in a united way ', the normal order of campus loans is maintained, and the commercial bank and the policy bank are required to purposefully develop financial products such as college-learning assistance, training, consumption, entrepreneurship and the like on the premise of controllable risks, and the interest rate of credit limits is reasonably set. Banks need to gradually replace various loan network and loan platforms in campuses to provide financial services related to students. The bank system needs to complete sharing of information resources together with the education system, and data transmission between the bank system and the education system can be completed in a special line butt joint mode, so that safety in data transmission is guaranteed. The bank is connected with an education system database through a bank external connection system to complete inquiry and information push, and whether the education inquiry information content is limited to the poverty and poverty school or not is judged, and the school-time score is obtained under the condition of the school awards and punishment.
For non-student client groups, such as graduate clients, a mechanism for establishing information sharing with the social and human resources system is needed. The bank system is similar to the interaction of the social human resource system, the data interaction inside and outside the bank is completed through the external connection system, and the data transmission is completed through a special line mode, so that the data safety is ensured. The social human resource system query information includes but is not limited to the employment situation, salary situation and administrative reward and punishment of customers.
As shown in fig. 3, the data query relationship for the inline system and the inline system.
(III) Risk control Scenario partitioning
The system participation in the credit transaction scenario is as follows:
as shown in fig. 4 and 5, the effective credit requirement of a credit investigation blank client needs to be confirmed, a credit scene needs to be divided, and after a data sharing mechanism is established, the credit scene targeted by the patent is a scene of online loan application of a personal client, including a loan application link, a fund accounting environment and a post-loan risk early warning link. The specific business process is as follows:
1. when applying for loan, the client uses the mobile phone bank to supplement and assist the verification of identity materials and loan purpose information materials, and the authorized bank can inquire the relevant data of the client (whether the student client is poor or not, shared information such as school scores and the like, and the working client inquires payment condition shared data such as on duty, social security, tax and the like).
2. And judging couples or parent-child relations recorded in the customer relationship management system in the customer association bank according to information inside and outside the bank, and frequently contacting risks of the commuters recorded in the data outside the bank (the frequently contacting risks of the commuters comprise abnormal transfer behaviors in the bank, credit default behaviors of credit investigation, other risks of credit investigation and open court judgment).
3. And inquiring the relevant information of the client from the education system and the social human resource system for credit granting. And (4) adopting different risk models to respectively carry out loan line credit for student groups and social employees by judging the category of the client groups. (details of the model information are described below in the model establishment calculation credit line)
4. When the account is confirmed, whether the client has high risk operation behavior is judged, if the risk transaction occurs, the client is blocked or early warned in time (the specific risk treatment part is detailed in the real-time risk prevention and control system establishment below)
(IV) establishing a model to calculate the credit line
As shown in FIG. 6, the establishment of the credit model is as follows:
firstly, establishing model factors, and using the internal and external data of the client as credit model factors. The out-of-line data used by the student client group includes: whether poverty is poverty or living, whether the poverty is in school or not, and whether the score (shared information) is in school or not are used as credit line model factors, wherein the existing data in the line comprises the following data: and (5) associating the trust records in the rows. The extravehicular data used by the social staff includes: the specific occupation, the period of employment, the average income (nearly March, nearly half year, nearly one year), the social security payment condition, the tax payment condition, the existing data in the row includes: the purchase condition of the intra-row financial products and the contract condition of the intra-row business. The specific credit formula is as follows:
student client group credit line + a poor credit line + a number of awards at school-b number of awards at school + c number of awards at leveling average performance point + d MAX (credit line granted in related personnel)
Wherein: a. b, c and d are respectively related coefficients, and when a plurality of related persons in the customer have credit lines, the highest credit line is taken as a credit factor. The highest credit limit does not exceed the consumption limit of the credit scene.
The credit line of the social on-duty personnel is the trade line + a the time of entry + b MAX (average income in nearly three months, average income in nearly half a year) + c monthly social security payment transaction line + d monthly public deposit payment transaction line + e tax payment transaction line + f the internal financial product purchase share + g the internal business subscription number.
Wherein: a. b, c, d, e, f and g are respectively correlation coefficients, and the average income of customers is the highest value of the average value of about March, about half year and about one year. The credit line does not exceed the consumption line of the credit scene.
Next, a look-ahead mode is used, and relevant weight coefficient values are set by using expert experience, and data accumulation is performed.
As in the student formula above: in the line, an expert model is used to set 1000 yuan for poor survival, a coefficient a is 100, a coefficient b is 100, a coefficient c is 100, and a coefficient d is 0.005, then, a student is poor survival, the number of times of correction and reward is 3, the number of times of division is 1, the average performance point is 3.5, the highest credit limit of the inter-line related person is 100000 yuan, and the credit amount of the student is 1000+100, 3-100, 1 is 100, 3.5+0.005, 100000, 2050 yuan. If the consumption amount of the current credit granting scene of the student client is 2000 yuan (namely the amount of the loan applied by the applicant) and is lower than the amount calculated by the formula, the final credit granting amount is 2000 yuan.
And finally, training the data in an incremental mode by adopting a Bayesian model according to the credit amount of the customer in the historical data and default risk condition data serving as the basis of big data model analysis, calculating the risk occurrence probability of the customer loan after establishing an automatic credit model, and automatically adjusting the weight coefficient of each factor in the credit model and the amounts of poverty, industry credit and the like according to the risk occurrence probability. And comparing the credit amount obtained by the big data model with the credit amount obtained by the original scoring card, and continuously optimizing the model.
After certain data accumulation and model training are carried out, due to the fact that default risks of clients are considered in the model, the coefficients in the formula are optimized and adjusted, for example, the poor living quota is adjusted to 800 yuan from 1000 yuan of an original expert model, the division coefficient b is adjusted to 200 yuan, and the performance point coefficient c is adjusted to 80 yuan.
The adjusted credit amount of the student is 800+100 x 3-200 x 1+80 x 3.5+0.005 x 100000-1680 yuan. Because the credit amount does not exceed the consumption scene amount, the final credit amount of the student client after model optimization is 1680 yuan.
And continuously adding new model factors according to the service operation condition and the service data accumulation, and then adding the new model factors into the limit test formula.
(V) establishment of real-time risk prevention and control system
Besides the pre-loan risk early warning and the limit measuring and calculating rule, a set of complete real-time wind control system needs to be established to carry out prevention and control in the loan, and the bank's own real-time risk prevention and control system is utilized to apply for risky centralized credit and adopt real-time transaction blocking with credit.
As shown in fig. 7, the real-time wind control process of the bank loan service is as follows:
in the steps of loan application, examination and approval, loan and loan, wind control precaution rule control is added, real-time prevention and control are carried out on the generated risk, and particularly in the loan process, when the risky transaction is inquired, the loan process is blocked in real time, so that the credit risk is avoided. Meanwhile, a big data wind control platform is used for calculating risk data in real-time services, storing the risk data and providing a data basis for an optimization model.
Since the credit investigation blank user group is mainly a young customer group, special treatment needs to be performed on the high-risk items and the risk characteristics of the young group in the aspect of risk prevention and control. The high risk of the young group comprises excessive advanced consumption, high-risk network credit and campus credit behaviors. The risks are not recorded to the people to assess credit, which is one of the reasons that the risk of assessing blank user groups is difficult to find, and under the condition that data is lack in the rows, the data needs to be shared with campus and social human resource data, and a third party cooperates with the campus and social human resource data, and the campus and social human resource data comprises an e-commerce platform, a data company and the like, so that the records of the high-risk behaviors of the customers are obtained and blocked in time.
Specific prevention and control rules are currently available as follows:
TABLE 5.1 wind control rules
The above rule actual risk handling case is as follows: when a client applies for a loan, the big data real-time computing engine finds that a large number of applications occur in the IP used by the client in a short time, judges that the IP has a centralized loan application risk, carries out early warning in the application stage, adds the IP to an IP blacklist, and rejects the loan application of the client.
The method comprises the steps of calculating risk probability in the money paying process and after money paying of a customer by adopting a Bayesian model, setting a risk threshold, conducting real-time blocking processing on risk transactions exceeding the threshold, conducting registration and reminding processing on transactions in the threshold, prompting default risks of the customer after credit, and enabling personnel in a bank to conduct risk prevention and control processing as soon as possible. And meanwhile, continuously extracting risk factors in the case to serve as risk factors of a client risk model, and optimizing and perfecting the model and the prevention and control rules.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.
Claims (10)
1. A credit line granting method for credit investigation blank clients is characterized in that: the method comprises the following steps:
step 1, receiving loan application data of an applicant;
step 2, checking loan application data;
step 3, after examination, if the applicant is a student, inquiring information of the student through an education system; if the applicant is a non-student, inquiring the information of the social human resource system;
step 4, setting the credit line according to the loan application data and the inquired data;
and 5, wholesale the money to the applicant according to the credit line.
2. The credit line method for credit investigation blank client as claimed in claim 1, wherein: the step 3 is further specifically as follows: after the examination is passed, if the applicant is a student, inquiring information of the student through an education system, wherein the information comprises whether the student is poverty or poverty, reward and punishment in school, score in school and credit in line of associated people; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
3. The credit line method for credit investigation blank client as claimed in claim 2, wherein: the step 4 is further specifically as follows: setting the credit line according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
4. The credit line method for credit investigation blank client as claimed in claim 1, wherein: the step 5 is further specifically as follows: before depositing money, obtaining the data of the applicant again, and if the risk exists, refusing to batch the money to the applicant; if no risk exists, money is batched to the applicant according to the credit limit.
5. The credit line method for credit investigation blank client as claimed in claim 4, wherein: the step 5 is further specifically as follows: before depositing money, obtaining the data of the applicant again, if the applicant is a student and the applicant appears a set place, the class escaping time exceeds the limited time or the average score is reduced to a limited score, refusing to batch the money to the applicant; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
6. A credit line system facing credit investigation blank clients is characterized in that: the method comprises the following steps:
a receiving module for receiving loan application data of an applicant;
the examination module is used for examining the loan application data;
the inquiry module inquires the information of the applicant through the education system if the applicant is a student after the examination is passed; if the applicant is a non-student, inquiring the information of the social human resource system;
the limit setting module is used for setting the credit limit according to the loan application data and the inquired data;
and the money paying module is used for paying money to the applicant according to the credit line.
7. The credit line system for credit investigation blank client as claimed in claim 6, wherein: the query module is further specifically: after the examination is passed, if the applicant is a student, inquiring information of the student through an education system, wherein the information comprises whether the student is poverty or poverty, reward and punishment in school, score in school and credit in line of associated people; if the applicant is a non-student, inquiring the information of the social human resource system, including the industry, whether the applicant is at work, the service life, the average income, the monthly social security payment transaction flow, the monthly public deposit payment transaction flow, the tax payment transaction flow, the in-line financial product purchase share and the in-line service contract number.
8. The credit line system for credit investigation blank client as claimed in claim 7, wherein: the limit setting module is further specifically: setting the credit line according to the loan application data and the inquired data; the credit line of the student is poor credit line + a at the school reward times-b + c at the school position times + d MAX at the leveling average performance point;
wherein: a. b, c and d are respectively set weight coefficients, and when a plurality of associated persons in the customer have credit lines, the highest credit line is taken as MAX;
if the credit is in operation, the non-student credit line is the industry line + a '+ the period of employment + b' + the average wage + c '+ the month average social security payment transaction flow + d' + the month public accumulation payment transaction flow + e '+ the tax payment transaction flow + f' + the in-line business subscription number of the purchased share of the in-line financial product; wherein if the student is not working, the non-student credit line is 0;
wherein: a ', b', c ', d', e ', f' and g 'are respectively set weight coefficients, and the average payroll is the highest value of the customer's average value in the last march, the average value in the last half year and the average value in the last year;
the highest credit line does not exceed the consumption line of the credit scene.
9. The credit line system for credit investigation blank client as claimed in claim 6, wherein: the deposit module further comprises: before depositing money, obtaining the data of the applicant again, and if the risk exists, refusing to batch the money to the applicant; if no risk exists, money is batched to the applicant according to the credit limit.
10. The credit line system for credit investigation blank client as claimed in claim 9, wherein: the deposit module further comprises: before depositing money, obtaining the data of the applicant again, if the applicant is a student and the applicant appears a set place, the class escaping time exceeds the limited time or the average score is reduced to a limited score, refusing to batch the money to the applicant; if not, the money is batched to the applicant according to the credit line;
if the applicant is a non-student and the student leaves the job or is in time sharing with a set place, refusing to batch the money to the applicant; otherwise, the money is batched to the applicant according to the credit line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910827561.1A CN110728568A (en) | 2019-09-03 | 2019-09-03 | Credit credit line method and system for credit investigation blank client |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910827561.1A CN110728568A (en) | 2019-09-03 | 2019-09-03 | Credit credit line method and system for credit investigation blank client |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110728568A true CN110728568A (en) | 2020-01-24 |
Family
ID=69218866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910827561.1A Pending CN110728568A (en) | 2019-09-03 | 2019-09-03 | Credit credit line method and system for credit investigation blank client |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728568A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598500A (en) * | 2020-12-21 | 2021-04-02 | 中国建设银行股份有限公司 | Credit processing method and system for non-limit client |
| CN113205396A (en) * | 2021-06-04 | 2021-08-03 | 中国银行股份有限公司 | Rental house loan processing method and device |
| CN113487424A (en) * | 2021-08-02 | 2021-10-08 | 中国工商银行股份有限公司 | Method and device for determining credit line of small and micro enterprise |
| CN114418729A (en) * | 2021-12-08 | 2022-04-29 | 同盾网络科技有限公司 | White household default risk assessment method and device, electronic equipment and storage medium |
| WO2022134424A1 (en) * | 2020-12-24 | 2022-06-30 | 平安普惠企业管理有限公司 | Service flow processing method and apparatus, and computer device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005018A (en) * | 2010-12-13 | 2011-04-06 | 苏州德融嘉信信用管理技术有限公司 | Credit limit management system |
| CN103150672A (en) * | 2013-04-09 | 2013-06-12 | 长沙钢为网络科技有限公司 | Bank quick credit granting system and method |
| US20160350849A1 (en) * | 2015-05-27 | 2016-12-01 | Mastercard Asia/Pacific Pte Ltd. | Computerized method and system of credit application and issuance thereof |
| CN106651570A (en) * | 2016-12-27 | 2017-05-10 | 中国建设银行股份有限公司 | System and method for real-time loan approval |
| CN107578330A (en) * | 2017-09-11 | 2018-01-12 | 安徽天恩信息科技有限公司 | A kind of business bank provides a loan approval system and its method with no paper at all |
| CN107993146A (en) * | 2018-01-25 | 2018-05-04 | 深圳市前海吉顺信科技发展有限公司 | The air control method and system of financial big data |
| CN108198067A (en) * | 2017-12-04 | 2018-06-22 | 屠雪祥 | Loan limit automatic evaluation system and loan limit method for automatically evaluating |
| CN109711969A (en) * | 2018-08-17 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Campus credit methods, device, equipment and storage medium based on data analysis |
-
2019
- 2019-09-03 CN CN201910827561.1A patent/CN110728568A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005018A (en) * | 2010-12-13 | 2011-04-06 | 苏州德融嘉信信用管理技术有限公司 | Credit limit management system |
| CN103150672A (en) * | 2013-04-09 | 2013-06-12 | 长沙钢为网络科技有限公司 | Bank quick credit granting system and method |
| US20160350849A1 (en) * | 2015-05-27 | 2016-12-01 | Mastercard Asia/Pacific Pte Ltd. | Computerized method and system of credit application and issuance thereof |
| CN106651570A (en) * | 2016-12-27 | 2017-05-10 | 中国建设银行股份有限公司 | System and method for real-time loan approval |
| CN107578330A (en) * | 2017-09-11 | 2018-01-12 | 安徽天恩信息科技有限公司 | A kind of business bank provides a loan approval system and its method with no paper at all |
| CN108198067A (en) * | 2017-12-04 | 2018-06-22 | 屠雪祥 | Loan limit automatic evaluation system and loan limit method for automatically evaluating |
| CN107993146A (en) * | 2018-01-25 | 2018-05-04 | 深圳市前海吉顺信科技发展有限公司 | The air control method and system of financial big data |
| CN109711969A (en) * | 2018-08-17 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Campus credit methods, device, equipment and storage medium based on data analysis |
Non-Patent Citations (3)
| Title |
|---|
| 李意柯: "商业银行个人客户授信评估的思考", 《中国金融电脑》 * |
| 福州晚报: "房贷发放前会再次查询客户征信信息 消费贷或影响放款", 《福州新闻》 * |
| 蔡鸣龙: "《商业银行信贷管理》", 30 June 2019 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598500A (en) * | 2020-12-21 | 2021-04-02 | 中国建设银行股份有限公司 | Credit processing method and system for non-limit client |
| WO2022134424A1 (en) * | 2020-12-24 | 2022-06-30 | 平安普惠企业管理有限公司 | Service flow processing method and apparatus, and computer device and storage medium |
| CN113205396A (en) * | 2021-06-04 | 2021-08-03 | 中国银行股份有限公司 | Rental house loan processing method and device |
| CN113487424A (en) * | 2021-08-02 | 2021-10-08 | 中国工商银行股份有限公司 | Method and device for determining credit line of small and micro enterprise |
| CN114418729A (en) * | 2021-12-08 | 2022-04-29 | 同盾网络科技有限公司 | White household default risk assessment method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728568A (en) | Credit credit line method and system for credit investigation blank client | |
| CN110610413A (en) | Loan transaction risk control method and system | |
| JP2022528839A (en) | Personal information protection system | |
| US20160042450A1 (en) | Methods and systems for deal structuring for automobile dealers | |
| JP2022520824A (en) | Intelligent warning system | |
| US8751338B2 (en) | System and method of intra-cycle payment of accrued employee wages | |
| US20040019500A1 (en) | System and method for providing corporate governance-related services | |
| US20110166987A1 (en) | Evaluating Loan Access Using Online Business Transaction Data | |
| US20160196605A1 (en) | System And Method To Search And Verify Borrower Information Using Banking And Investment Account Data And Process To Systematically Share Information With Lenders and Government Sponsored Agencies For Underwriting And Securitization Phases Of The Lending Cycle | |
| US20100268640A1 (en) | Apparatus and methods for renegotiating debt | |
| US20080109314A1 (en) | Method and apparatus for determining a customer's likelihood of reusing a financial account | |
| CN112435112A (en) | Bank internet credit wind control method for small and micro enterprises | |
| Woods et al. | Towards integrating insurance data into information security investment decision making | |
| US20190066248A1 (en) | Method and system for identifying potential fraud activity in a tax return preparation system to trigger an identity verification challenge through the tax return preparation system | |
| DeLiema et al. | Findings from a pilot study to measure financial fraud in the United States | |
| CN113743816A (en) | Vehicle rental risk control method and device, computer equipment and storage medium | |
| Xu et al. | On education level and terms in obtaining P2P funding: New evidence from China | |
| Jaya Sakti et al. | Online banking implementation: Risk mapping using erm approach | |
| Sadok et al. | The contribution of AI-Based analysis and rating models to financial inclusion: the Lenddo case for women-led SMEs in developing countries | |
| Nuñez et al. | Online payday and installment loans. who uses them and why | |
| CN109345396B (en) | Intelligent injury claim settlement management system | |
| CN115564591A (en) | Financing product determination method and related equipment | |
| US11797940B2 (en) | Method and system for assessment and negotiation of compensation | |
| Al Zyadat et al. | The Role of the System of Internal Control in Improving the Financial Performance of Water Authority of Jordan in the COVID-19 Pandemic | |
| Alma et al. | Strategic decision making of micro-lenders: An innovative business model for risk management |
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 |