Credit management method based on big data risk control

Abstract

The invention relates to the technical field of credit management, and discloses a credit management method based on big data risk control, and the method comprises the following steps: 1, receiving a loan application of a loan user, and carrying out the data collection of the loan user; step 2, carrying out preliminary auditing on the loan users, and carrying out supplementary information collection on the users who do not pass the auditing; 3, performing loan application data supplementation on the audited user to obtain loan application information of the user; 4, carrying out additional data collection on the loan user, and obtaining credit portrait data of the loan user; 5, calculating a credit risk coefficient according to the risk calculation model, and determining a pre-credit line and a pre-transaction interest rate according to the credit risk data; step 6, manually rechecking the step 5, and performing credit transaction according to the credit line and the transaction interest rate after the rechecking is passed; risk judgment is performed on the loan user through big data, so that the accuracy of risk judgment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of credit management, and more specifically, to a credit management method based on big data risk control. Background Art

[0002] Credit is a form of value movement that is conditional on repayment and interest payment. It not only includes credit activities such as bank deposits and loans, but is also commonly used with "credit" in a broad sense. Credit is an important form of mobilizing and allocating funds in a paid manner, and plays a leveraging role in economic development. Credit can be divided into broad and narrow senses. In a broad sense, credit refers to the general term for credit activities mediated by banks and based on deposits and loans, including deposits, loans and settlement business. In a narrow sense, credit usually refers to bank loans, that is, the act of issuing monetary funds with banks as the main body.

[0003] Risk control is particularly important for the bank's credit business. In the past, risk control was mainly conducted through analysis of historical bank credit data. There were few data sources, making it difficult to guarantee the degree of risk, and there was a certain amount of bad debts. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the present invention provides a credit management method based on big data risk control, which has the advantage of more precise operation.

[0005] To achieve the above purpose, the present invention provides the following technical solution: a credit management method based on big data risk control, comprising the following steps: Step 1: Accept loan applications from loan users and collect data on loan users; Step 2: Conduct a preliminary review of loan users and collect additional information for users who fail the review; Step 3: Supplement the loan application data of the users who have passed the review and obtain the loan application information of the users; Step 4: Collect additional data on loan users to obtain credit profile data of loan users; Step 5: Calculate the credit risk coefficient based on the risk calculation model, and determine the pre-credit limit and pre-transaction interest rate based on the credit risk data; Step 6: Manually review step 5, and after the review is passed, conduct the credit transaction according to the credit line and transaction interest rate.

[0006] As a preferred technical solution of the present invention, in step one, when submitting a loan application, the loan user needs to complete the basic information of the loan user and collect and organize the basic information; the basic information includes but is not limited to the user's name, ID number, mobile phone number, and work information.

[0007] As a preferred technical solution of the present invention, in the step 2, the basic information collected in the step 1 is reviewed and verified by an external database to see if there are any errors in the information; users who fail the review repeat step 1 and resubmit their loan application.

[0008] As a preferred technical solution of the present invention, in step three, the user who passes the review supplements the loan application data, and the loan application information includes but is not limited to the expected loan amount and repayment period.

[0009] As a preferred technical solution of the present invention, in step four, the credit data, financial transaction data, social media data, and public transaction data of the loan user are collected based on the identity information of the loan user, and the four sets of data are processed to obtain credit portrait data.

[0010] As a preferred technical solution of the present invention, in the step five, the credit profile data and loan application data processed in step four are processed and the credit risk coefficient is calculated through a risk calculation model.

[0011] As a preferred technical solution of the present invention, in the step five, several groups of pre-credit data are preset, each group of pre-credit data corresponds to a group of pre-credit limit and pre-transaction interest rate; the pre-credit data and credit risk threshold are processed to obtain a credit safety factor.

[0012] As a preferred technical solution of the present invention, the credit safety factor is compared with the credit risk factor. When the credit safety factor is greater than or equal to the credit risk factor, the pre-credit limit and pre-transaction interest rate in the corresponding pre-credit data are marked as passed.

[0013] As a preferred technical solution of the present invention, in step six, the credit limit and transaction interest rate are manually reviewed and verified with the borrower.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains data on loan users in multiple dimensions through big data, obtains a credit risk coefficient after analyzing and processing the data, and uses the credit risk coefficient to determine pre-credit data and credit risk thresholds; in this way, the accuracy of risk judgment is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] like Figure 1 As shown, the present invention provides a credit management method based on big data risk control, comprising the following steps: Step 1: Accept loan applications from loan users and collect data on loan users; Step 2: Conduct a preliminary review of loan users and collect additional information for users who fail the review; Step 3: Supplement the loan application data of the users who have passed the review and obtain the loan application information of the users; Step 4: Collect additional data on loan users to obtain credit profile data of loan users; Step 5: Calculate the credit risk coefficient based on the risk calculation model, and determine the pre-credit limit and pre-transaction interest rate based on the credit risk data; Step 6: Manually review step 5, and after the review is passed, conduct the credit transaction according to the credit line and transaction interest rate.

[0018] Users who need loans take the initiative to submit applications and supplement their personal information in the application; the entity providing loans collects the information and verifies it to confirm whether there are any errors, and saves and records the information to facilitate data management and subsequent calls. After the information is reviewed and approved, the user will complete and supplement the application for the loan, and the entity providing loans will collect it for subsequent calls. Based on the personal information provided by the user, user data in different dimensions is obtained based on big data, and the user's credit slip is confirmed based on user data in different dimensions; the credit risk coefficient is confirmed based on the credit portrait data, and the pre-credit limit and pre-transaction interest rate are confirmed through the credit risk coefficient. After manual review, the credit transaction is completed.

[0019] Among them, in step one, when submitting a loan application, the loan user needs to complete the basic information of the loan user and collect and organize the basic information; the basic information includes but is not limited to the user's name, ID number, mobile phone number, and work information.

[0020] By supplementing and improving the basic information of the borrowing entity, the information of the reception staff can be clarified, making it convenient to use big data to retrieve additional dimensional information based on the basic information.

[0021] In step 2, the basic information collected in step 1 is reviewed and verified through an external database to see if there are any errors in the information; users who fail the review repeat step 1 and resubmit their loan application. The verification and review of the application subject ensures the normal progress of subsequent steps, reduces redundant work processes, and avoids ineffective work.

[0022] Among them, in step 3, the approved users supplement the loan application data, and the loan application information includes but is not limited to the expected loan amount and repayment period. The collected data is improved for the subsequent construction of credit profile data.

[0023] Among them, in step four, based on the identity information of the loan user, the credit data, financial transaction data, social media data, and public transaction data of the loan user are collected, and the four sets of data are processed to obtain credit portrait data; credit data is a parameter that can mainly reflect the risk level of the loan user, and the remaining three parameters are used as a reference to cooperate with each other to construct credit portrait data for subsequent steps.

[0024] Among them, in step 5, the credit profile data and loan application data processed in step 4 are processed and the credit risk coefficient is calculated through the risk calculation model. The credit profile data and loan information can confirm to a certain extent the risk of whether the loan user can be given a loan, and the credit risk coefficient is used to quantify this risk for subsequent processing.

[0025] Among them, in step five, several groups of pre-credit data are preset, and each group of pre-credit data corresponds to a group of pre-credit line and pre-transaction interest rate; the pre-credit data and credit risk threshold are processed to obtain the credit safety factor. The credit safety factor is compared with the credit risk factor. When the credit safety factor is greater than or equal to the credit risk factor, the pre-credit line and pre-transaction interest rate in the corresponding pre-credit data are marked as passed. Different credit safety factors can be obtained for different pre-credit lines and pre-transaction interest rates; different credit safety factors are compared separately to confirm the most suitable pre-credit line and pre-transaction interest rate, and provide the best choice to both loan users and lending entities.

[0026] Among them, in step 6, the credit limit and transaction interest rate are manually reviewed and verified with the borrower. Manual review is performed to verify and confirm, and the borrowing process is improved to complete the borrowing transaction.

[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A credit management method based on big data risk control, characterized in that: The steps include: Step 1: Accept loan applications from loan users and collect data on loan users; Step 2: Conduct a preliminary review of loan users and collect additional information for users who fail the review; Step 3: Supplement the loan application data of the users who have passed the review and obtain the loan application information of the users; Step 4: Collect additional data on loan users to obtain credit profile data of loan users; Step 5: Calculate the credit risk coefficient based on the risk calculation model, and determine the pre-credit limit and pre-transaction interest rate based on the credit risk data; Step 6: Manually review step 5, and after the review is passed, conduct the credit transaction according to the credit line and transaction interest rate.

2. A credit management method based on big data risk control according to claim 1, characterized in that: In the step 1, when submitting a loan application, the loan user needs to complete the basic information of the loan user and collect and organize the basic information; the basic information includes but is not limited to the user's name, ID number, mobile phone number, and work information.

3. The credit management method based on big data risk control according to claim 1, characterized in that: In the step 2, the basic information collected in the step 1 is reviewed and verified by using an external database to check whether the information is wrong; users who fail the review repeat the step 1 and resubmit the loan application.

4. The credit management method based on big data risk control according to claim 1, characterized in that: In step three, the user who passes the review supplements the loan application data, and the loan application information includes but is not limited to the expected loan amount and repayment period.

5. The credit management method based on big data risk control according to claim 1, characterized in that: In the step 4, based on the identity information of the loan user, the credit data, financial transaction data, social media data, and public transaction data of the loan user are collected, and the four sets of data are processed to obtain credit profile data.

6. The credit management method based on big data risk control according to claim 1, characterized in that: In the step five, the credit profile data and loan application data processed in step four are processed and the credit risk coefficient is calculated through the risk calculation model.

7. The credit management method based on big data risk control according to claim 1, characterized in that: In the step 5, several groups of pre-credit data are preset, and each group of pre-credit data corresponds to a group of pre-credit limit and pre-transaction interest rate; Process the pre-credit data and credit risk threshold to obtain the credit safety factor.

8. A credit management method based on big data risk control according to claim 7, characterized in that: The credit safety factor is compared with the credit risk factor. When the credit safety factor is greater than or equal to the credit risk factor, the pre-credit limit and pre-transaction interest rate in the corresponding pre-credit data are marked as passed.

9. The credit management method based on big data risk control according to claim 1, characterized in that: In step six, the credit limit and transaction interest rate are manually reviewed and verified with the borrower.

Images