Intelligent evaluation method of lines of credit

Abstract

The invention discloses an intelligent evaluation method of lines of credit. The method comprises steps of S1, using the occurrence probability that a user normally fulfils the agreement as an initialcredit scoring value, and using user credit data to train the model of the probability so as to obtain an initial credit scoring model; S2, acquiring credit data of a to-be-evaluated user, and usingthe initial credit scoring model to score the acquired credit data so as to obtain an initial credit scoring value; and S3, inputting the initial credit scoring value into a probability distribution relation between a credit scoring value and a line of credit value constructed according to the probability distribution features in advance, and calculating to obtain the line of credit value of the to-be-evaluated user. According to the invention, the method is advantaged by simple achieving method, capability of achieving intelligent evaluation of the lines of credit, high evaluation efficiencyand precision and flexible application.

Description

technical field [0001] The invention relates to the technical field of credit evaluation, in particular to an intelligent evaluation method for credit limit. Background technique [0002] Credit rating refers to the evaluation by an independent third-party credit rating intermediary agency of the debtor's ability and willingness to repay debt principal and interest in full on schedule, and uses simple rating symbols to indicate the severity of its default risk and loss. Credit rating in a broad sense refers to The overall evaluation of the rating object's ability and willingness to fulfill relevant contracts and economic commitments. When the credit institution accepts the customer's credit application, it uses the characteristic variables in the application form submitted by the customer to establish a scoring model to obtain a credit value of the applicant, and compares this value with the standard value set in advance to judge the possibility of the borrower's overdue , ...

AI Technical Summary

Problems solved by technology

However, this type of method is complex to implement and requires the use of complex machine learning algorithms. For example, the implementation of neural network algorithms is very complex and requires a large amount of data for training. After each update of the data, the model needs to be regenerated. Tuning is also very cumbersome, and the entire evaluation process is inefficient and costly. For occasions with high real-time requirements, this type of method is not applicable

Images