Method for combining logistic regression credit approval based on user data and expert features

Abstract

The invention discloses a method for combining logistic regression credit approval based on user data and expert features. The method comprises the steps of inputting data cleaning, carrying out datadimension reduction and preprocessing, carrying out data classification, data feature engineering and feature extraction, introducing expert features, carrying out feature prediction and outputting anapproval list. In the present invention, according to the credit approval method, expert features in a traditional financial model are combined with a classic machine learning method. The future default possibility of possible dynamic change is predicted by combining market real-time updating data and feature engineering. A prediction model and an optimized logistic regression algorithm are adopted. The complex credit constraints are met. Obtained default probability prediction and risk premium results are more accurate. Auditors can be liberated from heavy credit risk assessment auditing andpricing. The large-scale small and micro enterprise credit approval can be rapidly achieved. It is possible to guarantee intelligent rating and avoid risks.

Description

Technical field [0001] The present invention relates to the technical field of credit artificial intelligence, and in particular to a method for credit approval based on merging logistic regression of user data and expert characteristics. Background technique [0002] With the deepening of inclusive finance and the maturity of the financial lending market, small and micro enterprises have an increasing demand for loans. At the same time, the requirements for loan approval efficiency, loan issuance time, and loan issuance management continue to increase. Under conditions, how to save review time, improve review accuracy, and optimize the management of loan pools has become a huge challenge at present. How to price various risks scientifically and reasonably is for the bank's credit department to achieve efficient operation management, reduce operating costs, An important link to ensure the quality and level of customer service. [0003] The risk premium is mainly determined based o...

AI Technical Summary

Problems solved by technology

[0003] The risk premium is mainly determined according to the company's actual capital cost and the customer's default probability. The main issue in the review process is how to ensure that the interest and principal of the loan can be paid in full and on time, and the approval process is short enough without causing waste of human resources

In general enterprises, most of the detailed audits are conducted by managers or specialized personnel. This working method has natural defects: low audit efficiency, long time consumption, and high requirements for the working ability and physical strength of auditors; Having their own focus and preferences will cause differences in audit results, and there is a certain test for the self-regulation ability of employees at work; (customer credit is characterized by a huge demand, a large number of people, and a small single amount, which leads to manual audits The difficulty and workload of completing this work are relatively large, so manual review is difficult to complete; on the other hand, manual review has not paid good attention to and combined with the real-time risk data in the market, especially a large amount of text data. , often only rely on one's own empirical judgment and patterned processing, which is prone to misjudgment

Images