Financial risk classification method and device and electronic equipment

Abstract

The invention relates to a financial risk classification method and device, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a terminal application listof a user, wherein the terminal application list comprises installed application information; respectively inputting the application information in the terminal application list into a first word vector model and a second word vector model to generate word vector information of the user; and inputting the word vector information of the user into a user risk classification model to generate a riskclassification identifier of the user and a risk probability corresponding to the risk classification identifier, wherein the user risk classification model is obtained by training a multi-layer perceptron model. According to the financial risk classification method and device, the electronic equipment and the computer readable medium, the risk levels of different users can be analyzed adaptively, closed-loop operation of risk management and control is achieved, analysis and disposal bases are provided for managers, and risks caused by manual auditing are reduced.

Description

technical field [0001] The present disclosure relates to the field of computer information processing, in particular, to a financial risk classification method, device, electronic equipment and computer readable medium. Background technique [0002] Individual users or corporate users often carry out borrowing activities by financial service institutions. For financial service institutions, users' borrowing activities are likely to bring risks to financial service companies. At present, the identification of financial risks is often obtained by analyzing the user's basic information and behavior information. For example, the basic information may include the user's age, gender, occupation, region, etc., and the behavior information may include the user's loan information, Repayment information, default information, etc. How to dig out more information that can reflect a certain aspect of the user's characteristics, so as to conduct a more comprehensive analysis and judgment...

AI Technical Summary

Problems solved by technology

[0004] Existing technology’s risk perception of app information is mostly focused on client’s app classification information and manual experience. Every time a new case occurs, it needs to be checked by the reviewing colleagues after demarcating the scope

The result of this is excessive use of manpower, and manpower may be overtired and cause errors

The use of traditional statistical models relies on manual experience, requiring detailed analysis of user app information and expression of abnormal information, which is time-consuming and labor-intensive

Images