Network training method, risk user identification method, device, equipment and medium

Abstract

The present application provides a network training method, risk user identification method, device, electronic equipment, and storage medium. The training method includes: acquiring multiple low-risk user information; performing vector encoding on multiple low-risk user information to obtain multiple low-risk User vector; perform vector splicing and vector replacement on multiple low-risk user vectors, and construct the first normal user matrix, the second normal user matrix, and the abnormal user matrix; based on the first normal user matrix, the second normal user matrix, and the abnormal user matrix , train the preset pre-trained network until the loss function of the pre-trained network reaches the preset convergence condition, and obtain the risk feature extraction network. In this embodiment, an abnormal user matrix with high-risk features is constructed based on low-risk user information, thereby realizing the construction of a training sample set for a risk feature extraction network, reducing the difficulty of network training and improving the accuracy of network training.

Description

technical field [0001] The present application relates to the technical field of data processing, and specifically relates to a network training method, a risk user identification method, a device, an electronic device, and a storage medium. Background technique [0002] With the rapid development of Internet technology, more and more financial businesses conduct online transactions online. However, online transactions are accompanied by the risk of online financial fraud. Therefore, risk identification is an important means of guaranteeing the security of online financial services. important in prevention. [0003] At present, risk identification methods mainly use statistical models and machine learning models for risk assessment, such as support vector machines, random forests, and gradient boosting decision trees. With the continuous improvement of computer computing power, deep learning networks have also been applied to risk identification. The main purpose of risk i...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiment of the present application is to provide a network training method, risk user identification method, device, electronic equipment and storage medium, aiming to solve the problem of difficulty in current risk identification network training

Images