User data processing method and device and electronic equipment

Abstract

The invention relates to a user data processing method and device, electronic equipment and a computer readable medium. The method comprises the steps of obtaining first user data, wherein the first user data comprises basic data and behavior data; determining a label for the first user data based on the basic data and the behavior data, wherein the label comprises a positive label and a negativelabel; training the generative adversarial network model through the first user data with the label to obtain a sample generation model; generating second user data with a negative label through the sample generation model; and generating sample data through the second user data and the first user data. According to the user data processing method and device, the electronic equipment and the computer readable medium, the sample overfitting phenomenon in the machine learning model can be reduced, and the training efficiency of the machine learning model and the accuracy of model calculation areimproved.

Description

technical field [0001] The present disclosure relates to the field of computer information processing, and in particular, to a user data processing method, device, electronic equipment, and computer-readable medium. Background technique [0002] Unbalanced samples may lead to failure of some machine learning models, such as logistic regression, which is not suitable for dealing with class imbalance problems, such as logistic regression in fraud detection problems, because most of the samples are normal samples, and there are few fraud samples , the logistic regression algorithm will tend to judge most samples as normal samples, which can achieve a high accuracy rate, but cannot achieve a high recall rate. Usually, the machine learning model needs to learn positive samples (good samples) and negative samples (bad samples). The positive samples are the samples corresponding to the correctly classified categories. In principle, the negative samples can select any other samples ...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present disclosure provides a user data processing method, device, electronic device, and computer-readable medium, which can solve the problem of unbalanced number of positive and negative samples in training samples during machine learning model training, and reduce the number of machine learning models. Medium sample overfitting phenomenon, improve machine learning model training efficiency and model calculation accuracy

Images