Sample prediction method and device based on federation training and storage medium

Abstract

The invention discloses a sample prediction method based on federation training, comprises the following steps: federating two aligned training samples by using an XGboost algorithm to construct a gradient lifting tree model, wherein the gradient lifting tree model comprises a plurality of regression trees, and a split node of the regression tree corresponds to a feature of the training sample; based on the gradient lifting tree model, jointly predicting the sample to be predicted to determine a sample class of the sample to be predicted or to obtain a prediction score of the sample to be predicted. The invention also discloses a sample prediction device based on federation training and a computer-readable storage medium. The invention realizes federated training modeling by using trainingsamples of different data parties, and further realizes sample prediction based on the established model.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a federated training-based sample prediction method, device and computer-readable storage medium. Background technique [0002] In the current information age, some behaviors of people can be expressed through data, such as consumption behavior, which leads to big data analysis, and builds corresponding behavior analysis models through machine learning, and then can classify people's behavior or based on user behavior features to predict. [0003] In existing machine learning techniques, one party usually trains the sample data independently, that is, unilateral modeling. At the same time, based on the established mathematical model, the features with relatively high importance in the sample feature set can be determined. However, in many cross-domain big data analysis scenarios, for example, users have both consumption behavior and lending behavior, and the us...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a sample prediction method, device and computer-readable storage medium based on federated training, aiming to solve the problem that the existing technology cannot realize the joint training of sample data from different data providers, and thus cannot realize the joint participation of both parties Technical Issues in Modeling and Sample Prediction

Images