User classification method and device based on random forest, equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence, and provides a user classification method and device based on a random forest, equipment and a storage medium. The method comprises the following steps: acquiring a training sample set, wherein training samples in the training sample set comprise user features and user classifications; clustering the training samples according to user features in the training sample set, and determining a sample subset according to a clustering result; respectively constructing corresponding classification trees according to the determined sample subsets; and determining a random forest according to the classification tree, and classifying to-be-classified users according to the random forest. Through the recommendation method, the construction efficiency of the random forest can be effectively improved, the similarity problem of classification trees can be effectively reduced, generation of a sample subset missing training samples is avoided, and the classification precision of the random forest is improved, so that user classification can be more accurately performed, and the efficiency of obtaining required products by users is improved.

Description

Technical field [0001] The present application belongs to the field of manual intelligence, in particular, to user classification methods, devices, equipment, and storage media based on random forests. Background technique [0002] When users use financial platforms or products to purchase web pages, the products in the platform or page are more, and people faced by each product will be different. In order to enable the user to efficiently find the product that matches the user, the user's category is typically identified, and the corresponding product is recommended based on the identified category. [0003] The currently commonly used method includes forming a training set in a way with a random forest algorithm, and determines a plurality of decision trees based on the training set formed, and a random forest consisting of multiple decision trees. However, due to the formation of training sets in a random forest algorithm, it is possible to extract duplicate data, as well as d...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides a random forest-based user classification method, device, device, and storage medium to solve the problem that the user classification method in the prior art has a large amount of calculation for user classification and inaccurate classification. The system's user classification accuracy is not high, which is not conducive to improving the efficiency of users to find the products they need

Images