Stock recommendation method and server

Abstract

The invention discloses a stock recommendation method and a server. The method includes: determining a high-profit customer according to the stock transaction data of a first preset number of customers within a preset time by the control server; The first preset number of customers is used as the training set, and some ordinary trading users are randomly selected as the test set, and the first preset number of customers are classified to form the second preset number of data categories; The rule is to use the second preset number of data classes as a training set, to discriminate the classes of ordinary users, and to match with the second preset number of data classes. The present invention can accurately push stocks of different styles to ordinary users who prefer corresponding styles.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a stock recommendation method and server. Background technique [0002] With the increasingly fierce competition in the domestic securities market, the business model of securities companies has gradually changed from "technology-driven" to "service-driven". In the face of diversified, hierarchical and personalized customer needs, mass marketing and services have lost their advantages. The concept of insight marketing and personalized marketing based on in-depth data analysis of customer needs has gradually been accepted by major securities firms, and they are eager to Reduce marketing costs and improve marketing efficiency by mining value from data. At present, the industry also uses historical transaction data to recommend stocks to users, but this existing recommendation method usually uses a single index such as yield rate and winning rate for stock screening, the accuracy...

AI Technical Summary

Problems solved by technology

At present, the industry also uses historical transaction data to recommend stocks to users, but this existing recommendation method usually uses a single index such as yield rate and winning rate for stock screening, the accuracy rate is low, and the user's transaction is not fully considered. Habits (for example, preference for selling high and buying low, preference for short-term trading, preference for small-cap stocks, etc.)

Images