Potential customer mining and recommending method

Abstract

The invention provides a potential customer mining and recommending method, which comprises the following steps of obtaining personal information and social activity information of a user from a social platform, fusing the personal information and the social activity information with locally stored user shopping records, and carrying out data cleaning and screening to obtain data for training andtesting a potential customer classification model; constructing a user portrait according to the personal information, the social record and the shopping record of the user, processing the social record and the shopping record of the user into a feature vector form which can be used by a model, then training a user interest prediction model, and dividing the users into potential customers and passers-by; and finally, identifying and providing more targeted commodity pages for the potential customers according to the interests of the potential customers. According to the method, the interest ofthe user can be judged while the user is accurately classified; corresponding products are displayed or precise advertisement putting is implemented according to the interest judgement of the users,so that conversion of potential customers is realized; targeted recommendation can also be provided for old customers, and customer stickiness is improved.

Description

technical field [0001] The invention relates to the technical field of customer mining methods, in particular to a potential customer mining and recommendation method. Background technique [0002] In this increasingly competitive e-commerce era, on the basis of existing customers, by continuously expanding new customers and increasing the total number of customers and customer viscosity, enterprises can obtain more economic benefits and market competitive advantages. More and more businesses Selling goods through online shopping malls, in the process of promotion by merchants, a problem that is of great concern is: how to tap potential customers based on the information of customers that the merchant currently has (such as customer age, gender, home address, etc.) , to achieve precise customer contact. [0003] Existing potential customer mining technologies are mainly divided into two types based on user attribute tags and based on user browsing behavior. [0004] Potent...

AI Technical Summary

Problems solved by technology

[0006] However, the existing technology only uses information such as customer attribute labels and behavior records stored inside the e-commerce website. For new users who log in to the website, there is a problem of low mining accuracy caused by too little user information, and it is difficult to accurately judge user interests. Unable to effectively guide enterprises to formulate corresponding strategies to achieve customer conversion

Images