Research on the implementation of teaching consumer online behavior pattern recognition technology in higher vocational college e-commerce education

Abstract Residents’ consumption level is increasing, e-commerce vocational education has become an increasingly important field of education, how to realize customer value-added has become the focus of attention of e-commerce platforms. In this paper, we use the improved dynamic RFM customer segmentation model based on K-Means clustering to segment e-commerce consumers, to accurately portray the changes of e-commerce consumers’ loyalty and the transfer characteristics between e-commerce consumers’ groups, to achieve the identification of consumers’ online behavioral patterns. The RFM model classifies users into four categories: important value, general value, focus on development, and focus on retention. The important value users of Product B have high activity and contribution, but very low loyalty, which indicates that there may be group purchasing behaviors in this group, and the e-commerce operator of Product B can focus on serving this type of customers. After implementing the technique in teaching, the six dimensions of the experimental class C about teaching effectiveness are better than the other two classes, which shows that the technique provides a new perspective for the improvement of teaching effectiveness in e-commerce education.