Consumers’ Purchase Behavior Preference in E-Commerce Platform Based on Data Mining Algorithm


Authors: Wenjun Yang, Jia Guo

Abstract: E-commerce platform can recommend products to users by analyzing consumers’ purchase behavior preference. In the clustering process, the existing methods of purchasing behavior preference analysis are easy to fall into the local optimal problem, which makes the results of preference analysis inaccurate. Therefore, this paper proposes a method of consumer purchasing behavior preference analysis on e-commerce platform based on data mining algorithm. Create e-commerce platform user portrait template with consumer data records, select attribute variables and set value range. This paper uses data mining algorithm to extract the purchase behavior characteristics of user portrait template, takes the characteristics as the clustering analysis object, designs the clustering algorithm of consumer purchase behavior, and grasps the common points of group behavior. On this basis, the model of consumer purchase behavior preference is established to predict and evaluate the behavior preference. The experimental results show that the accuracy rate of this method is 91.74%, the recall rate is 88.67%, and the F1 value is 90.17%, which are higher than the existing methods, and can provide consumers with more satisfactory product information push.

Pages: 603-609

DOI: 10.46300/9106.2022.16.75

International Journal of Circuits, Systems and Signal Processing, E-ISSN: 1998-4464, Volume 16, 2022, Art. #75

PDF DOI XML

Certification