Mining Users’ Preference Similarities in E-commerce Systems Based on Webpage Navigation Logs

International journal of computers, communications and control

Ping Li¹  Shaozhong Zhang²  Chunxue Wu³  Xinwu Yu⁴  Haidong Zhong⁵ 

[1] College of Biological and Environmental Sciences,Zhejiang Wanli UniversityNo. 8 South Qianhu Rd., Ningbo, Zhejiang, 315100,P. R. China,;School of Electronic and Computer Science,Zhejiang Wanli UniversityNo. 8 South Qianhu Rd., Ningbo, Zhejiang, 315100,P. R. China,;School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and TechnologyNo. 516 Jun Gong Road, Shanghai 200093,P. R. China,;The Information Center,Zhejiang Wanli UniversityNo. 8 South Qianhu Rd., Ningbo, Zhejiang, 315100,P. R. China,;Zhejiang Wanli University, Ningbo, Zhejiang, P.R.China

关键词: web browsing history mining;    e-commerce;    preference;    recommendation. Copyright ©;   

DOI  :  10.15837/ijccc.2017.5.2565

学科分类：计算机科学（综合）

来源: Universitatea Agora

【 摘 要 】

Mining users’ preference patterns in e-commerce systems is a fertile area for a great many application directions, such as shopping intention analysis, prediction and personalized recommendation. The web page navigation logs contain much potentially useful information, and provide opportunities for understanding the correlation between users’ browsing patterns and what they want to buy. In this article, we propose a web browsing history mining based user preference discovery method for e-commerce systems. First of all, a user-browsing-history-hierarchical-presentationgraph to established to model the web browsing histories of an individual in common e-commerce systems, and secondly an interested web page detection algorithm is designed to extract users’ preference. Finally, a new method called UPSAWBH (User Preference Similarity Calculation Algorithm Based on Web Browsing History), which measure the level of users’ preference similarity on the basis of their web page click patterns, is put forward. In the proposed UPSAWBH, we take two factors into account: 1) the number of shared web page click sequence, and 2) the property of the clicked web page that reflects users’ shopping preference in e-commerce systems. We conduct experiments on real dataset, which is extracted from the server of our self-developed e-commerce system. The results indicate a good effectiveness of the proposed approach.

【 授权许可】

Free