Research on Personalized Recommendation System for e-Commerce based on Web Log Mining and User Browsing Behaviors
Web server log files and customers transaction data can be mined meaningful user access patterns to anticipate potential customers so as to enable personalized information services and targeted e-commerce activities. The paper bases on Clustering technology of Web Mining to provide a personalized solution to implement an e-commerce recommendation system. The paper introduces the UserlD-URL associated matrix according to log information, We calculate UserlD-URL associated matrix and Distance matrix to cluster users into user groups. Clustering algorithm is simple and easy to achieve due to improve the nature of algorithm, no such the candidate set of Apriori algorithm in association rules. The system can recommend the goods which other users of this cluster browse to the user and achieve the objective of personalized goods recommendation.
web log mining e-commerce user cluster
Xia Min-jie Zhang Jin-ge
Department of Computer Science Zhongyuan Institute of Technology ZhengZhou,China School of Management Henan University of Technology ZhengZhou,China
国际会议
太原
英文
408-411
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）