Title: Extracting users pattern from web log data using decision tree and association rule

Authors: R. Krishnamoorthi, K.R. Suneetha

Addresses: Computer Science and Engineering, Bharathidasan Institute of Technology, Ann University-Tiruchirappalli, Tamil Nadu 620 024, India. ' Department of Computer Science and Engineering, Bangalore Institute of Technology, K.R. Road, V.V. Puram, Bengaluru, Karnataka 560 004, India

Abstract: Web usage mining is the task of applying data mining technique to discover usage patterns from web log file in order to understand and better serve the users navigating the web. Extracting users behaviour pattern is an important and challenging research topic of web usage mining. Analysing such patterns helps to determine the lifetime value of customers, cross marketing strategies across products and provides valuable information to improve the design of a website. This paper proposes an idea to find frequent patterns in two phases. In the first phase the pre-processed data is categorised into focused subsets using decision tree. In the second phase association rule is applied to find frequent pattern.

Keywords: web usage; data mining; decision trees; association rules; frequent patterns; world wide web; internet users; web logs; web navigation; behaviour patterns; lifetime values; customers; cross marketing; product marketing; website design; pre-processed data; categorisation; focused subsets; business performance; operations research; engineering management; ICOREM.

DOI: 10.1504/IJBPSCM.2010.036165

International Journal of Business Performance and Supply Chain Modelling, 2010 Vol.2 No.2, pp.125 - 133

Published online: 25 Oct 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article