A Support-Ordered Trie for Fast Frequent Itemset Discovery
IEEE Transactions on Knowledge and Data Engineering
A design and implementation of a web server log file analyzer
WSEAS Transactions on Information Science and Applications
Speeding up web access using weighted association rules
PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence
| Hi-index | 0.00 |
The rising popularity of electronic commerce makes datamining an indispensable technology for business competitiveness.The World Wide Web provides abundant raw datain the form of web access logs, web transaction logs andweb user profiles. Without data mining tools, it is impossibleto make any sense of such massive data. In this paper,we focus on web usage mining because it deals most appropriatelywith understanding user behavioral patterns whichis the key to successful customer relationship management.Previous work deals separately on specific issues of web usagemining and make assumptions without taking a holisticview and thus, have limited practical applicability. We formulatea novel and more holistic version of web usage min-ingtermed TRAnsactionized LOgfile Mining (TRALOM)to effectively and correctly identify transactions as well asto mine useful knowledge from web access logs. We alsointroduce a new data structure, called the Webrie, to efficientlyhold useful preprocessed data so that TRALOM canbe done in an online and incremental fashion. Experimentsconducted on real web server logs verify the usefulness andpracticality of our proposed techniques.