IPACT: Improved Web Page Recommendation System Using Profile Aggregation Based On Clustering of Transactions
- 1 Department of Computer Science, Faculty of Computer Science and Information Technology, University Putra Malaysia, 43400 UPM Serdang, Selangor Darul Ehsan, Malaysia
Abstract
Problem statement: Recently, Web usage mining techniques have been widely used to build recommendation systems especially for anonymous users. Approach: Assigning the current user to the best web navigation profile with similar navigation activities will improve the ability of the prediction engine to produce a recommendation list then introduce it to the user. This study presents iPACT an improved recommendation system using Profile Aggregation based on Clustering of Transactions (PACT). Results: iPACT shows better prediction accuracy than the previous methods PACT and Hypergraph. Conclusion: The users’ interests change over time; hence an incremental and adaptive web navigation profiling is a key feature for the future works.
DOI: https://doi.org/10.3844/ajassp.2011.277.283
Copyright: © 2011 Yahya AlMurtadha, Md. Nasir Bin Sulaiman, Norwati Mustapha and Nur Izura Udzir. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- 3,993 Views
- 4,070 Downloads
- 21 Citations
Download
Keywords
- Recommender systems
- web usage mining
- web navigation profiles
- prediction engine
- profile aggregation
- Collaborative filtering (CF)
- Case-Based Reasoning Plan Recognition (CBRPR)
- hybrid filtering
- Web Usage Mining (WUM)
- Longest common Sequences algorithm (LCS)