Incremental and interactive mining of web traversal patterns
Information Sciences: an International Journal
Efficient approach for interactively mining web traversal patterns
ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part II
Hi-index | 0.00 |
Web usage mining is the process of extractinginteresting patterns from web logs. This paperproposes an IPA (Integrating Path traversal patternsand Association rules) model for web usage mining inthe EC (Electronic Commerce) environment. The IPAmodel takes both the traveling and purchasingbehaviors of customers into consideration at the sametime to overcome the disadvantages of the pureassociation rule mining and pure path traversalpattern mining. The IPA model considers not onlyuser traversal forward information but also backwardinformation. Besides, web structure is also used inthis paper to prune unnecessary candidates.Especially, the IPA model allows the noise exist in webtransactions. The experimental results show that theIPA model can correctly capture the user's traversingand purchasing behaviors.