A New Web Usage Mining Approach for Next Page Access Prediction

To engage users of a website at an early stage of surfing, a novel web access recommendation system is essential. In this paper, a new web usage mining approach is proposed to predict next page access. It is proposed to identify similar access patterns from web log using pair-wise nearest neighbor based clustering and then sequential pattern mining is done on these patterns to determine next page accesses. The tightness of clusters is improved by setting similarity threshold while forming clusters. In traditional recommendation models, clustering by non-sequential data decreases recommendation accuracy. In this paper it is proposed to integrate Markov model based sequential pattern mining with clustering. A variant of Markov model called dynamic support pruned all k order Markov model is proposed in order to reduce state space complexity. Mining the web access log of users of similar interest provides good recommendation accuracy. Hence, the proposed model provides accurate recommendations with reduced state space complexity.