Integrating Markov Model with Clustering for Predicting Web Page Accesses

Faten Khalil, Doctoral Student, Department of Mathematics & Computing, University of Southern Queensland, Toowoomba, Australia, Email: khalil@usq.edu.au

Jiuyong Li, Associate Professor, School of Computer and Information Science, University of South Australia, Mawson Lakes, Australia, Email: Jiuyong.Li@unisa.edu.au

Hua Wang, Senior Lecturer, Department of Mathematics and Computing, University of Southern Queensland, Toowoomba, Australia, Email: wang@usq.edu.au

Keywords

Markov model, clustering, Web page prediction, k-means, distance measures.

Abstract

Predicting the next page to be accessed by Web users has attracted a large amount of research work lately due to the positive impact of such prediction on different areas of Web based applications. Major techniques applied for this intention are Markov model and clustering. Low order Markov models are coupled with low accuracy, whereas high order Markov models are associated with high state space complexity. On the other hand, clustering methods are unsupervised methods, and normally are not used for classification directly. This paper involves incorporating clustering with low order Markov model techniques. The pre-processed data is divided into meaningful clusters then the clusters are used as training data while performing 2^nd order Markov model techniques. Different distance measures of k-means clustering algorithm are examined in order to find an optimal one. Experiments reveal that incorporating clustering of Web documents according to Web services with low order Markov model improves the web page prediction accuracy.