Web UR: Effective Techniques For Web Usage Mining And Recommender System

Abstract

The proliferation of internet along with the attractiveness of the web in recent years has made web mining as the research area of great magnitude. Web mining essentially has many advantages which make this technology attractive to researchers. The analysis of web users’ navigational pattern within a web site can provide useful information for server performance enhancements, restructuring a web site, direct marketing in e-commerce etc. This thesis discusses an effective clustering technique that groups user sessions, by modifying k-means algorithm. The proposed distance measures namely, the variable length vector distance, sequence alignment based distance measure, and hybrid sequence alignment measure are explained. The results obtained are validated. The present work attempts to solve the problem of predicting the next page to be accessed by the user based on the mining of web server logs, that maintains the information of users who access the web site. The proposed model yields good prediction accuracy compared to the existing methods like Markov model, association rule, ANN etc. A recommender system based on session collaborative filtering is proposed. The proposed recommender system is compared with a few other recommender systems by using precision and recall as metrics, and a better performance is observed. The outcome of prediction and recommender system could be used to suggest any structural modifications to the web site.