Masomeh khabazfazli - Department of computer, Science and Research branch, Islamic Azad University, Ardabil, Iran
Ali Harounabadi - Department of Computer Science, Islamic Azad University, Central Tehran Branch, Tehran, Iran
Shahram Jamali - Computer Engineering Department, University of Mohaghegh Ardabil, Ardabil, Iran

Upon integration of internet and its various applications andincrease of internet pages, access to information in searchengines becomes difficult. To solve this problem, web pagerecommendation systems are used. In this paper, recommenderengine are improved and web usage mining methods are used forthis purpose. In recommendation system, clustering was used forclassification of users’ behavior. In fact, we implemented usagemining operation on the data related to each user for making itsmovement pattern. Then, web pages were recommended usingneural network and markov model. So, performance ofrecommendation engine was improved using user’s movementpatterns and clustering and neural network and Markov model,and obtained better results than other methods. To predict thedata recovery quality on web, two factors including accuracy andcoverage were used

Web Page Recommendation, Web Mining, WebUsage Mining, Clustering