Automatic Recommendation of Web Pages for Online Users Using Web Usage Mining

Now a days, user rely on the web for information, but the currently available search engines often gives a long list of results, much of which are not always relevant to the user´s requirement. Since a user has a specific goal when searching for information, personalized search may provide the results that accurately satisfy user´s specific goal and intent for the search. Personalization of web search is to retrieve information according to user´s interests which may be inferred from user´s action, browsed documents or past query history etc. A real problem before web master of a website is to match the user needs and keep their attention focused to his website. In this paper, we propose a web recommendation approach which recommends user a list of pages based upon user´s historic pattern and a list of web pages which have not been visited yet. This approach results in the improvement in the accuracy of the pages presented to the users.