Preprocessing of Web Usage Data for Application in Prefetching to Reduce Web Latency

-The Popularity of Web resulted in heavy traffic in the Internet. This intense increase in internet traffic has caused significant increase in the user perceived latency. In order to reduce this effectively. Prefetching techniques are found to be best suitable. Prefetching technique is motivated by the fact that, in general, once a user goes to a Web site; he/she generally browses around for several pages before leaving for another site. Since the user follows hyperlinks upon his/her interests, it is likely that links are not followed uniformly. It is possible to either predict each user’s interest using cookies or mine a consensus of interests (i.e., generally what pages will be requested after the current page) with some confidence from access log files recorded by the Web server. This information not only is valuable for the Web administrator to eliminate uninterested pages, or balance load among the servers, but also can help to improve Web-browsing time. In this paper, we propose a comprehensive preprocessing methodology as a prerequisite and first stage for Prefetching application, which has four steps: Data Cleaning, Identification of users & Sessions, and finally the Data Formatting and Summarization. An attempt is made to reduce the quantity of the WUD and thereby improve the quality of WUD for effective use in Prefetching application. Several heuristics have been proposed for cleaning the WUD which is then aggregated and recorded in the relational data model. To validate the efficiency of our preprocessing methodology, several experiments were conducted log files on three different web sites: Academic, Research, Commercial and the results shows that our methodology reduces the Web access log files size down to 72-83% of the initial size and offer richer logs that are structured for application in Prefetching. Index Term-Preprocessing, Prefetching, Web Usage Data,