Thesis (M.Sc.) - Cairo University - Institute of Statistical Studies and Research - Department of Computer and Information Science

Nowadays, users rely on the web for information, but the amount of data on the web is growing in an uncontrolled way; therefore, finding the relevant and required information is a hard task; this problem is referred to as information overload. Accordingly, web usage mining becomes an important research subject. Such a research area covers web-based personalized services, prediction of user near future intentions, adaptive websites, and customer profiling. Among the significant methods that can handle this problem effectively are recommender systems, which are alternative, user- central approaches. They help users by giving them personalized recommendations. These systems rely either on ratings the various items submitted by users and their own behaviors; or rely on existing approaches to content and collaborative filtering to generate a customized recommendations. Web page prediction is strongly limited by the nature of web logs, the intrinsic complexity of the problem and the tight efficiency requirements. This work proposes two hybrid page ranking models based on web usage mining technique by exploiting session data of users, to enhance the recommendations of the next candidate web page to be accessed. Both models represents a combination between two page ranking approaches. The first one computes the frequency ratio, which indicates the number of occurrences of each page in the search result. On the other hand, the second approach computes the coverage ratio from similar behavior patterns. As a result of the first proposed approach, a set of candidate pages are ranked and the page with highest rate is recommended

Issued also as CD