Selecting type of clusters that are most appropriate for capturing overlapping interests of different types of users in personalization tasks using Web Usage Mining

Clustering is one of the most important phase of the web personalization, so selecting proper types of cluster to justifythe user interest for creating user profile is again very important.In this paper, we address the problem, which types of cluster aremost appropriate for personalization task and how to identify and make use of such cluster in personalization. If user interest is overlapped amongst the cluster then which one or others are most appropriate for users likes. We have to find the parameters that are required to select the clusters that potentially capture overlapping interests of different types of users.