Web Usage Mining with Variable Precision Rough Set Approach

The rich Web information makes the Web users to be drowned in the huge Web data. This paper proposes a new navigation approach termed WUMVPRSM (Web Usage Mining based on Variable Precision Rough Set Model) for Web users browsing a website. First, Log training data sets are reduced using attribute reduction module by rough set. And then, a reduced Log data set is trained to create a rough classifier. The final classification result for identifying Web user is obtained according to rough decision rules. Simulation results illustrate the efficiency of the proposed approaches.