Appling Association Rule to Web Prediction

With the rapid development of the Internet, Web log mining, which is used to find useful information about users from Web log files, has become a heat issue of research. The aim of association rule mining is to find interesting and useful patterns in a transaction base. This paper makes use of variable precision rough set theory to retrieve the associated rules from Web log and applies the rules to the prediction of users' behaviors. Experiments indicate that the prediction precision is better than those existing methods