Evolutionary Biclustering of Clickstream Data

Abstract

Biclustering is a two way clustering approach involving simultaneous clustering along two dimensions of the data matrix. Finding biclusters of web objects (i.e. web users and web pages) is an emerging topic in the context of web usage mining. It overcomes the problem associated with traditional clustering methods by allowing automatic discovery of browsing pattern based on a subset of attributes. A coherent bicluster of clickstream data is a local browsing pattern such that users in bicluster exhibit correlated browsing pattern through a subset of pages of a web site. This paper proposed a new application of biclustering to web data using a combination of heuristics and meta-heuristics such as K-means, Greedy Search Procedure and Genetic Algorithms to identify the coherent browsing pattern. Experiment is conducted on the benchmark clickstream msnbc dataset from UCI repository. Results demonstrate the efficiency and beneficial outcome of the proposed method by correlating the users and pages of a web site in high degree.This approach shows excellent performance at finding high degree of overlapped coherent biclusters from web data.