Prediction of User Browsing Behavior Using Web Log Data

Abstract: Web usage mining is one of the areas of data mining where it not only deals with the analysis of web data but also discovers frequent patterns from them to improve the web based applications. It consists of three phases preprocessing, pattern discovery and pattern analysis. After the completion of these phases, the user can find interesting and frequent patterns whatever he/she wants to be need with the use of these information for specific needs. In other words, one can say that it deals with the extracting of useful information and find interesting usage patterns from web server, proxy server or web clients. In this paper, combined approach of Ant Colony Optimization and DBSCAN is used to get effective Association Rules to predict the customer�s browsing behavior .Moreover, the aim is to find the user�s behavior with less error rate in prediction.

Keywords: Web mining, Web log, Pattern discovery, Clustering, User�s browsing behavior.