Extracting Weighted Frequent Patterns from Web Log Data

Abstract

World Wide Web (WWW) today is growing into infinity and it has massive wealth of information. Mining the web is very essential in order to retrieve the necessary information for any user. Sequential Pattern Mining using weights involves applying data mining methods to large web log data to extract most weighted frequent patterns. In this paper, Sequential Pattern Mining is performed using weighted graph algorithm. This paper investigates algorithm, on the basis of various other algorithms which are designed to increase efficiency of mining. In this project we perform usage analysis which includes straightforward statistics, such as page access frequency, as well as more sophisticated forms of analysis, such as finding the common traversal paths through Website. The Weighted graph algorithm is used to find the frequent browsing patterns of the user. The experimental results show that the performance of the weighted graph algorithm is relatively better than GSP in spite of having complex calculations involving weights.
Key Words: Generalized Sequential Pattern, Graph Based Web, Sequential Pattern Mining, Weighted Graph Web Usage Mining