Enhanced Matrix based Frequent Accessed Pages Mining Algorithm

Abstract

In computer science and Web mining which is an interdisciplinary subfield of computer science, is the computational process of discovering patterns in web log files. The overall goal of the web mining process is to extract information from web log files and transform it into an understandable structure for further use. In Web mining, Apriori is a classic algorithm for learning association rules. This classical algorithm is inefficient due to so many scans of database and takes too much time to scan the database. In this paper we will build a method to obtain the frequent page-item set by using a different approach to the classical Apriori algorithm but based on it and applying the concept of transaction reduction and a new matrix method.