Mining of Users Access Behaviour for Frequent Sequential Pattern From Web Logs

Sequential Pattern mining is the process of applying data mining techniques to asequential database for the purposes of discovering the correlation relationships that existamong an ordered list of events. The task of discovering frequent sequences ischallenging, because the algorithm needs to process a combinatorially explosive numberof possible sequences. Discovering hidden information from Web log data is called Webusage mining. One common usage in web applications is the mining of users’ accessbehaviour for the purpose of predicting and hence pre-fetching the web pages that theuser is likely to visit. The aim of discovering frequent Sequential patterns in Web log datais to obtain information about the access behaviour of the users.Finding Frequent Sequential Pattern (FSP) is an important problem in web usagemining. In this paper, we explore a new frequent sequence pattern technique calledAWAPT (Adaptive Web Access Pattern Tree), for FSP mining. An AWAPT combinesSuffix tree and Prefix tree for efficient storage of all the sequences that contain a givenitem. It eliminates recursive reconstruction of intermediate WAP tree during the miningby assigning the binary codes to each node in the WAP Tree. Web access pattern tree(WAP-tree) mining is a sequential pattern mining technique for web log accesssequences, which first stores the original web access sequence database(WASD) on aprefix tree, similar to the frequent pattern tree (FP-tree) for storing non-sequential data.WAP-tree algorithm then, mines the frequent sequences from the WAP-tree byrecursively re-constructing intermediate trees, starting with suffix sequences and endingwith prefix sequences. An attempt has been made to AWAPT approach for improvingefficiency. AWAPT totally eliminates the need to engage in numerous reconstructions ofintermediate WAP-trees during mining and considerably reduces execution time.