Sequence Pattern Mining for Web Logs

Interestingness measures play an important role in finding frequently occurring patterns, regardless of the kind of patterns being mined. In this work, we propose variation to the AprioriALL Algorithm, which is commonly used for the sequence pattern mining. The proposed variation adds up the measure interest during every step of candidate generation to reduce the number of candidates thus resulting in reduced time and space cost. The proposed algorithm derives the patterns which are qualified and more of interest to the user. The algorithm, by using the interest, measure limits the size the candidates set whenever it is produced by giving the user more importance to get the desired patterns.

[1]  Johannes Gehrke,et al.  Sequential PAttern mining using a bitmap representation , 2002, KDD.

[2]  Jaideep Srivastava,et al.  Selecting the right interestingness measure for association patterns , 2002, KDD.

[3]  Heikki Mannila,et al.  Finding interesting rules from large sets of discovered association rules , 1994, CIKM '94.

[4]  Philip S. Yu,et al.  A new framework for itemset generation , 1998, PODS '98.

[5]  Qiming Chen,et al.  PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth , 2001, Proceedings 17th International Conference on Data Engineering.

[6]  Xiangji Huang,et al.  Comparison of interestingness functions for learning web usage patterns , 2002, CIKM '02.

[7]  Ramakrishnan Srikant,et al.  Mining sequential patterns , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[8]  Ramakrishnan Srikant,et al.  Mining Sequential Patterns: Generalizations and Performance Improvements , 1996, EDBT.

[9]  Sunita Sarawagi.  Sequence data mining techniques and applications , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).