An Efficient Heuristic Search for Real-Time Frequent Pattern Mining

Real-time frequent pattern mining for business intelligence systems are currently in the focal area of research. In a number of areas of doing business, especially in the arena of supply chain management systems, real-time frequent pattern mining is in need. The need is being felt more due to the possibility of real-time knowledge discovery along with the gradual acceptance of technologies like RFID and grid computing and the huge amount of possibilities they promise for real-time decision making like supply-chain optimization. In this paper, we describe a domain-independent heuristic, h1-max and a heuristic search algorithm, BDFS(b)-h1-max for real-time frequent pattern mining, even using limited computer memory. Empirical evaluations show that the techniques being presented can make a fair estimation of the set of the probable frequent patterns and completes the search much faster than the existing algorithms.

[1]  Ulrich Güntzer,et al.  Mining Association Rules: Deriving a Superior Algorithm by Analyzing Today's Approaches , 2000, PKDD.

[2]  Mohammed J. Zaki,et al.  Theoretical Foundations of Associations Rules , 1998 .

[3]  Bart Goethals,et al.  A tight upper bound on the number of candidate patterns , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[4]  Bart Goethals,et al.  Memory issues in frequent itemset mining , 2004, SAC '04.

[5]  Ambuj Mahanti,et al.  Fast Frequent Pattern Mining in Real-Time , 2005, COMAD.

[6]  Salvatore J. Stolfo,et al.  Real time data mining-based intrusion detection , 2001, Proceedings DARPA Information Survivability Conference and Exposition II. DISCEX'01.

[7]  Ambuj Mahanti,et al.  An Efficient Technique for Frequent Pattern Mining in Real-Time Business Applications , 2005, Proceedings of the 38th Annual Hawaii International Conference on System Sciences.

[8]  Ulrich Güntzer,et al.  Algorithms for association rule mining — a general survey and comparison , 2000, SKDD.

[9]  Souren Paul,et al.  Data Mining, Group Memory, Group Decision Making: A Theoretical Framework , 2003, AMCIS.

[10]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[11]  Ron Kohavi,et al.  Applications of Data Mining to Electronic Commerce , 2000, Springer US.

[12]  Shoumen Datta.  Adapting Decisions, Optimizing Facts and Predicting Figures: Can Convergence of Concepts, Tools, Technologies and Standards Catalyze Innovation? , 2008 .

[13]  Bart Goethals,et al.  Survey on Frequent Pattern Mining , 2003 .

[14]  Ambuj Mahanti,et al.  Implementing BDFS(b) with diff-sets for real-time frequent pattern mining in dense datasets - first findings , 2005, International Workshop on Ubiquitous Data Management.

[15]  Roberto J. Bayardo,et al.  Efficiently mining long patterns from databases , 1998, SIGMOD '98.

[16]  Wee Keong Ng,et al.  Rapid association rule mining , 2001, CIKM '01.

[17]  Rajeev Motwani,et al.  Dynamic itemset counting and implication rules for market basket data , 1997, SIGMOD '97.

[18]  Wen-Yang Lin,et al.  CBW: an efficient algorithm for frequent itemset mining , 2004, 37th Annual Hawaii International Conference on System Sciences, 2004. Proceedings of the.

[19]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.