Discovering Strong Meta Association Rules Using Bees Swarm Optimization

For several applications, association rule mining produces an extremely large number of rules. Analyzing a large number of rules can be very time-consuming for users. Therefore, eliminating irrelevant association rules is necessary. This paper addresses this problem by proposing an efficient approach based on the concept of meta association rules. The algorithm first discovers dependencies between association rules called meta association rules. Then, these dependencies are used to eliminate association rules that can be replaced by a more general rule. Because the set of meta-rules can be very large, a bee swarm optimization approach is applied to quickly extract the strongest meta-rules. The approach has been applied on a synthetic dataset and compared with a state-of-the-art algorithm. Results are promising in terms of number of rules found and their quality.

[1]  Wilhelmiina Hämäläinen,et al.  StatApriori: an efficient algorithm for searching statistically significant association rules , 2010, Knowledge and Information Systems.

[2]  Yves Bastide,et al.  Intelligent Structuring and Reducing of Association Rules with Formal Concept Analysis , 2001, KI/ÖGAI.

[3]  A. Chemchem,et al.  Organizing association rules with meta-rules using knowledge clustering , 2013, 2013 11th International Symposium on Programming and Systems (ISPS).

[4]  Djamel Djenouri,et al.  Data Mining-Based Decomposition for Solving the MAXSAT Problem: Toward a New Approach , 2017, IEEE Intelligent Systems.

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

[6]  Wynne Hsu,et al.  Pruning and summarizing the discovered associations , 1999, KDD '99.

[7]  Habiba Drias,et al.  Hybrid Intelligent Method for Association Rules Mining Using Multiple Strategies , 2014, Int. J. Appl. Metaheuristic Comput..

[8]  Habiba Drias,et al.  Pruning irrelevant association rules using knowledge mining , 2014, Int. J. Bus. Intell. Data Min..

[9]  Kweku-Muata Osei-Bryson,et al.  Using ontologies to facilitate post-processing of association rules by domain experts , 2011, Inf. Sci..

[10]  Fabrice Guillet,et al.  Knowledge-Based Interactive Postmining of Association Rules Using Ontologies , 2010, IEEE Transactions on Knowledge and Data Engineering.

[11]  Djamel Djenouri,et al.  Diversification Heuristics in Bees Swarm Optimization for Association Rules Mining , 2017, PAKDD.

[12]  Smaine Mazouzi,et al.  Penguin Search Optimisation Algorithm for Finding Optimal Spaced Seeds , 2015, Int. J. Softw. Sci. Comput. Intell..

[13]  Toshihiko Watanabe.  An improvement of fuzzy association rules mining algorithm based on redundacy of rules , 2010 .

[14]  Nadia Nouali-Taboudjemat,et al.  An efficient measure for evaluating association rules , 2014, 2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[15]  Mohammed J. Zaki.  Generating non-redundant association rules , 2000, KDD '00.

[16]  Philippe Fournier-Viger,et al.  Fast and effective cluster-based information retrieval using frequent closed itemsets , 2018, Inf. Sci..

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

[18]  Jian Pei,et al.  Mining frequent patterns without candidate generation , 2000, SIGMOD 2000.

[19]  Laks V. S. Lakshmanan,et al.  Exploratory mining and pruning optimizations of constrained associations rules , 1998, SIGMOD '98.

[20]  Ke Wang,et al.  Visually Aided Exploration of Interesting Association Rules , 1999, PAKDD.

[21]  Habiba Drias,et al.  Bees swarm optimisation using multiple strategies for association rule mining , 2014, Int. J. Bio Inspired Comput..

[22]  Abdelaziz Berrado,et al.  Using metarules to organize and group discovered association rules , 2006, Data Mining and Knowledge Discovery.

[23]  Philippe Fournier-Viger,et al.  Extracting useful knowledge from event logs: A frequent itemset mining approach , 2018, Knowl. Based Syst..

[24]  Ana Cristina Bicharra Garcia,et al.  Association Rule Visualization and Pruning through Response-Style Data Organization and Clustering , 2012, IBERAMIA.

[25]  Youcef Djenouri,et al.  Bees swarm optimization guided by data mining techniques for document information retrieval , 2018, Expert Syst. Appl..

[26]  Sohag Kabir,et al.  Penguins Search Optimisation Algorithm for Association Rules Mining , 2016, J. Comput. Inf. Technol..

[27]  Djamel Djenouri,et al.  Bee swarm optimization for solving the MAXSAT problem using prior knowledge , 2017, Soft Computing.

[28]  Zoran Mitrovic,et al.  Discovering Interesting Association Rules in the Web Log Usage Data , 2010 .

[29]  Djamel Djenouri,et al.  SS-FIM: Single Scan for Frequent Itemsets Mining in Transactional Databases , 2017, PAKDD.