A Comparison of Frequent Itemsets Mining Algorithms
Main Article Content
Abstract
This research aimed to 1) study and compare algorithm used for searching Frequent Itemsets, which is one of the process of association rule mining; 2) explore procedure of algorithm method and techniques used for searching of frequent Itemsets; and 3) summarize which algorithm is the best fit with each type of data and which one has the best performance of executing time or with the least memory.
According to the findings of the study, they can be concluded that (1) each algorithm used for searching Frequent Itemsets has different advantages and disadvantages. Thus, each algorithm will be used to analyze different type of dataset. (2) The fastest algorithm for large dataset with high density were FP-Growth, Apriori and PrePost+. (3) The algorithm that consumes the shortest time for large dataset with low density was LCMFreq. (4) The algorithm that consumes the shortest time for small dataset with low density was LCMFreq. And (5) the algorithm that consumes the shortest time for small dataset with high density were PrePost+ and LCMFreq.
Article Details
References
Bases (VLDB’94), Santiago dc Chile, Morgan Kaufmann.
[2] M.J.Zaki, and K.Gouda. (2000). Generating non-redundant association rules. In 6th ACM SIGKDD Int’l Conf. Knoledge Discovery and Data Mining, August 2000.
[3] Deng Z. H., Lv S. L. (2014). Fast mining frequent itemsets using Nodesets. Expert systems with Applications, No.41(2014), 4505-4512.
[4] J.Han, J. Pei, and Y. Yin (2000). Mining Frequent Patterns Without Candidate Generation. Proc. ACM-SIGMOD Int’l Conf, Management of Data. pp. 1-12, May 2000.
[5] J. Pei, et.al. (2007). H-Mine: Fast and space-preserving frequent pattern mining in large databases. IIE transaction (2007) 39, 593-605.
[6] T. Uno, et.al. (2004). LCM ver. 2: Efficient mining algorithms for Frequent/Closed/Maximal Itemsets. National Institute of informatics 2-1-2 Hototsubashi, Chiyoda-ku,
Tokyo, Japan.
[7] Deng Z. H., and Lv S. L. (2015). PrePost+: An efficient N-lists based algorithm for mining frequent itemsets via Children-Parent Equivalence pruning. Expert systems with
Applications, No.42(2015), 5424-5432.
[8] C. Borgelt. (2005). Keeping Things Simple: Finding Frequent Item Sets by Recursive Elimination. University of Magdeburg, Germany.
[9] M.J.Zaki, and K.Gouda. (2001). Fast Vertical Mining Using Diffsets. Rensselaer Polytechnic Institute, Troy, NY, USA. Kyushu University, Fukuoka Japan.
[10] M.J. Zaki, and W.M. JR. (2014). Data Mining and Analysis Fundamental Concepts and Algorithms. Cambridge University Press. New York, NY 10013-2473, USA.
