Vertical Pattern Mining Algorithm for Multiple Support Thresholds

• Published in: Procedia computer science Vol. 112; pp. 417 - 426
• Main Authors: Darrab, Sadeq, Ergenc, Belgin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 2017
• Subjects: frequent pattern mining; multiple support thresholds; pattern growth tree; vertical mining; multiple support thresholds; pattern growth tree; vertical mining; frequent pattern mining
• ISSN: 1877-0509; 1877-0509
• DOI: 10.1016/j.procs.2017.08.051

Frequent pattern mining is an important task in discovering hidden items that co-occur (itemset) more than a predefined threshold in a database. Mining frequent itemsets has drawn attention although rarely occurring ones might have more interesting insights. In existing studies, to find these interesting patterns (rare itemsets), user defined single threshold should be set low enough but this results in generation of huge amount of redundant itemsets. We present Multiple Item Support-eclat; MIS-eclat algorithm, to mine frequent patterns including rare itemsets under multiple support thresholds (MIS) by utilizing a vertical representation of data. We compare MIS-eclat to our previous tree based algorithm, MISFP-growth28 and another recent algorithm, CFP-growth++22 in terms of execution time, memory usage and scalability on both sparse and dense databases. Experimental results reveal that MIS-eclat and MISFP-growth outperform CFP-growth++ in terms of execution time, memory usage and scalability.