期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2012
卷号：2
期号：4
出版社：S.S. Mishra
摘要：A new algorithm called Rapid Association Rule Mining (RARM) is proposed to further push the speed barrier so that association rule mining can be performed more efficiently in electronic commerce. To achieve large speed-ups even at low support, thresholds, RARM constructs a new data structure called Support-Ordered Trie Item set (SOTrieIT). This trie-like tree structure stores the support counts of all 1-itemsets and 2-itemsets in the database. RARM uses SOTrieIT to quickly discover large 1-itemsets and 2-itemsets without scanning the database. The need to generate candidate 1-itemsets and 2-itemsets constitutes the main bottleneck in large item set generation. Therefore, by eliminating this step, RARM achieves significant speed -ups even though subsequently, it also applies the Apriori algorithm to obtain larger-sized item sets.
