An Efficient Frequent Pattern Mining Algorithm to Find the Existence of K-Selective Interesting Patterns in Large Dataset Using SIFPMM

Association rule mining in huge database is one of most popular data exploration technique for business decision makers. Discovering frequent item set is the fundamental process in association rule mining. Several algorithms were introduced in the literature to find frequent patterns. Those algorithms discover all combinations of frequent item sets for a given minimum support threshold. But sometimes, it is needed to discover the frequency of specified few frequent item sets found in last dataset to check its existence in current dataset to improve the strategy of future business. Among all, Apriori and FP-tree are the most common techniques for discovering frequent item sets. Apriori finds all significant frequent item sets using candidate generation with specified minimum support threshold and several number of database scans. FP-tree finds all significant frequent item sets using specified minimum support threshold with two database scans. This proposed SIFPMM (Selective Item sets Frequent Pattern Mining Method) finds frequency of selective item sets using Existence Count Table (ECT) with one database scan. Experimental results of SIFPMM shows that this method outperforms than Apriori and FP-tree.