FP-GROWTH ALGORITHM BASED INCREMENTAL ASSOCIATION RULE MINING ALGORITHM FOR BIG DATA

Abstract

Discovering associations among huge collection of transactions is beneficial to rectify and to take appropriate decision made by decision makers. Discovering frequent itemsets is the key process in association rule mining. Since association rule mining process generates large number of rules which makes the algorithm inefficient is the biggest challenge for any and makes it difficult for the end users to comprehend the generated rules. The better idea is to use iterative technique to discover association rules. To overcome this problem, incremental updating of frequent itemsets is proposed in this paper. Proposed incremental data mining algorithm is based on FP-Growth and uses the concept of heap tree to address the issue of incremental updating of frequent itemsets. The proposed uses good tricks of FP-Growth, and significantly reduces the complexity. The experimental results show that the proposed algorithm reduces the execution time substantially and outperforms other algorithms.