Parallelizing Apriori Algorithm using Open MP

Nilesh Sadashivrao Korde; Shailendra W. Shende

doi:10.37591/rtpc.v1i1.43

Abstract

An Association rule mining used for finding frequent item sets thus generating rules from the frequent item sets. Finding frequent itemsets is more expensive in terms of CPU power and computing resources utilization. Apriori Algorithm is used for high dimensionality on massively large data sets. Parallelism reduces the time required for serial processing. Parallel computing can be applied for mining of association rules. Parallel apriori algorithm focus on parallelizing the process of frequent item set discovery. The computation of frequent item sets mainly consists of creating the candidates and counting them. The parallel frequent itemsets mining algorithms addresses the issue of distributing the candidates among processors such that their counting and creation is effectively parallelized. In this paper we have Implemented Apriori Algorithm in serial and parallel on a quad core processor and compared their performance with respect to time.Keywords: Multi-core, parallelism, Apriori, data mining, open MP