Exploiting Parallelism in Association Rule Mining Algorithms

Association rule mining is one of the major technique of data mining, involves finding of frequent itemsets with minimum support and generating association rule among them with minimum confidence. The task of finding all frequent itemsets for a large datasets requires a lot of computation which can be minimized by exploiting parallelism to the sequential algorithms. In this paper, we provide the preliminaries of basic concepts about association rule mining, different sequential association rule mining algorithms on different hardware platforms and also focus on the challenges in exploiting parallelism to these algorithms. We also discusses up to what extent these challenges e.g. load balancing, efficient memory usage, minimization of communication cost among processors, efficient data and task decomposition etc. are congregate by a given parallel association rule mining algorithm and classifies them accordingly. Although, this survey cannot be complete review of all algorithms, but it provides information that will cover major theoretical issues and can be serve as a reference for both the researchers and the practitioners.