Parallel mining of frequent patterns in transactional databases

One of the important and well-researched problems in data mining is mining association rules from transactional databases, where each transaction consists of a set of items. The main operation in this discovery process is computing the occurrence frequency of the interesting set of items. In practice, we are usually faced with large datasets, and an exponentially large space of candidate itemsets. A potential solution to the computation complexity is to parallelize the mining algorithm. In this paper, firstly, we introduce an already proposed sequential mining algorithm for discovery of frequent itemsets, which requires just a single scan of the database. In the next part, we present four parallel versions of the algorithm. The parallel algorithms will be compared analytically and experimentally, regarding some important factors, such as time complexity, communication rate, load balancing, etc.