gpuDCI: Exploiting GPUs in Frequent Itemset Mining

Frequent itemset mining (FIM) algorithms extract sub-sets of items that occurs frequently in a collection of sets. FIM is a key analysis in several data mining applications, and the FIM tools are among the most computationally in-tensive data mining ones. In this work we present a many-core parallel version of a state-of-the-art FIM algorithm, DCI, whose sequential ver-sion resulted, for most of the tested datasets, better than FP-Growth, one of the most efficient algorithms for FIM. We propose a couple of parallelization strategies for Graph-ics Processing Units (GPU) suitable for different resource availability, and we present the results of several experi-ments conducted on real-world and synthetic datasets. 1