MINING HIGH UTILITY ITEMSET USING GRAPHICS PROCESSOR

In Data Mining, Association Rule Mining is one of the most influential tasks. Several analyses and algorithm of it provides knowledge to investors or marketing manager to analysis and predict their market field and managing their records. But these procedures are not enough to originate more productive results. The traditional high utility itemset mining algorithms occupy more space, memory and time for generation of the candidate list. We presented the novel algorithm for Mining high utility itemsets using a parallel approach for transactional datasets. Therefore, the Sales Manager can use this utility itemset for their historical analysis of data, stock planning, and decision making. Our new approach is an extension of FHM algorithm, by attaching pruning method in HUIM. This utilization is improved to acquire immense efficiency on a miscellaneous platform which consists of a shared memory multiprocessor and numerous cores NVIDIA based Graphics Processing Unit (GPU) coprocessor. An empirical study and results of existing algorithm FHM are compared with the novel algorithm on NVIDIA Kepler GPUs and discovered significant improvements in computing time compare to FHM.