Parallel frequent itemsets mining algorithm without intermediate result

Mining association rules from large databases is an important problem in data mining. FP-growth is a powerful algorithm to mine frequent patterns and it is non-candidate generation algorithm using a special structure FP-tree. In order to enhance the efficiency of FP-grown algorithm, propose a novel parallel algorithm PFPTC to create sub FP-trees concurrently and a FP-tree merging algorithm called FP-merge, which can merge two FP-trees into one FP-tree. Also propose a new efficient algorithm QFP-growth, which can avoid bottleneck of FP-growth in generating a huge number of intermediate result.