Efficiently Mining Maximal Frequent Itemsets Based on Digraph

We present MFIMiner, a new algorithm for mining maximal frequent itemsets. The algorithm has a preprocessing phase in which a digraph is constructed. The digraph represents the set of the frequent 2-itemsets which is the key issue of the performance of the data mining. Then the search for maximal frequent itemsets is done in the digraph. Experiments show that the algorithm is efficient not only to dense data, but to sparse data.