Efficiently Using Matrix in Mining Maximum Frequent Itemset
Zhenyu Liu, Weixiang Xu, Liu Xumin · 2010
An efficient way to discover the maximum frequent itemsets can be very useful for mining association rules, correlations, episodes patterns, etc. Most existing work focuses on the technique for mining candidate maximal frequent itemsets and ignores the technique for MFI checking. However the efficient of a MFS mining algorithm lies on these two parts. In this paper, a new MFI checking method is presented based on the optimizing of the former called MaxMatrix and an additional constraint for association rules generating is discussed to save mining time. In order to understand the process of MaxMatrix easily, an example is provided in detail.