Motivation-based association rule mining

Existing algorithms for support-based association rule mining (ARM) can not discover the itemsets which are scarce but have high utility values, while utility-based association rule mining (UBARM) can not discover the itemsets whose utility values are not high but the product of the support and utility of the same itemset (defined as motivation) is very large. This paper proposes motivation-based association rule and a down-top algorithm called HM-miner to discover all high motivation item-sets efficiently. By integrating the advantages of support and utility, the new measure, i.e., motivation can measure both the statistical and semantic significance of an itemset. HM-miner adopts a new pruning strategy, which is based on the motivation upper bound property, to cut down the search space.