An effective algorithm for mining quantitative associations based on subspace clustering

Abstract

Algorithms for mining Boolean association rules have been well studied and documented, but they cannot deal with quantitative data directly. In this paper, a novel algorithm MQAR (Mining Quantitative Association Rules based on dense grid) which uses tree structure DGFP-tree to cluster dense subspaces is proposed, which transforms mining quantitative association rules into finding dense regions. MQAR not only can solve the conflict between minimum support problem and minimum confidence problem, but also can find the interesting quantitative association rules which may be missed by previous algorithms. Experimental results show that MQAR can efficiently find quantitative association rules.