Dynamic FP-Tree Based Mining of Frequent Patterns Satisfying Succinct Constraints

Abstract

Since its introduction, frequent-pattern mining has been generalized to many forms, which include constrained data mining. The use of constraints permits user focus and guidance, enables user exploration and control, and leads to effective pruning of the search space and efficient mining of frequent patterns. In this paper, we focus on the use of succinct constraints. In particular, we propose a novel algorithm, called dyFPS, for dynamic FP-tree based mining of frequent patterns satisfying succinct constraints. Here, the term “dynamic” means that, in the middle of the mining process, users are able to modify the succinct constraints they specified. In terms of functionality, our algorithm is capable of handling these modifications effectively by exploiting succinctness properties of the constraints in an FP-tree based framework. In terms of performance, the dyFPS algorithm efficiently computes all frequent patterns satisfying the constraints.