作者: Bin Shen , Min Yao , Zhaohui Wu , Yunjun Gao
DOI: 10.1007/S10115-009-0207-1
关键词:
摘要: In this paper, we study a new problem of mining dynamic association rules with comments (DAR-C for short). A DAR-C contains not only rule itself, but also its that specify when to apply the rule. order formalize problem, first present expression method candidate effective time slots, and then propose several definitions concerning DAR-C. Subsequently, two algorithms, namely ITS2 EFP-Growth2, are developed handling particular, is an improved two-stage algorithm, while EFP-Growth2 based on EFP-tree structure suitable high-density mass data. Extensive experimental results demonstrate efficiency scalability our proposed algorithms (i.e., EFP-Growth2) tasks, their practicability real retail dataset.