Abstract: Traditional association rule mining algorithm has low efficiency and it has a mount of redundant in mining results. Aiming at this problem, this paper presents an association rule mining algorithm based on base set and concept lattice. It replaces the original database with the base set which has seed item distribution range, and builds concept lattice to find association rules. Experimental results show that this algorithm has much superior to Base and Apriori algorithm on the performance of time efficiency.

Key words: data mining, association rule, concept lattice, base set

摘要： 传统关联规则挖掘算法的挖掘效率较低，且挖掘结果中存在大量冗余。针对该问题，提出一种基于概念格与基集的关联规则挖掘算法。利用规定种子项分布范围的基集代替原始数据库以缩小挖掘源规模，从而建立概念格快速求解出关联规则。实验结果表明，该算法在时间效率方面优于Base和Apriori算法。

关键词: 数据挖掘, 关联规则, 概念格, 基集

CLC Number: 

• TP393