MINING CONCISE ASSOCIATION RULES BASED ON GENERATORS AND CLOSED ITEMSETS

摘要：

It is well-recognized that the main factor that hinders the applications of Association Rules (ARs) is the huge number of ARs returned by the mining process. To solve this problem, an algorithm for mining concise association rules based on generators and closed itemsets is proposed. Firstly, the concept of concise association rule is proposed, and the rationality of the definition is explained based on conviction. Then, the definitions of concise min-max precise rule basis and concise min-max approximate rule basis are proposed, and the corresponding pruning strategies are discussed. Finally, the characteristics and connection strategies of generator are presented, and based on subsume index, a breadth-first algorithm for mining concise association rule is proposed. Experimental results show that the concise rules with smaller sizes can be discovered. Thus, the understandability of mining result is improved.

关键词： Data mining Concise association rule Generator Closed itemset Subsume indez

作者: WEI SONG JIN-HONG LI

作者单位: College of Information Engineering, North China University of Technology, Beijing 100144, China

会议类型: 国际会议

会议名称: 2009 International Conference on Machine Learning and Cybernetics(2009机器学习与控制论国际会议)

会议地点: 保定

会议语种:英文

页码: 249-254

在线出版日期: 2009-07-12（万方平台首次上网日期，不代表论文的发表时间）