摘要
文中基于chi-square检验、有趣度及信息增益理论,给出了一种挖掘优化关联规则的算法。该算法将冗余的规则分为两个部分:一部分规则缺乏统计的相关性,而另外一部分规则不满足“新奇的”要求。实验结果表明算法可以有效地去除冗余规则并提高挖掘效率。
Based on theory of chi-square test,interest measure and information gain,an algorithm which can be used for mining optimized association rules is presented in this paper.In this algorithm,the redundant rules are divided into two parts:rules lacking statistical correlation,and rules without 'novelty'.The experiment results show that the algorithm can prune the redundant rules effectively and improve the mining efficiency.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第26期204-207,共4页
Computer Engineering and Applications
基金
广东省自然科学基金资助(编号:011750)
关键词
关联规则挖掘
有趣度
信息增益
association rule mining,interest measure,information gain
