典型关联规则挖掘算法的分析与比较  

Analysis and Comparison of Representative Algorithms for Mining Association Rules

作　　者：冯洁[1] 陶宏才[1] 

机构地区：[1]西南交通大学信息科学与技术学院,四川成都610031

出　　处：《计算机技术与发展》2007年第3期121-124,共4页Computer Technology and Development

摘　　要：关联规则的发现是数据挖掘的一个重要方面,目前许多研究人员正致力于关联规则的快速开采算法的研究。文中介绍了几种典型的开采大型事务数据库中所有关联规则的算法,特别针对算法过程中产生候选频繁项集的大小和所需扫描事务数据库的次数这两个影响关联规则挖掘效率的关键问题,分析各个算法采用的解决策略及相应的局限性,并比较它们的时间效率和空间效率。最后展望了关联规则挖掘算法的研究方向。Discovering association rules is an important data mining problem. Recently, there has been considerable research in designing algorithms for this task. Introduce some representative Mgorithms for discovering all significant association rules amo .ng items in large database of transactions, and it＇s known that there are two key problems that affect the efficiency of discovering association rules,so analyse the strategy each algonithm adopts seperately, and compare their tradeoffs, finally prospects development trends of algorithms of discovering association rules.

关 键 词：数据挖掘 关联规则 频繁项集 算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]