高效的关联规则挖掘算法  

Efficient algorithm for mining association rules

作　　者：郭健美[1] 宋顺林[1] 肖仁财[1] 

机构地区：[1]江苏大学计算机学院,江苏镇江212013

出　　处：《计算机工程与设计》2008年第13期3378-3380,共3页Computer Engineering and Design

基　　金：江苏省产业信息化重点基金项目(1633000004)

摘　　要：针对Apriori算法多次扫描数据库且生成的候选项集数量大的缺陷,提出了一种数据库优化策略,并结合修剪频繁集和连接优化策略,得到一种新的关联规则挖掘算法-NApriori算法。该算法减小了数据库的规模以及候选项集的数目,避免了连接过程中相同项目的重复比较。实验表明此方法比Apriori算法有更好的性能。Aimed at the disadvantages of scanning the database multiply and generating a large quantity ofthe candidate sets in the Apriori algorithm, a strategy of database optimization is presented, and frequent set pruning is combined and join optimization strategy. A new algorithm of mining association rule - NApriori algorithm is presented, The algorithm could reduce the size of the database gradually and the number of the candidate itemsets, avoid the repeated comparison of the same itemsets in the join procedure. The experiment indicates that this method has a better performance than the Apriori algorithm.

关 键 词：数据挖掘 关联规则 频繁项集 事务数据库 最小支持数 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]