基于事务压缩的关联规则挖掘算法改进  

An Improved Algorithm for Association Rules Mining Based on Reducing Transaction

作　　者：孙金华[1] 谢彦麒[1] 

机构地区：[1]厦门理工学院计算机科学与技术系,福建厦门361024

出　　处：《微计算机信息》2010年第27期223-225,共3页Control & Automation

基　　金：申请人:孙金华;项目名称:基于关联规则的Web日志挖掘研究;颁发部门:厦门市科技局(3502Z20077021)

摘　　要：关联规则挖掘是数据挖掘研究领域中的一个重要任务,旨在挖掘事务数据库中事务的关联关系。Apriori算法是关联规则挖掘中的经典算法,该算法需反复扫描数据库,因此效率较低。本文在分析Apriori算法的原理及效率的基础上,提出基于事务压缩的改进方法,并将其与Apriori算法对比分析,实验表明改进算法在时间性能上优于Apriori算法。Mining association rule is an important task in data mining research field, its purpose is to mine associations in transaction database. Apriori algorithm is a classical algorithm for mining association rule, due to the algorithm need to be repeated scanning the database, and it has less efficiency. Based on the study of principle and efficiency of the Apriori algorithm, this paper proposes an improved strategy based on reducing transaction to optimize the Apriori algorithm,the analysis and comparison is carried out between it and the Apriori algorithm. The experimental result shown that the improved algorithm has a more significant performance than the Apriori algorithm.

关 键 词：关联规则 数据挖掘 APRIORI算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]