摘要
在支持度和事务库发生变化时,如何有效地更新关联规则的问题是目前数据挖掘研究的热点。但当事务库中的属性发生变化时,如何高效地更新关联规则的问题一直都没有引起研究人员的重视。ACA+和ACA-算法对单属性增减后的关联规则进行了研究,在此基础上,提出了解决多属性增减的增量关联规则更新算法MACA+和MACA-。通过建立事务-属性矩阵有效地解决了该问题。
When support and transaction database are changing,the problem of how to effectively update association rules is a hot topic in data mining research.However the problem of how to effectively update association rules after a change of the attributes in transaction database has not too much attention.ACA+ and ACA-algorithm do researches on signal attribute change of it.Based on this,the paper proposes incremental updating algorithms for mining association rules based on the change of multiple attributes,which are MACA+ and MACA-.By structuring transaction-attribute matrix,it can effectively solve the problem.
出处
《计算机工程与应用》
CSCD
北大核心
2010年第30期138-141,共4页
Computer Engineering and Applications
基金
国家税务总局项目
关键词
多属性
数据挖掘
关联规则
基于多属性变化
增量式关联规则更新
multiple attribute; data mining; association rules; multiple attribute change; incremental association rules updating;