多属性变化的增量关联规则更新研究

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。

Research on incremental updating for mining association rules based on change in multiple attributes

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.