基于属性变化的增量关联规则挖掘

Incremental updating algorithm for mining association rules based on change in attributes

关联规则的挖掘是数据挖掘研究中的一个重要课题,目前已经提出了许多用于发现海量事务库中关联规则的算法以及更新已经发现的关联规则的算法。但是在关联规则的更新算法中,都是基于支持度变化和事务库变化的研究,目前没有人研究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。针对这种情况,提出了三种基于属性变化的增量关联规则挖掘算法ACA+(Attribute Change Algorithm)和ACA-(ACA1-),从而解决了该问题。

Currently,mining association rules is a key problem in the field of data mining.Lots of algorithms for efficiently mining association rules or incremental updating association rules in large database have been proposed.However,all of them are based on changes in support or transaction database about the algorithms of updating association rules.No one does researches on how to effectively update association rules under changing the attributes in transaction database.Under this kind of situation,the paper proposes incremental updating algorithms for mining association rules based on the change in attributes,which are ACA ＋ （Attribute Change Algorithm） and ACA-（ACA1-）.Therefore,it can solve the problem.