带有多个可转化约束的频繁项集挖掘算法

Mining Frequent Item Sets with Multiple Convertible Constraints

1.引言 频繁项集的挖掘是数据挖掘课题中的一个很重要的方面,然而频繁项集的挖掘过程通常会产生数目庞大的频繁项集,并且其中的绝大多数并不是客户所期望得到的,因而使挖掘过程的效果和效率都大打折扣.

Recent work has highlighted the importance of the constraint-based mining paradigm in the context of frequent item sets, associations, correlations. Some research has raised the notion 'convertible constraints', and this method can push some constraints into the mining algorithm which essentially can't be pushed. This article has introduced a multiple convertible constraints mining algorithm, which analyzes the constraints by taking advantage of a sample database and then decides a optimal method to process data mining