一种基于布尔矩阵的关联规则快速挖掘算法

A fast algorithm for mining fo association rules based on boolean matrix

关联规则的发现是数据挖掘中的一个重要问题,其核心是频繁模式的挖掘,通常采用的Apriori算法要多次扫描数据库并产生大量的候选项集,开销很大。本文采用基于布尔矩阵关联挖掘的算法,只需扫描一次数据库而且不需要链接产生候选项集,从而提高算法的效率。并通过实例说明了它是一种有效的关联规则挖掘方法。

The discovery of association rules in data mining is an important issue, the core of which is the frequent pattern mining, Apriori algorithm is classical for the association rule mining, but it should repeatedly scan the database and can produce plenty of candidates. By exernples, it is proved that Boolean Matrix Association Rules algorithm can improve the algorithmic efficiency by reducing the times of accessing database and without producing candidates.