一种无冗余的快速关联规则发现算法

An Efficient Algorithm for Rapidly Mining Non-redundant Rules

关联规则的发现是数据挖掘的一个重要方面。传统算法不但涉及大量的数据库操作，而且生成的关联规则之间存在着大量的冗余规则。文章给出了一种无冗余的快速关联规则算法，能大量减少所需的I/O的次数，内存开销适中，并且利用规则之间的冗余关系消除了规则之间的冗余性。

Discovering association rules is an important aspect of data mining problem. The traditional association rules discovery algorithm not only involves a great deal DB operation, but also produces too many redundant rules. This paper presents an algorithm for rapidly mining non-redundant rules using the redundant relationship of rules. The algorithm uses memory moderately, reduces I/O overheads greatly, and eliminates the redundancy between the rules.