关键词: 数据挖掘 精简集 频繁项目集 无规则集

Abstract:

Given a large collection of transactions containing items, a basic common problem is to extract the so-called frequent itemset. The idea presented in  this paper is to extract a condensed representation of the frequent itemsets called rule-free sets, instead of extracting the whole frequent itemset col lection. We show that this condensed representation can be used to regenerate all frequent patterns and their exact frequencies without any access to th e original data. An algorithm named HOPE-Ⅲ is given to extract the frequent rule-free sets. We compared it with an algorithm named A-Close which extrac  cts another condensed representation of frequent itemsets previously investigated in the literature called frequent closed sets. The experiments show th at in all cases, HOPE-Ⅲ is much more efficient than A-Close.

Key words: （data mining, condensed representation, frequent itemset, rule-free set）