一个改进项目的加权关联规则挖掘算法  

An Improved Mining Algorithm of Weighted Association Rule

作　　者：刘燕[1] 

机构地区：[1]闽江学院计算机科学系,福建福州350108

出　　处：《昆明理工大学学报（理工版）》2008年第4期34-37,共4页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：福建省教育厅项目(项目编号:JB07172)

摘　　要：提出了一个改进的项目加权关联规则挖掘算法.该算法利用一个加权频繁项目集必须满足的加权支持度下界,对加权频繁候选项目集进行剪枝,该下界计算简便,可以减少挖掘的计算量.理论分析和实验表明本算法和MINWAL(W)相比,具有生成候选集数量少、挖掘效率高等特点,特别在项目权值相差不大时,本算法的优势更明显.An improved mining lower support bound of frequent algorithm is introduced to handle the item sets with weights is applied to this problem of weighted association rule. A algorithm to prune the number of the candidate item sets, which can increase its simplicity and decrease the number of calculation in the mining process. It is shown through analysis and examples that the algorithm is efficient and performs better than MINWAL（ W）, especially when the difference between the weights of items is not so large.

关 键 词：数据挖掘 关联规则挖掘 交易数据库 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP18[自动化与计算机技术—计算机科学与技术]