一种高效的关联规则维护算法研究与实现  

Study and Implementation of High-Performance Maintenance Algorithm for Mining Association Rules

作　　者：郭有强[1] 

机构地区：[1]蚌埠学院计算机科学与技术系,安徽蚌埠233030

出　　处：《计算机技术与发展》2007年第10期123-126,共4页Computer Technology and Development

基　　金：安徽省科技厅自然科学研究项目(050420207)

摘　　要：关联规则挖掘是数据挖掘领域中的重要研究内容之一。由于数据挖掘的过程是动态交互的,因此对已经发现的关联规则进行维护更新显得非常重要。提出了一种实用的在支持度和置信度不变的情况下数据集规模减小的负增量关联规则维护算法。算法在如何减少数据集的扫描次数,如何充分利用现有的信息减少候选集的规模等方面进行了研究,给出了算法的具体实现。理论分析和实验结果表明算法是有效的。Mining of association rules is an important research topic among the various data mining problems. The issue of maintaining discovered association rules is paid more attention in the same way. This paper provides a practical maintenance algorithm for negative incremental association rules in which the size of data sets is reduced, with the supporting and confidence limits unchanged. The algorithm explores how to diminish the number of scanning data sets, and how to make the best use of known information to shorten the size of candidate sets and so on. The concretization of the algorithm is also given. Theoretical analysis and experimental results suggest that is effctive.

关 键 词：数据挖掘 关联规则 增量维护算法 剪枝 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]