一种基于可信度最优的数量关联规则挖掘算法

An Algorithm for Mining Optimized Confidence Quantitative Association Rules

研究了数量关联规则挖掘过程中的连续属性离散化问题 ,描述了连续属性离散化方法 ,包括连续属性区间划分算法和数据库样本大小的确定 ,提出了基于可信度最优的数量关联规则挖掘算法 .该算法首先利用等深度划分算法对连续属性进行离散化 ,然后利用凸包处理技术提取强规则中可信度最高的数量关联区间 ,它对于数量关联规则的优化有着重要的应用价值 .应用该算法对股票行情进行了数量关联分析 ,提取股票涨跌与股票价格之间可信度最高的关联规则 .实验表明该算法是非常有效的 .

This paper discusses the problem of discretization for continuous attributes and describes a method for discretization in the processing of mining quantitative association rules, including quantitative ranges partitioning and sampling to a huge database. An algorithm for mining optimized confidence quantitative association rules is presented. In the algorithm, the equi depth partitioning is used to discrete for continuous attributes and a technique of handing convex hulls is used to compute optimized confidence quantitative association ranges. Given a huge database, we address the problem of finding association rules for numeric attributes, such as ( A∈[v 1,v 2])C , in which C is boolean attribute. Our goal is to realize a system that finds an appropriate range automatically. We use the algorithms to analyse the buying and selling of stocks, finding association rules between stock price and fluctuation of price. The experiment states clearly that the algorithms are correct.