一种基于FP-Tree强相关项目对挖掘方法.pdfVIP

一种基于 FP-Tree 的强相关项目对挖掘方法* 何增有, 徐晓飞, 邓胜春 (哈尔滨工业大学计算机科学与工程系 315 信箱, 哈尔滨, 150001) （zengyouhe@, {xiaofei, dsc}@ ） 摘要： 在给定最小相关阈值θ和待挖掘的交易数据库的情况下, 强相关项目对的挖掘问题 是要找出所有的满足皮尔森关联系数（Pearsons correlation coefficients ）不小于θ 的项目对 [1]. 尽管文献[1]中提出的Taper算法使用了基于皮尔森关联系数上界的剪枝技术，但当项 目和交易的数目非常大的时候，Taper算法中的候选项目对的产生－测试过程仍然需要很高 的计算代价。为了避免候选项目对的产生－测试过程产生的计算代价，提出了一个新的基于 FP-Tree的强相关项目对的挖掘算法，Tcp算法。在实际数据和合成数据上的试验结果表明， Tcp算法的性能明显优于已有的Taper算法。 关键词： 相关性, 关联规则, 交易数据, FP-tree, 数据挖掘 A FP-Tree Based Approach for Mining All Strongly Correlated Pairs without Candidate Generation Zengyou He, Xiaofei Xu, Shengchun Deng (Department of Computer Science and Engineering, Harbin Institute of Technology,P. R. China, 150001) Abstract Given a user-specified minimum correlation threshold θand a transaction database, the problem of mining all-strong correlated pairs is to find all item pairs with Pearsons correlation coefficients above the threshold θ. Despite the use of upper bound based pruning technique in the Taper algorithm [1], when the number of items and transactions are very large, candidate pair generation and test is still costly. To avoid the costly test of a large number of candidate pairs, in this paper, we propose an efficient algorithm, called Tcp, based on the well-known FP-tree data structure, for mining the complete set of all-strong correlated item pairs. Our experimental results on both synthetic and real world datasets show that, Tcps performance is significantly better than that of the previously developed Taper algorithm over practical ranges of correlation threshold specifications. Keywords Correlation, Association Rule, Transactions, FP-tree, Data Mining *基金项目：国家 863 高技术研究发展计