MPSQAR: Mining Quantitative Association Rules Preserving Semantics

To avoid the loss of semantic information due to the partition of quantitative values, this paper proposes a novel algorithm, called MPSQAR, to handle the quantitative association rules mining. And the main contributions include: (1) propose a new method to normalize the quantitative values; (2) assign a weight for each attribute to reflect the values distribution; (3) extend the weight-based association model to tackle the quantitative values in association rules without partition; (4) propose a uniform method to mine the traditional binary association rules and quantitative association rules; (5) show the effectiveness and scalability of new method by experiments.

• Type: Conference
• Year: 2008
• Where: ADMA
• Authors: Chunqiu Zeng, Jie Zuo, Chuan Li, Kaikuo Xu, Shengqiao Ni, Liang Tang, Yue Zhang, Shaojie Qiao
• Keywords: ADMA 2008, Association Rules, Data Mining, Quantitative Association Rules, Quantitative Values