Title :
The measures and mining method of credible association rule
Author :
Xiao, Bo ; Xu, Qianfang ; Lin, Zhiqing ; Guo, Jun
Author_Institution :
Beijing Univ. of Posts & Telecommun., Beijing, China
Abstract :
Credible association rule(CAR) is a new type of association pattern in which items are highly affiliated with each other. The presence of an item in one transaction strongly implies the presence of every other item in the same CAR. And a maximal CAR is a CAR whose each superset isn´t a CAR, so the maximal CAR specifies a more compact representation of a group of CARs. In this paper, we introduce some measures for CAR which all represent the affinity of the items in a CAR. A mining method based on maximal clique is also presented to mine all of the maximal CARs. The experimental results demonstrate that the mining method is more effective than the other stand mining methods for association rules.
Keywords :
data mining; association pattern; credible association rule; data mining; item affinity; maximal clique; Association rules; Data mining; Itemsets; Transaction databases; credible association rule(CAR); data mining; maximal clique; measure;
Conference_Titel :
Network Infrastructure and Digital Content, 2009. IC-NIDC 2009. IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4898-2
Electronic_ISBN :
978-1-4244-4900-6
DOI :
10.1109/ICNIDC.2009.5360993