Association rules mining with relative weighted support

Abdullah, Zailani and Mat Deris, Mustafa Association rules mining with relative weighted support. Proceedings of the 11th International Conference on Information Integration and Web-based Applications & Services .

Full text not available from this repository.

Official URL: http://delivery.acm.org/10.1145/1810000/1806433/p5...

Abstract

Mining weighted association rules are very important in a domain of knowledge discovery. Most of traditional association rules are focused on binary relationships rather than the mixture binary-weight relationships of items. As a result, the significance of weight of each item in a transaction is just ignored completely. Until this instance, only few studies are dedicated for weighted schemes as compared to existing binary association rules. Here, we propose a novel weighted association rules scheme called Relative Weighted Support (RWS). The result reveals that RWS can easily discover the significance of weighted association rules and surprisingly all of them are extracted from the least items.

Item Type:Article
Uncontrolled Keywords:weighted association rules, knowledge discovery, least
Subjects:T Technology > T Technology (General)
Divisions:Faculty of Science Computer and Information Technology > Department of Software Engineering
ID Code:2207
Deposited By:Normajihan Abd. Rahman
Deposited On:28 Mar 2012 08:50
Last Modified:28 Mar 2012 09:02

Repository Staff Only: item control page