Please use this identifier to cite or link to this item:
|Title:||Dilated Chi-Square : a novel interestingness measure to build accurate and compact decion list||Authors:||Lan, Yu
|Issue Date:||2005||Publisher:||Springer||Source:||He, Qing; Zhongzhi, Shi (Ed.). Intelligent Information Processing II, p. 233-237||Abstract:||Associative classification has aroused significant attention in recent years. This paper proposed a novel interestingness measure, named dilated chi-square, to statistically reveal the interdependence between the antecedents and the consequent of classificaton rules. Using dilated chi-square, instead of confidence, as the primary ranking criterion for rules under the framework of popular CBA algorithm, the adapted algorithm presented in this paper can empirically generate more accurate and much more compact decision lists.||Keywords:||dilated chi-square; associative classification; CBA||Document URI:||http://hdl.handle.net/1942/14638||ISBN:||978-0-387-23151-8||DOI:||10.1007/0-387-23152-8_30||Category:||B2||Type:||Book Section||Validations:||vabb 2015|
|Appears in Collections:||Research publications|
Show full item record
Files in This Item:
|127.46 kB||Adobe PDF||View/Open Request a copy|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.