Lancaster EPrints

Multiple classifier architectures and their application to credit risk assessment

Finlay, Steven M. (2011) Multiple classifier architectures and their application to credit risk assessment. European Journal of Operational Research, 210 (2). pp. 368-378. ISSN 0377-2217

Full text not available from this repository.

Abstract

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. In this paper the performance of several multiple classifier systems are evaluated in terms of their ability to correctly classify consumers as good or bad credit risks. Empirical results suggest that some multiple classifier systems deliver significantly better performance than the single best classifier, but many do not. Overall, bagging and boosting outperform other multi-classifier systems, and a new boosting algorithm, Error Trimmed Boosting, outperforms bagging and AdaBoost by a significant margin.

Item Type: Article
Journal or Publication Title: European Journal of Operational Research
Additional Information: Date of Acceptance: 22/09/2010
Uncontrolled Keywords: OR in banking ; Data mining ; Classifier combination ; Classifier ensembles ; Credit scoring
Subjects:
Departments: Lancaster University Management School > Management Science
ID Code: 45057
Deposited By: ep_importer_pure
Deposited On: 11 Jul 2011 19:25
Refereed?: Yes
Published?: Published
Last Modified: 18 Jun 2015 05:32
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/45057

Actions (login required)

View Item