2011 | OriginalPaper | Buchkapitel
Credit Scoring Using Soft Computing Schemes: A Comparison between Support Vector Machines and Artificial Neural Networks
verfasst von : Nnamdi I. Nwulu, Shola Oroja, Mustafa Ilkan
Erschienen in: Digital Enterprise and Information Systems
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The recent financial crisis that has devastated many nations of the world has made it imperative that nations upgrade their credit scoring methods. Although statistical methods have been the preferred method for decades, soft computing techniques are becoming increasingly popular due to their efficient and accurate nature and relative simplicity. In this paper a comparison is made between two prominent soft computing schemes namely Support Vector Machines and Artificial Neural Networks. Although a comparison can be made along various criteria, this study attempts to compare both techniques when applied to credit scoring in terms of accuracy, computational complexity and processing times. In order to assure meaningful comparisons, a real world dataset precisely the Australian Credit Scoring data set available online was used for this task. Experimental results obtained indicate that although both soft computing schemes are highly efficient, Artificial Neural Networks obtain slightly better results and in relatively shorter times.