TY - GEN
T1 - Credit scoring using soft computing schemes
T2 - International Conference on Digital Enterprise and Information Systems, DEIS 2011
AU - Nwulu, Nnamdi I.
AU - Oroja, Shola
AU - Ilkan, Mustafa
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
KW - Artificial Neural Networks
KW - Credit scoring
KW - Soft computing schemes
KW - Support Vector Machines
UR - http://www.scopus.com/inward/record.url?scp=80052184609&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-22603-8_25
DO - 10.1007/978-3-642-22603-8_25
M3 - Conference contribution
AN - SCOPUS:80052184609
SN - 9783642226021
T3 - Communications in Computer and Information Science
SP - 275
EP - 286
BT - Digital Enterprise and Information Systems - International Conference, DEIS 2011, Proceedings
Y2 - 20 July 2011 through 22 July 2011
ER -
