Modeling credit approval data with neural networks: an experimental investigation and optimization

Chi Guotai, Mohammad Zoynul Abedin and Fahmida–E Moula

Journal of Business Economics and Management, 2017, vol. 18, issue 2, 224-240

Abstract: This study proposes an investigation and optimization of Multi-Layer Perceptron (MLP) based artificial neural networks (ANN) credit prediction model, combine with the effect of different ratios of training to testing instances over five real-world credit databases. As an outcome from the alteration procedure, three different types of hidden units [K = 9 (ANN–1), K = 10 (ANN–2), K = 23 (ANN–3)] are chosen through the pilot experiments and execute, therefore, 45 (5×3×3) unique neural models. Experimental results indicate that “the neural architecture with ten hidden units” is proposed as an optimal approach to classifying the credit information. With these contributions, therefore, we complement previous evidence and modernize the methods of credit prediction modeling. This study, however, has realistic implications for bank managers and other stakeholders to delineate the risk profile of the credit customers.

Date: 2017
References: Add references at CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://hdl.handle.net/10.3846/16111699.2017.1280844 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:jbemgt:v:18:y:2017:i:2:p:224-240

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TBEM20

DOI: 10.3846/16111699.2017.1280844

Access Statistics for this article

Journal of Business Economics and Management is currently edited by Izolda Joksiene, Romualdas Ginevicius and Ieva Meidute

More articles in Journal of Business Economics and Management from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().