Title: Real-world credit scoring: a comparative study of statistical and artificial intelligent methods

Authors: Zhou Ying; Tabassum Habib; Guotai Chi; Mohammad Shamsu Uddin

Addresses: School of Management and Economics, Dalian University of Technology, Dalian 116024, China ' School of Management and Economics, Dalian University of Technology, Dalian 116024, China ' School of Management and Economics, Dalian University of Technology, Dalian 116024, China ' School of Management and Economics, Dalian University of Technology, Dalian 116024, China; Department of Business Administration, Metropolitan University, Sylhet, Bangladesh

Abstract: Credit scoring is an integral and crucial part of any lending process that any little development in it can reduce huge potential losses of financial organisations. The assessment of model performance varies because of different performance measures under a variety of circumstances on different nature of datasets. Therefore, this study employed six well-known classification approaches on six real-world credit datasets for comprehensive assessment by combining ten representative performance criterions. The experimental outcomes, statistical significance test and the estimated cost of prediction error confirm the marginal superiority of logistic regression (LR) and TreeNet over CART and MARS, being more robust compared to other two approaches LASSO and RF.

Keywords: credit scoring; performance measures; statistical method; artificial intelligence; AI.

DOI: 10.1504/IJKEDM.2019.097357

International Journal of Knowledge Engineering and Data Mining, 2019 Vol.6 No.1, pp.32 - 55

Received: 05 Jul 2018
Accepted: 28 Sep 2018
Published online: 15 Jan 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article