Research Opportunities for Neural Networks: The Case for Credit

• Author: Amelia A. Baldwin,Brad S. Trinkle
• Date: 01 July 2016
• DOI: http://doi.org/10.1002/isaf.1394
• Published date: 01 July 2016

RESEARCH OPPORTUNITIES FOR NEURAL NETWORKS: THE

CASE FOR CREDIT

BRAD S. TRINKLE

a

*AND AMELIA A. BALDWIN

b

a

Mississippi State University, Adkerson School of Accountancy, PO Box EF,, Mississippi State, MS USA

b

Department of Accounting, Economics, Finance, University of Arkansas–Fort Smith, Fort Smith, AR USA

SUMMARY

This article identifies research opportunities in the use of artificial neural networks in credit scoring and related

business intelligence situations, particularly as they have been emerging in the global economy. In the literature

review, particular attention is paid to commercial lending credit risk assessment and consumer credit scoring.

Investors and auditors need models that can predict whether a customer will stay viable. Lenders must manage their

credit risk to maximize profits and cash flow,while minimizing losses. As the global economic recession continues,

investors are tightening their investment belts and need models that help them make better investment decisions,

while lenders must strengthen lending practices and better identify both good and bad credit risks. Artificial neural

networks may help firms improve their credit model development, and thereby their credit decisions and

profitability.Such technology may also help improve development in emerging economies. Copyright © 2016 John

Wiley & Sons, Ltd.

1. INTRODUCTION

Opportunities for research on artificial neural network (ANN) use in problem solving in the new global

economy are increasing rapidly. A combination of economic and political events, including the

financial crisis of 2008 and the rise of developing and emerging economies in the beginning of the

21st century, has created special opportunities for applying intelligent problem-solving tools to a

myriad of credit and financial decisions. However, research to date has shown somewhat conflicting

results, indicating the need and opportunity for further investigation. This introduction provides a brief

history of credit scoring and an introduction to ANNs.

1.1. A Brief History of Credit Scoring

Traditionally, the use of consumer credit scores has been a common practice in lending deci-

sions. However, this was not always true. Consumer credit scoring models were initially devel-

oped and used by Henry Wells of Spiegel, Inc. during the 1940s (Lucas, 2001; Davies, 2003).

The concept of consumer credit scoring did not become widely accepted until the 1950s when

Bill Fair and Earl Isaacs formed the credit scoring firm of Fair Isaacs, Inc. and generated generic

models (Thomas, 2000; Lucas, 2001). Generic scorecards are developed from data that are exter-

nal to the lender and that may be heterogeneous to the credit applications scored by individual

enterprises. Generic scorecards are not designed for a specific type of product or borrower

(Mays, 2004). Model heterogeneity and lack of specificity to lenders’situations may lead to

* Correspondence to: Brad S. Trinkle, Mississippi State University, Adkerson School of Accountancy, PO Box EF, Mississippi

State, MS 39762, USA. E-mail: brad.trinkle@msstate.edu

Copyright © 2016 John Wiley & Sons, Ltd.

INTELLIGENT SYSTEMS IN ACCOUNTING, FINANCE AND MANAGEMENT

Intell. Sys. Acc. Fin. Mgmt. 23, 240–254 (2016)

Published online 10 May 2016 in Wiley Online Library (wileyonlinelibrary.com) DOI: 10.1002/isaf.1394