Predicting SME loan delinquencies during recession using accounting data and SME characteristics: The case of Greece

• Author: Eleftherios Aggelopoulos,Vasilios Giannopoulos
• DOI: http://doi.org/10.1002/isaf.1456
• Date: 01 April 2019
• Published date: 01 April 2019

RESEARCH ARTICLE

Predicting SME loan delinquencies during recession using

accounting data and SME characteristics: The case of Greece

Vasilios Giannopoulos

1

|Eleftherios Aggelopoulos

2

1

Department of Accounting and Finance,

University of Peloponnese, Antikalamos,

Kalamata, Greece

2

Department of Business Administration,

University of Patras, Rio, Patras, Greece

Correspondence

Vasilios Giannopoulos, Department of

Accounting and Finance, University of

Peloponnese, 24100, Antikalamos, Kalamata,

Greece.

Email: v.giannopoulos@accfin.edu.gr

Summary

The objective of this paper is the comparison of various credit‐scoring models (i.e.

binomial logistic regression, decision tree, multilayer perceptron neural network,

radial basis function, and support vector machine) in evaluating the risk of small and

micro enterprises' (SMEs') loan delinquencies based on accounting data and appli-

cants' specific attributes. Exploiting a representative large data set of SMEs' loans

granted by a large Greek commercial bank in the expansion period, we track the evo-

lution of SMEs' delinquencies over the recession period August 2010 to July 2012.

This time frame encompasses a period of manageable levels of delays (early recession

period: August 2011–July 2012) and a period when delays were increased to a very

high degree (deep recession period: August 2011–July 2012). Comparison of the

employed credit‐scoring models during the early recession period shows that the

multilayer perceptron neural network produces the highest predicting capacity,

followed by the support vector machine model. As the crisis deepens, the support

vector machine model presents the highest predicting accuracy, followed by the deci-

sion tree and then the multilayer perceptron model. Generally, the predictive perfor-

mance of all credit‐scoring models seems to be substantially reduced as the recession

escalates. Our paper has important implications for the proper financing of SMEs

given their importance for the European economy.

KEYWORDS

banks, credit‐scoring models, Greek crisis, micro and small enterprises, non‐performing loans

JEL CLASSIFICATION

G21; C23

1|INTRODUCTION

Small and micro enterprises (SMEs) are key players in the EU econ-

omy, since more than 99% of all European businesses are SMEs,

providing two‐thirds of the private sector jobs and contributing to

more than half of the total value‐added (Muller et al., 2016). How-

ever, SMEs present some distinct specificities, stemming mainly from

the fact that the owner of the SME is, most likely, also the manager

of the SME. Specifically, SMEs are characterized by specific credit

risk attributes that affect their repayment behaviour, such as high

transactional costs and high loan interest rates, and they face a

more uncertain competitive environment and are less equipped

with the human and capital resources to withstand economic

adversity than larger companies are (Stiglitz & Weiss, 1981). Thus,

the role of the SMEs, especially when they are the backbone of an

economy, becomes controversial when an economic shock occurs.

This is what the recent crisis teaches us, since SMEs present the

highest level of non‐performing loans (NPLs; 18.5% in June 2015;

European Banking Authority, 2015) compared with other strategic

firm groups.

Received: 28 October 2018 Revised: 24 April 2019 Accepted: 4 May 2019

DOI: 10.1002/isaf.1456

Intell Sys Acc Fin Mgmt. 2019;26:71–82. © 2019 John Wiley & Sons, Ltd.wileyonlinelibrary.com/journal/isaf 71