Ability to Borrow Modeling Techniques for Small and Medium-Sized Enterprises

Aidas Malakauskas; Ausrine Lakstutiene; Lina Sineviciene; Andrzej Buszko

doi:10.5755/j01.ee.36.4.40554

Authors

Aidas Malakauskas Kaunas University of Technology, Lithuania https://orcid.org/0000-0001-6739-2481
Ausrine Lakstutiene Kaunas University of Technology, Lithuania https://orcid.org/0000-0003-1130-2592
Lina Sineviciene Kaunas University of Technology, Lithuania
Andrzej Buszko Pomeranian UniPomeranian University in Słupsk, Institute of Management, Poland https://orcid.org/0000-0003-0600-4646

DOI:

https://doi.org/10.5755/j01.ee.36.4.40554

Keywords:

SMEs, Ability to borrow, Machine learning methods, Gradient Boosting, The Baltic States

Abstract

This study comprehensively evaluates the ability to borrow machine learning modeling techniques for SMEs, utilizing a sample of the Baltic States with many variables. The study aims to assess the applicability of access to credit modeling techniques for SMEs. This is the first study in which a large–scale assessment has been carried out in the Baltic States sample, covering five years of credit applications from SMEs to a depository institution. The results showed that Gradient Boosting produces the most accurate results. Gradient Boosting demonstrated better results than the benchmark Logistic Regression as well as other advanced machine learning models, including Random Forests and Multilayer Perceptron models. The method showed the highest accuracy of the overall receiver operating characteristic (ROC) curve and the associated area under the curve (AUC) (ROC–AUC) and Average Precision values, as well as other discriminatory threshold values, compared to alternative methods.

Author Biographies

Aidas Malakauskas, Kaunas University of Technology, Lithuania

Aidas Malakauskas holds a PhD in Economics and works at AB Swedbank as the Head of the Financing Transformation Department. He is also a member of the Sustainable Economics Research group at the School of Economics and Business, Kaunas University of Technology. His research interests include credit risk, SMEs, access to finance, credit rationing, and machine learning. ORCID iD 0000-0001-6739-2481.
Ausrine Lakstutiene, Kaunas University of Technology, Lithuania

Ausrinė Lakstutiene, Dr., is a Professor at the School of Economics and Business and a member of the Sustainable Economics research group at Kaunas University of Technology. Her research interests are in the areas of risk assessment, financial services development, financial institution management, and business financing sources rationing. ORCID iD 0000-0003-1130-2592.
Lina Sineviciene, Kaunas University of Technology, Lithuania

Lina Sineviciene, Dr., is an Associate Professor at the School of Economics and Business and a member of the Sustainable Economics research group at Kaunas University of Technology. Her research interests focus on relationship between fiscal policy and private investment, public finance, environmental economics, investment in green technologies, and corporate financial management. ORCID iD 0000-0003-2844-2751.
Andrzej Buszko, Pomeranian UniPomeranian University in Słupsk, Institute of Management, Poland

Andrzej Buszko, Ph.D. Habil, is a Professor at Pomeranian University. His research interests include the shadow economy, financial management, and institutional economy. He is a member of the Scientific Board of United Nation Global Compact Network and Doctor honoris causa of Tajik State University of Commerce. ORCID: https://orcid.org/0000-0003-0600-4646.