Bankruptcy Prediction of Privately Held SMEs Using Feature Selection Methods

64 Pages Posted: 27 Aug 2021 Last revised: 20 Jun 2022

See all articles by Florentina Paraschiv

Florentina Paraschiv

Zeppelin University, Chair of Finance; Norwegian University of Science and Technology, Faculty of Economics and Management, NTNU Business School; University of St. Gallen, Institute for Operations Research and Computational Finance

Markus Schmid

University of St. Gallen - Swiss Institute of Banking and Finance; University of St. Gallen - School of Finance; Swiss Finance Institute

Ranik Raaen Wahlstrøm

NTNU Business School, Norwegian University of Science and Technology

Date Written: June 17, 2022

Abstract

In this paper, we test alternative feature selection methods for bankruptcy prediction and illustrate their superiority versus popular models used in the literature. We test these methods using a comprehensive dataset of more than one million financial statements covering the entire universe of privately held Norwegian SMEs in 2006-2017. Our methods can choose among 155 accounting-based input variables derived from prior literature. We find that the input variables chosen by an embedded least absolute shrinkage and selection operator (LASSO) method yield the best in-sample fit and out-of-sample performance. We show in a simulation, which mimics a real-world competitive credit market, that using LASSO to choose bankruptcy predictors improves credit risk pricing and decision making, resulting in significantly higher bank profits. Finally, we show that model performance can be further improved by running feature selection methods on sub-sets of the company universe, such as for example within-industry.

Keywords: Bankruptcy prediction, Feature selection methods, LASSO, Deep learning, Bank profitability

JEL Classification: G33, G17, M41, C25

Suggested Citation

Paraschiv, Florentina and Schmid, Markus and Wahlstrøm, Ranik Raaen, Bankruptcy Prediction of Privately Held SMEs Using Feature Selection Methods (June 17, 2022). Available at SSRN: https://ssrn.com/abstract=3911490 or http://dx.doi.org/10.2139/ssrn.3911490

Florentina Paraschiv

Zeppelin University, Chair of Finance ( email )

Am Seemooser Horn 20
Friedrichshafen, 88045
Germany

Norwegian University of Science and Technology, Faculty of Economics and Management, NTNU Business School ( email )

Klæbuveien 72
Trondheim, NO-7030
Norway

University of St. Gallen, Institute for Operations Research and Computational Finance ( email )

Bodanstrasse 6
St. Gallen, 9000
Switzerland

Markus Schmid (Contact Author)

University of St. Gallen - Swiss Institute of Banking and Finance ( email )

Unterer Graben 21
St. Gallen, 9000
Switzerland

University of St. Gallen - School of Finance ( email )

Unterer Graben 21
St.Gallen, CH-9000
Switzerland

Swiss Finance Institute

c/o University of St. Gallen
Dufourstrassse 50
St. Gallen, SG 9000
Switzerland

Ranik Raaen Wahlstrøm

NTNU Business School, Norwegian University of Science and Technology ( email )

Trondheim, 7491
Norway

HOME PAGE: http://www.ntnu.edu/employees/ranik.raaen.wahlstrom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
144
Abstract Views
1,575
rank
276,342
PlumX Metrics