Affiliation:
1. Faculty of Management and Business, University of Prešov, Konštantínova 16, 080 01 Prešov, Slovakia
Abstract
Predicting the risk of corporate bankruptcy is one of the most important challenges for researchers dealing with the issue of financial health evaluation. The risk of corporate bankruptcy is most often assessed with the use of early warning models. The results of these models are significantly influenced by the financial features entering them. The aim of this paper was to select the most suitable financial features for bankruptcy prediction. The research sample consisted of enterprises conducting a business within the Slovak construction industry. The features were selected using the domain knowledge (DK) approach and Least Absolute Shrinkage and Selection Operator (LASSO). The performance of VRS DEA (Variable Returns to Scale Data Envelopment Analysis) models was assessed with the use of accuracy, ROC (Receiver Operating Characteristics) curve, AUC (Area Under the Curve) and Somers’ D. The results show that the DK+DEA model achieved slightly better AUC and Somers’ D compared to the LASSO+DEA model. On the other hand, the LASSO+DEA model shows a smaller deviation in the number of identified businesses on the financial distress frontier. The added value of this research is the finding that the application of DK features achieves significant results in predicting businesses’ bankruptcy. The added value for practice is the selection of predictors of bankruptcy for the analyzed sample of enterprises.
Funder
Scientific Grant Agency of the Ministry of Education, Science, Research and Sport of the Slovak Republic and the Slovak Academy of Sciences
Subject
Strategy and Management,Economics, Econometrics and Finance (miscellaneous),Accounting
Reference129 articles.
1. Predicting corporate financial distress: A neural networks approach;Abid;Finance India,2002
2. A statistical model of financial risk bankruptcy applied for Romanian manufacturing industry;Achim;Procedia Economics and Finance,2012
3. Adisa, Juliana Adeola, Ojo, Samuel Olusegun, Owolawi, Pius Adewale, and Pretorius, Agnieta Beatrijs (, January November). Financial Distress Prediction: Principle Component Analysis and Artificial Neural Networks. Paper presented at 2019 International Multidisciplinary Information Technology and Engineering Conference (IMITEC), Vanderbijlpark, South Africa.
4. Predicting US Banks Bankruptcy: Logit Versus Canonical Discriminant Analysis;Affes;Computational Economics,2019
5. Aghaie, Arezoo, and Saeedi, Ali (, January April). Using Bayesian Networks for Bankruptcy Prediction: Empirical Evidence from Iranian Companies. Paper presented at 2009 International Conference on Information Management and Engineering, Kuala Lumpur, Malaysia.