A large number of studies on bankruptcy prediction are published every year. The topic of SME failure prediction has evolved over the past decades into a relevant research area that has grown exponentially across many disciplines, including finance and management, for obvious reasons. This has been motivated by the massive toll on SMEs caused by the global crisis of 2007-2009, the recent COVID-19 crisis and the resulting need to update indicators of SME failure. Many authors during the last fifty years have examined several possibilities to predict business failure. They have studied bankruptcy prediction models under different perspectives but still could not indicate the most reliable model. This paper focuses on the Czech economy, specifically at small and medium-sized enterprises (SMEs).
This article aims to find if there exist different factors that could predict bankruptcy for manufacturing and commercial companies. Considering the research objective, the following hypotheses were set: H1: Indicators used in the financial distress model for manufacturing companies differ from commercial companies.; H2: Applying a model based on different segmentation criteria improves the reliability of bankruptcy prediction.
It is the ongoing research about the value of several popular bankruptcy models that are often applied, namely the Altman Z-score, the Ohlson O-score, the Zmijewski's model, the Taffler's model, and the IN05 model. The logistic regression has been used to investigate around 1800 companies, of which 308 failed during 2010 – 2017.
Reached results confirm both hypotheses and some suggestions arise from it. When we develop a bankruptcy model, it is necessary to sort companies according to different criteria. It also confirms findings of the last years literature review the closer the similarity of businesses, the greater accuracy of bankruptcy models. Further, it is required to exploit common used financial indicators with a combination of modified indicators to assess the probability of bankruptcy precisely.