Predicting Business Bankruptcy: A Comprehensive Case Study

Predicting Business Bankruptcy: A Comprehensive Case Study

Rui Sarmento (FEUP, University of Porto and Gallicyadas, Porto, Portugal), Luís Trigo (FLUP, University of Porto and Gallicyadas, Porto, Portugal) and Liliana Fonseca (FEP, University of Porto, Porto, Portugal)
DOI: 10.4018/IJSODIT.2016070105
OnDemand PDF Download:
No Current Special Offers


Managers, investors, financial institutions and government agencies have a major concern on forecasting enterprise bankruptcy. It enables the sustainability assessment of critical suppliers and clients, as well as competitors and the business environment. Throughout the 20th and the 21st century, advances in statistics and computer science fields enabled the development of different trends in financial distress assessment that co-exist today. However, recent Data Mining (DM) techniques are regarded as being the most precise. IT expertise requirements in the constantly evolving DM field may have been a major obstacle to the adoption of these techniques by decision makers. Furthermore, DM software tools that are now widespread offer a broad spectrum of Artificial Intelligence algorithms and the most difficult task may be the decision of selecting the appropriate algorithm. Hence, the adoption of a good workflow method for data processing and analysis is critical for having fast and reliable results. This work presents an overview of the available bankruptcy techniques and provides a comprehensive case study exploring the latest Data Mining techniques.
Article Preview

In this section, we provide related background to the business bankruptcy prediction task. Additionally, we provide an introduction to classification algorithms data analysts frequently use in prediction tasks. Some of these algorithms will be used in our case study.

Empirical models to predict corporate bankruptcy and bankruptcy theories have been different strands of research. However different paths have a substantial amount of overlap (Scott, 1981).

The literature in the field dates back to the 1930's with the analysis of single financial ratios for specific purposes and industry (Bellovary et al., 2007). With no advanced statistical methods, analysts only compared failed and non-failed companies and noticed that failed companies had worst performance ratios.

Beaver (1966) introduced a statistical perspective in univariate ratio analysis. From the 30 selected ratios, only six were significant:

  • Cash Flow / Total Debt

  • Net Income / Total Assets

  • (Current + Long-term Liabilities) / Total Assets

  • Working Capital / Total Assets

  • Current Ratio

  • No-credit Interval

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 6: 1 Issue (2017)
Volume 5: 2 Issues (2016)
Volume 4: 2 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing