Financial distress prediction using cutting-edge statistical techniques

Financial distress is a real-world problem that affects numerous businesses the world over.Consequences of such an occurrence can go beyond the business owners and stakeholders – as we saw in the 2008 GFC, it can lead to a much larger macroeconomic calamity. Therefore, having the power to predict – and hence aid businesses from failing, has the potential to save not only the company, but whole countries from collapsing. This paper will adopt financial data from hundreds of Australian companies to work on advancing financial distress prediction modelling by utilizing cutting-edge statistical models, namely: Decision Trees, TreeNet, and Random Forests, to test for the most accurate model in financial distress prediction. The paper will also test whether this accuracy can be improved when the companies are segregated according to their respective industries. There are many gains from the study, including aiding lenders in accurately assessing loan-giving to prospective borrowers, providing investors with invaluable insight on their investment, and the potential to aid the economy as a whole not to fall into a recession or slump as a result of increased business failure.