MDA financial distress prediction model for selected Balkan countries

Abstract

The issue of company financial distress and the early prediction of potential bankruptcy is one of the most discussed issues of economists around the world in recent decades. The most widely used method to create these models is Multidimensional Discrimination Analysis from the first attempts in the 1960s to the present. In the paper we present prediction model for some emerging market countries in Balkan region created using a Multidimensional Discriminant Analysis method based on real data from the financial statements obtained from Amadeus - A database of comparable financial information for public and private companies across Europe. Our database contains data more than 200 000 companies and about 25 predictors. Using this model, it is possible to predict the financial difficulties of companies one year in advance.

Mda Financial Distress Prediction Model for Hungarian Companies

“…We used the random division in the most frequently used ratio of 80:20. [16] Another approach to analyse the quality of financial distress prediction model is using or Receiver Operating Characteristic (ROC) curve. The ROC curve gives an image of the behaviour of the created model.…”