Bankruptcy Prediction as for the Russian Companies

The goal of this paper is to construct a statistical model for bankruptcy prediction of Russian companies, based on the composed sample and a list of financial ratios of the firms, which would most likely give the best estimates of default probability. On the basis of the goal, the following tasks must be solved: analyze the advantages and disadvantages of existing foreign and Russian models of default prediction; to choose the relevant statistical approach for the analysis; select a sample of financial ratios calculated on the basis of financial statements, analyze the sample and identify the most important factors for the models; and, finally, choose the best combination of factors for the model, so that it would have the highest available prediction power. The practical part of the work will be of constructing one statistical model for predicting bankruptcy from 1 year prior default to 4 years on the basis of the data taken from the building sector of the Russian economy, which is currently one of the riskiest in respect to default. The paper is divided into 3 chapters: the first one is devoted to the theoretical framework of the event of default and to the overview of the existing models in the Western countries and in Russia as well; the second one is devoted to the sample choice, data collection and all the difficulties faced; the third chapter shows the results obtained from the statistical analysis performed in practice.