Default Prediction for Small-Medium Enterprises: Evidence from Russia

The chief aim of this paper is to compare performance of different statistical models of bankruptcy prediction for Russian private small and medium-sized companies prior and subsequent to the economic crisis of 2008 --- 2009. We use the following methods: Linear Discriminant Analysis, Quadratic Discriminant Analysis, Mixture Discriminant Analysis, Logistic Regression, Probit Regression, Support Vector Machine, Tree and Random Forest.Our dataset comprises about 1 000 000 observations from the Ruslana database and covers the period from 2004 to 2012. The definition of default is extended to financial difficulties by adding voluntary liquidated firms to those liquidated as a result of legal bankruptcy.Heterogeneity of Russian companies is taken into account in several ways. We study four industries in detail: construction, manufacturing, real estate activities, retail and wholesale trade. In addition to financial ratios derived from financial statements we include non-financial variables such as regional distribution, age, size and legal form into statistical models.Evaluation of the prediction performance is done with the help of out-of-sample forecasts. We obtain models with high predictive power, area under ROC curve reaches 0.8. Random Forest outperformed all applied methods. Adding non-financial information such as age, federal region, company size leads to the improved forecasts while legal form does not have a great impact on the outcome. Among financial measures liquidity, profitability and leverage ratios turned out to be essential. Moreover, our models captured structural changes some of which were likely to be caused by crisis of 2008 --- 2009.This research will be of vital importance especially to banks and other credit organisations providing loans to small and medium businesses.