Failure prediction in the Russian bank sector with logit and trait recognition models

The Russian banking sector experienced considerable turmoil in the late 1990s, especially around the Russian banking crisis in 1998. The question is what types of banks are vulnerable to shocks and whether or not bank-specific characteristics can be used to predict vulnerability to failures. In this study we employ a parametric logit model and a nonparametric trait recognition approach to predict failures among Russian commercial banks. We modify the trait recognition approach such that the default probabilities are calculated directly without preliminary classification of cells in the voting matrix as safe or unsafe. We test the predictive power of the models based on their prediction accuracy using holdout samples. All models performed better than the benchmark; the modified trait recognition approach outperformed logit and the traditional trait recognition approach in both the original and the holdout samples. As expected liquidity plays an important role in bank failure prediction, but also asset quality and capital adequacy turn out to be important determinants of failure.