Predicting bankruptcy using neural networks in the current financial crisisa study for US commercial banks

Resumo

We develop a model of neural network to study the bankruptcy of banks in the US in 2009. We provide a new model to predict bank defaults some time before the bankruptcy happens, taking into account the specific features of the current financial crisis. Based on data from the Federal Deposit Insurance Corporation our results corroborate the higher credit risk taken by distressed banks, and their heavier concentration on real estate. Interestingly, distressed banks do not show lower cost efficiency than their wealthy counterparts, so that bank failures seem to be a consequence of careless bank strategies rather than low cost efficiency. After drawing the profile of distressed banks, we use our model to predict possible future bankruptcies and we test the performance of the model by comparing our predictions with the actual bankruptcies between January and June 2010. Our model shows a high discriminant power and is able to differentiate correctly wealthy and distressed banks. More specifically, our model would have been able to predict in December 2009around 60% of failures happened in 2010.