Study of Discrete Choice Models and Artificial Intelligence Approaches in the Prediction of Economic Crises

We examine various and different approaches for the prediction of economic crisis periods of US economy. We examine the traditional econometric discrete choice Logit and Probit models then a feed-forward neural network (FFNN) model and finally we apply an Adaptive Neuro-Fuzzy Inference System (ANFIS). We examine the period 1950-2009, where we take as the in-sample or training period 1950-2005, while 2006-2009 is obtained as the out-of-sample or the testing period. We find that ANFIS in the out-of-sample period outperforms significant the other approaches followed by FFNN and Probit, while Logit presents the lowest forecasting performance. Our findings indicate that artificial procedures combining fuzzy logic and neural networks can be superior to simple neural networks or discrete choice models