A fuzzy neural network model with application to Financial Risk Early Warning

The traditional financial risk warning model are all based on probability theory and statistical analysis, but the precisions of the results are usually not satisfied in practice. In this study, rough set theory is first used to evaluate factors and then the key factors are selected as inputs to construct a neural network model combined with fuzzy rules. Furthermore, the fuzzy neural network (FNN) model is applied to Financial Risk Early Warning(FREW) problem. The results indicate that the predictive accuracies obtained from FNN are much higher than the ones obtained from NN system. To make this clearer, an illustrative example is given for demonstration.