A Modified Genetic Fuzzy Neural Network with Application to Financial Distress Analysis

Neural networks have been widely used to solve financial distress problems because of their excellent performances of treating non-linear data with self-learning capability. However, the shortcoming of NNs is also significant due to the "black box" syndrome. Moreover, in many situations NNs more or less suffer from the slow convergence and occasionally involve in a local optimal solution, which strongly limited their applications in practice. To overcome NN\´s drawbacks, this paper presents a hybrid system that merges the three evolution techniques, i.e. neural networks, fuzzy logic and genetic algorithms, into a comprehensive model, named as a modified genetic fuzzy neural network (GFNN). Furthermore, the new model has been applied to financial distress analysis based on the data collected from a set of Chinese listed corporations, and the results indicate that the performance of GFNN model is much better than the one of NN model.