A Particle Swarm Optimized Fuzzy Neural Network for Credit Risk Evaluation

Neural networks (NNs) have been widely used to financial risk management because of their excellent performances of treating non-linear data with self-learning capability. However, the shortcoming of neural networks is also significant due to a "black box" syndrome and the difficulty in dealing with qualitative information, which limited its applications in practice. To overcome these drawbacks of NNs, in this study a particle swarm optimized fuzzy neural network (PSO-FNN) are proposed to evaluate credit risk. the results indicate that the predictive accuracies obtained from PSO-FNN are much higher than the ones obtained from NNs. To make this clearer, an illustrative example is also demonstrated in this study.