A Modified Particle Swarm Algorithm Combined with Fuzzy Neural Network with Application to Financial Risk Early Warning

Particle Swarm Optimization (PSO) algorithm and Fuzzy Neural Network (FNN) system has been widely used to solve complex decision making problems in practice. However, both of them more or less suffer from the slow convergence and occasionally involve in a local optimal solution. To overcome these drawbacks of PSO and FNN, in this study a modified particle swarm optimization algorithm (MPSO) is developed and then combined with neural network to optimize the network weight training process. Furthermore, the new MPSO-FNN model has been applied to financial risk early warning problem, and the results indicate that the predictive accuracies obtained from MPSO-FNN are much higher than the ones obtained from original FNN system. To make this clearer, an illustrative example is also demonstrated in this study. It seems that the proposed new comprehensive evolution algorithm may be an efficient forecasting system in financial time series analysis.