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.

[1]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[2]  R. Eberhart,et al.  Fuzzy adaptive particle swarm optimization , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[3]  M. Rast.  Forecasting financial time series with fuzzy neural networks , 1997, 1997 IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335).

[4]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  James Kennedy,et al.  The particle swarm: social adaptation of knowledge , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[6]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[7]  Eivind Bernhardsen,et al.  Model for Analysing Credit Risk in the Enterprise Sector , 2001 .

[8]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[10]  W. Perraudin,et al.  Regulatory implications of credit risk modelling , 2000 .