Managing in Uncertainty: Theory and Practice pp 93-101 | Cite as
Evaluation of a Neuro-Fuzzy Scheme Forecasting Exchange Rates
Abstract
A Neuro-fuzzy windowing scheme is applied to predict exchange rates. By using a hybrid learning procedure an input-output mapping can be constructed based on training data pairs. The scheme applies the ANFIS (Adaptive-Network-based Fuzzy Inference System) algorithm which is based on the least-squares method and the back-propagation gradient descent for identifying linear and nonlinear parameters, respectively, in a Sugeno-type fuzzy inference system. The retraining is performed in a moving window of input data, thus keeping track of the latest changes. An evaluation of the scheme for a short-term prediction interval is performed using real exchange rates of USD vs. GRD, DEM, FRF and ECU.
Keywords
Forecast Exchange rate Fuzzy logic Fuzzy inference system Adaptive networksPreview
Unable to display preview. Download preview PDF.
References
- Bosarge W. Jr (1993), “Adaptive Processes to Exploit the Non-linear structure of Financial Markets”, in: R. Trippi and E. Turban (eds.), Neural Networks in Finance and Investing, Probus Publishing, 465–492.Google Scholar
- Iebeling, K. and Milton B. (1996), “Designing a neural network for forecasting financial and economic time series”, Neurocomputing 10/3, 215–236.Google Scholar
- Jang R. (1991), “Fuzzy modeling using generalized neural networks”, Prot: 4 th IFSA World Congress. Google Scholar
- Kane R. and Milgram M. (1994), “Financial forecasting and rules extraction from trained networks”, Proceedings of the 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA, 3190–3195.CrossRefGoogle Scholar
- Medsker L., Turban E. and Trippi, R. (1993), “Neural network fundamentals for financial analysts”, in: R. Trippi and E. Turban (eds.), Neural Networks in Finance and Investing, Probus Publishing, 3–27.Google Scholar
- Parker D.B. (1987), “Optimal algorithms for adaptive networks: Second order back propagation, second order direct propagation and second order Hebbian learning”, Proc. IEEE Int. Conf. Neural Networks, 593–600.Google Scholar
- Refenes A. (1993), “Constructive learning and its application to currency exchange rate forecasting”, in: R. Trippi and E. Turban (eds.), Neural Networks in Finance and Investing, Probus Publishing, 465–492.Google Scholar
- Jang, R. (1993), “ANFIS: Adaptive-Network-Based Fuzzy Inference System”, IEEE Transactions on Systems, Man and Cybernetics 23/3, 665–685.CrossRefGoogle Scholar
- Takagi H. and Sugeno, M. (1983), “Derivation of fuzzy control rules from human operator’s control actions”, Proc. IF AC Symp. Fuzzy Inform., Knowledge Representation and Decision Analysis, 55–60.Google Scholar
- Weigend, A.S., Rumelhar D.E. and Huberman, B.A. (1990), “Back propagation weight-elimination and time series prediction”, in: Touretzky D., Hinton G. and T. Sejnowski (eds.), Proc. 1990 Connectionist Models Summer School, Carnegie Mellon University, 105–116.Google Scholar
- Weigend, A.S., Rumelhar D.E. and Huberman, B.A. (1991), “Generalization by weight-elimination with application to forecasting” in: D. Touretzky (ed.), Advances in Neural Information Processing Systems III, San Mateo, 875–882.Google Scholar
- Yaser, A. and Amir, F. (1996), “Introduction to financial forecasting”, Applied Intelligence 6/3, 205–213.Google Scholar