Testing Currency Predictability Using An Evolutionary Neural Network Model

Andreou, A. and Georgakopoulos, E. and Likothanassis, S. and Zombanakis, George A. (1998): Testing Currency Predictability Using An Evolutionary Neural Network Model. Published in: Proceedings of the International Conference on Forecasting Financial Markets, BNP/Imperial College , Vol. 1, No. 1 (15 May 1998): pp. 1-23.

Abstract

Two alternative learning approaches of a MLP Neural Network architecture are employed to forecast foreign currencies against the Greek Drachma, a Back-Propagation with a hyperbolic tangent activation scheme and an evolutionary trained model. Four major currency data series, namely the U. S. Dollar, the British Pound, the French Franc and the Deutsche Mark, are used in this forecasting experiment. Extended simulations have shown a high predictive ability, which is significantly better when using the actual rates compared to using the logarithmic returns of each series. The genetic algorithm performs best on FF and DM, while the back-propagation on USD and BP.

• Item Type: MPRA Paper
• Language: English
• Keywords: Currency Forecasting Artificial Neural Networks
• Subjects: F - International Economics > F3 - International Finance > F31 - Foreign Exchange; F - International Economics > F4 - Macroeconomic Aspects of International Trade and Finance > F47 - Forecasting and Simulation: Models and Applications

References

Adamopoulos, A., Andreou, A., Georgopoulos E.and Likothanassis, S. (1997) “Currency forecasting using recurrent RBF networks optimized by genetic algorithms”. Proceedings of the Fifth International Conference on Computational Finance, London Business School, London, 1997.

Andreou, A., Georgopoulos, E., Likothanassis, S. and Polidoropoulos, P. (1997) “Is the Greek foreign exchange-rate market predictable? A comparative study using chaotic dynamics and neural networks”. Proceedings of the Fourth International Conference on Forecasting Financial Markets, Banque Nationale de Paris and Imperial College, London.

Bank of Greece (1984) “Report of the Governor”, Athens.

Bank of Greece (1986) “Report of the Governor”, Athens.

Bank of Greece (1991) “Report of the Governor”, Athens.

Bank of Greece (1994) “Report of the Governor”, Athens.

Bank of Greece (1997) Annual Monetary Program Announcement, Athens.

Brissimis S. N. and J. A. Leventakis (1989) “The Effectiveness of Devaluation: A General Equilibrium Assessment with Reference to Greece”, Journal of Policy Modelling, 11(2), pp.247-271.

Karadeloglou P. (1990) “On the Existence of an Inverse J-curve”, Greek Economic Review, V.12,2, p.p. 285-305.

Karadeloglou P., C. Papazoglou, G. A. Zombanakis (1998) “Is the Exchange Rate An Effective Anti-Inflationary Instrument, Economia, Vol. 2, 1 1998 p.p. 47-72.

Likothanassis, S. D., Georgopoulos, E. and Fotakis, D. (1997) “Optimizing the Structure of Neural Networks using Evolution Techniques”, Proceedings of the 5th Intern. Conf. on HPC in Engineering, Spain, 4-7 July.

Michalewicz, Z. (1994) “Genetic Algorithms + Data Structures = Evolution Programs”, Second Ext. Edition, Springer Verlag.

Papaioannou, G. and Karytinos, A. (1995) Nonlinear time series analysis of the stock exchange: The case of an emerging market. International Journal of Bifurcation and Chaos 5, 1557-1584.

Yao, X., “A Review of Evolutionary Artificial Neural Networks”, International Journal of Intelligent Systems, vol. 8, pp. 539 – 567.

Zombanakis G. A. (1998) “Is The Greek Exporters’ Price Policy Asymmetric?”, Greek Economic Review Vol. 19, 1 1998.