Munich Personal RePEc Archive

Modeling And Forecasting Exchange-Rate Shocks

Andreou, A. S. and Zombanakis, George A. and Likothanassis, S. D. and Georgakopoulos, E. (1998): Modeling And Forecasting Exchange-Rate Shocks. Published in: Proceedings of the 60th BNP/Applied Econometrics Association , Vol. 1, No. Special Issue on Financial Instruments and Emerging Markets (6 June 1998): pp. 1-29.

[img]
Preview
PDF
MPRA_paper_51539.pdf

Download (337kB) | Preview

Abstract

This paper considers the extent to which the application of neural networks methodology can be used in order to forecast exchange-rate shocks. Four major foreign currency exchange rates against the Greek Drachma as well as the overnight interest rate in the Greek market are employed in an attempt to predict the extent to which the local currency may be suffering an attack. The forecasting is extended to the estimation of future exchange rates and interest rates. The MLP proved to be highly successful in predicting the shocks, while exhange-rates and interest-rates forecasts with MLP and RBF optimized by a genetic algorithm resulted in good approximations.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.