Exchange-Rates Forecasting: A Hybrid Algorithm Based on Genetically Optimized Adaptive Neural Networks

作     者：Andreou, Andreas S. Georgopoulos, Efstratios F. Likothanassis, Spiridon D. 

作者机构：Department of Computer Science University of Cyprus CY1678 Nicosia 75 Kallipoleos Str. P.O. Box 20537 Cyprus Department of Computer Engineering and Informatics University of Patras Patras 26500 Greece Computer Technology Institute 2622 1 Patras 3 Kolokotroni Str. Greece 

出 版 物：《Computational Economics》 (Comput. Econ.)

年 卷 期：2002年第20卷第3期

页      面：191-210页

学科分类：0202[经济学-应用经济学] 1202[管理学-工商管理] 0201[经济学-理论经济学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：exchange-rates filtering forecasting genetic algorithms neural networks 

摘      要：The use of neural networks trained by a new hybrid algorithm is employed on forecasting the Greek Foreign Exchange-Rate Market. Four major currencies, namely the U. S. Dollar (USD), the Deutsche Mark (DEM), the French Franc (FF) and the British Pound (GBP), versus the Greek Drachma, were used as experimental data. The proposed algorithm combines genetic algorithms and a training method based on the localized Extended Kalman Filter (EKF), in order to evolve the structure and train Multi-Layered Perceptron (MLP) neural networks. The goal of this effort is to predict, as accurately as possible, exchange-rates future behavior. Simulation results show that the method gives highly successful results, while the diversification of the structure between the four currencies has no effect on the performance. © 2002 Kluwer Academic Publishers.