Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/13832
Title: Exchange-Rates Forecasting: A Hybrid Algorithm Based on Genetically Optimized Adaptive Neural Networks
Authors: Likothanassis, Spiridon D. 
Georgopoulos, Efstratios F. 
Andreou, Andreas S. 
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: exchange-rates;filtering;forecasting;genetic algorithms;neural networks
Issue Date: Dec-2002
Source: Computational Economics, 2002, vol. 20, no. 3, pp. 191–210
Volume: 20
Issue: 3
Journal: Computational Economics 
Abstract: 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.
ISSN: 0927-7099
DOI: 10.1023/A:1020989601082
Rights: © 2002 Springer Nature
Type: Article
Affiliation : University of Cyprus 
University of Patras 
Computer Technology Institute 
Appears in Collections:Άρθρα/Articles

CORE Recommender
Show full item record

SCOPUSTM   
Citations 10

37
checked on Aug 31, 2020

Page view(s)

30
Last Week
0
Last month
0
checked on Oct 25, 2020

Google ScholarTM

Check

Altmetric


Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.