Forecasting exchange rates using an evolutionary neural network

Author: Alvarez-Diaz Marcos   Alvarez Alberto  

Publisher: Routledge Ltd

ISSN: 1744-6546

Source: Applied Financial Economics Letters, Vol.3, Iss.1, 2007-01, pp. : 5-9

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

In this article, we employ an Evolutionary Neural Network to forecast exchange rates returns for the Japanese Yen and the British Pound against the US dollar. This method combines genetic programming and neural network methodologies. Empirical results show the existence of a short-term weak predictable structure for both currencies. Therefore, they do not support the hypothesis that the exchange rates follow a random walk and that returns are unpredictable.