IJPAM: Volume 107, No. 1 (2016)
DIFFERENTIAL NEURAL NETWORKS WITH
AN EXTENDED TRACKING PROCEDURE


Francisco Venegas-Martínez


Calle Augusto Rodin 498, Benito Juárez, Insurgentes Mixcoac, C.P.03920
México City, MÉXICO

Av. Acueducto de Guadalupe S/N, Gustavo A Madero, Barrio La Laguna Ticoman, C.P.07340
México City, MÉXICO

Plan de Agua Prieta 66, Delegación Miguel Hidalgo, Colonia Plutarco Elás Calles, C.P.11350
México City, MÉXICO
Abstract. This paper develops a new kind of non-parametrical artificial neural network useful to forecast exchange rates. We departure from the Differential Neural Networks (DNN) framework and extend the tracking procedure. Under this approach, we examine daily closing exchange rates of Euro against US dollar, Japanese yen and British pound. With our proposal, extended DNN or EDNN, we perform the tracking procedure from February 15, 1999, to August 31, 2013, and, subsequently, the forecasting procedure from September 2 to September 13, 2013. The accuracy of the obtained results is remarkable, since the error percentage in the forecasting period varies from 0.001.
Received: December 31, 2015
AMS Subject Classification: 92B20, 82C32, 68T05
Key Words and Phrases: exchange rates, artificial neural network, differential neural network, tracking and forecasting
Download paper from here.
DOI: 10.12732/ijpam.v107i1.8 How to cite this paper?
Source: International Journal of Pure and Applied Mathematics
ISSN printed version: 1311-8080
ISSN on-line version: 1314-3395
Year: 2016
Volume: 107
Issue: 1
Pages: 87 - 110
Google Scholar; DOI (International DOI Foundation); WorldCAT.
This work is licensed under the Creative Commons Attribution International License (CC BY).