Welcome to the InfoSci Platform
Reference Hub2
An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates

An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates

Salim Lahmiri
Copyright: © 2015 |Pages: 17
ISBN13: 9781466672727|ISBN10: 1466672722|EISBN13: 9781466672734
DOI: 10.4018/978-1-4666-7272-7.ch022
Cite Chapter Cite Chapter

MLA

Lahmiri, Salim. "An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates." Handbook of Research on Organizational Transformations through Big Data Analytics, edited by Madjid Tavana and Kartikeya Puranam, IGI Global, 2015, pp. 380-396. https://doi.org/10.4018/978-1-4666-7272-7.ch022

APA

Lahmiri, S. (2015). An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates. In M. Tavana & K. Puranam (Eds.), Handbook of Research on Organizational Transformations through Big Data Analytics (pp. 380-396). IGI Global. https://doi.org/10.4018/978-1-4666-7272-7.ch022

Chicago

Lahmiri, Salim. "An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates." In Handbook of Research on Organizational Transformations through Big Data Analytics, edited by Madjid Tavana and Kartikeya Puranam, 380-396. Hershey, PA: IGI Global, 2015. https://doi.org/10.4018/978-1-4666-7272-7.ch022

Export Reference

Mendeley
Favorite

Abstract

This chapter applies the Backpropagation Neural Network (BPNN) trained with different numerical algorithms and technical analysis indicators as inputs to forecast daily US/Canada, US/Euro, US/Japan, US/Korea, US/Swiss, and US/UK exchange rate future price. The training algorithms are the Fletcher-Reeves, Polak-Ribiére, Powell-Beale, quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), and the Levenberg-Marquardt (LM). The standard Auto Regressive Moving Average (ARMA) process is adopted as a reference model for comparison. The performance of each BPNN and ARMA process is measured by computing the Mean Absolute Error (MAE), Mean Absolute Deviation (MAD), and Mean of Squared Errors (MSE). The simulation results reveal that the LM algorithm is the best performer and show strong evidence of the superiority of the BPNN over ARMA process. In sum, because of the simplicity and effectiveness of the approach, it could be implemented for real business application problems to predict US currency exchange rate future price.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.