Published

2007-09-01

Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate

Entrenamiento de una red neuronal multicapa para la tasa de cambio euro - dólar (EUR/USD)

DOI:

https://doi.org/10.15446/ing.investig.v27n3.14851

Keywords:

artificial neural network, chemotaxis, FOREX, trading strategy (en)
chemotaxis, estrategias de negociación, Forex, redes neuronales artificiales, redes multicapa, JEL, F310, C450 (es)

Authors

  • Jaime Alberto Villamil Torres Bancolombia
  • Jesús Alberto Delgado Rivera Universidad Nacional de Colombia

A mathematical tool or model for predicting how an economic variable like the exchange rate (relative price between two currencies) will respond is a very important need for investors and policy-makers. Most current techniques are based on statistics, particularly linear time series theory. Artificial neural networks (ANNs) are mathematical models which try to emulate biological neural networks’ parallelism and nonlinearity; these models have been successfully applied in Economics and Engineering since the 1980s. ANNs appear to be an alternative for modelling the behavior of financial variables which resemble (as first approximation) a random walk. This paper reports the results of using ANNs for Euro/USD exchange rate trading and the usefulness of the algorithm tor chemotaxis leading to training networks thereby maximising an objective function re predicting a trader’s profits. JEL: F310, C450.

Tanto para los inversionistas como para las autoridades económicas es necesario que se desarrolle una herramienta matemática que logre dar cuenta de la dirección de una variable como el tipo de cambio (el precio relativo entre dos monedas). Muchos de los mecanismos usados actualmente están basados en el uso de técnicas estadísticas, en particular series de tiempo lineales. Las redes neuronales artificiales (RNA) son modelos matemáticos que pretenden emular el funcionamiento del cerebro humano, su aplicación en economía e ingeniería surge a finales de los años ochenta con buenos resultados. Las RNA se presentan como una alternativa para simular el comportamiento de variables financieras que, por lo general, tienden a parecerse a un paseo aleatorio. En este trabajo se muestran los resultados del entrenamiento de una red neuronal para negociación de la tasa de cambio EUR/USD y las bondades del algoritmo de entrenamiento chemotaxis, que permite entrenar redes que maximicen una función objetivo que relacione aciertos en la predicción con las ganancias de un trader.

References

Bremermann, H.J, Anderson, R.W., How the Brain Adjusts Synapses -Maybe., En: Automated Reasoning. Essays in Honor of Woody Bledsoe, Robert S. Boyer (Ed.), Boston, Kluwer Academic Publishers, 1991. DOI: https://doi.org/10.1007/978-94-011-3488-0_6

Delgado, A., Inteligencia Artificial y MiniRobots., Bogotá, Ecoe Ediciones, 1998.

Delgado, A., Control of Nonlinear Systems Using a Self-Organising Neural Network., Neural Computing & Applications, No. 9, 2000, pp. 113-123. DOI: https://doi.org/10.1007/s005210070022

Dunis, C., Willians, M., Modelling and Trading the EUR/USD Exchange Rate: Do Neural Network Models Perform Better? Liverpool Business School, Working Paper, 2002. Disponible en: www.cibef.com

Fama. E., The Behaviour of Stock Market Prices., Journal of Business, No. 38, 1969, pp. 34-105. DOI: https://doi.org/10.1086/294743

Fama. E., Efficient Capital Markets: A Review of Theory and Empirical Work., Journal of Finance, N° 25, 1970, pp. 383-417. DOI: https://doi.org/10.1111/j.1540-6261.1970.tb00518.x

Funahashi, K.Y., On the Approximate Realization of Continuous Mapping by Three Neural Networks., Electronics and Communications in Japan, Part 3, No.73, 1989, pp. 61-68. DOI: https://doi.org/10.1002/ecjc.4430731107

Gibb, J., Back Propagation Family Album., Technical Report C/TR96-05, Macquarie University, August, 1996. Disponible en: http://citeseer.ist.psu.edu/gibb96back.html

Haykin, S., Neuronal Networks: A Comprehensive Foundation, New York, McMillan College Publishing Company, 1994.

Kröse, B., van der Smagt, P., An Introduction to Neural Networks, The University of Amsterdam. November, 1996. Disponible en: http://citeseer.ist.psu.edu/ose96introduction.html

Kuan, C-M., Liu, T., Forecasting Exchange Rates using Feedforward and Recurrent Neural Networks., Journal of Applied Econometrics, Vol 10, 1995, pp. 347-364. DOI: https://doi.org/10.1002/jae.3950100403

McCulloch, W.S., Pitts, W., A Logical Calculus of the Ideas Immanent in Nervous Activity., Bulletin of Mathematical Biophysics, N°5, 1943, pp. 115-133. DOI: https://doi.org/10.1007/BF02478259

Minsky, M., Papert, S., Perceptrons: An Introduction to Computational Geometry., Cambridge, MA, MIT Press, 1969.

Peña, D., Estadística, Modelos y Métodos. Fundamentos, Alianza Editorial, 1998.

Pesaran, M., Timmermann, A., A Simple Nonparametric Test of Predictive Performance., Journal of Business and Economic Statistics, Vol 10, No 4: 1992, pp. 461-65. DOI: https://doi.org/10.1080/07350015.1992.10509922

Sarle, W.S., Neural Networks Implementation in SAS., Proceedings of the Nineteenth Annual SAS Users Group International Conference, April, 1994. Disponible en: http://citeseer.ist.psu.edu/36580.html

Wong, F., Tan, C., Hybrid Neural, Genetic and Fuzzy Systems., En: Trading on the Edge. Neural, Genetic and Fuzzy Systems for Chaotic Financial Markets., Guido J. Deboek (Ed.)., John Wiley and Sons. Inc., 1994.

Yao, J., Tan, L., A Case of Study on using Neural Networks to perform Technical Forecasting of FOREX., Neurocomputing, No. 34, 2000, pp. 79 - 98. Disponible en: http://citeseer.ist.psu.edu/yao00case.html DOI: https://doi.org/10.1016/S0925-2312(00)00300-3

How to Cite

APA

Villamil Torres, J. A. and Delgado Rivera, J. A. (2007). Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate. Ingeniería e Investigación, 27(3), 106–117. https://doi.org/10.15446/ing.investig.v27n3.14851

ACM

[1]
Villamil Torres, J.A. and Delgado Rivera, J.A. 2007. Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate. Ingeniería e Investigación. 27, 3 (Sep. 2007), 106–117. DOI:https://doi.org/10.15446/ing.investig.v27n3.14851.

ACS

(1)
Villamil Torres, J. A.; Delgado Rivera, J. A. Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate. Ing. Inv. 2007, 27, 106-117.

ABNT

VILLAMIL TORRES, J. A.; DELGADO RIVERA, J. A. Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate. Ingeniería e Investigación, [S. l.], v. 27, n. 3, p. 106–117, 2007. DOI: 10.15446/ing.investig.v27n3.14851. Disponível em: https://revistas.unal.edu.co/index.php/ingeinv/article/view/14851. Acesso em: 28 mar. 2024.

Chicago

Villamil Torres, Jaime Alberto, and Jesús Alberto Delgado Rivera. 2007. “Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate”. Ingeniería E Investigación 27 (3):106-17. https://doi.org/10.15446/ing.investig.v27n3.14851.

Harvard

Villamil Torres, J. A. and Delgado Rivera, J. A. (2007) “Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate”, Ingeniería e Investigación, 27(3), pp. 106–117. doi: 10.15446/ing.investig.v27n3.14851.

IEEE

[1]
J. A. Villamil Torres and J. A. Delgado Rivera, “Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate”, Ing. Inv., vol. 27, no. 3, pp. 106–117, Sep. 2007.

MLA

Villamil Torres, J. A., and J. A. Delgado Rivera. “Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate”. Ingeniería e Investigación, vol. 27, no. 3, Sept. 2007, pp. 106-17, doi:10.15446/ing.investig.v27n3.14851.

Turabian

Villamil Torres, Jaime Alberto, and Jesús Alberto Delgado Rivera. “Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate”. Ingeniería e Investigación 27, no. 3 (September 1, 2007): 106–117. Accessed March 28, 2024. https://revistas.unal.edu.co/index.php/ingeinv/article/view/14851.

Vancouver

1.
Villamil Torres JA, Delgado Rivera JA. Training a multilayer neural network for the Euro-dollar (EUR/ USD) exchange rate. Ing. Inv. [Internet]. 2007 Sep. 1 [cited 2024 Mar. 28];27(3):106-17. Available from: https://revistas.unal.edu.co/index.php/ingeinv/article/view/14851

Download Citation

CrossRef Cited-by

CrossRef citations1

1. Jimmy Rafael Landaburu Mendoza, Luz María Quinde Arreaga, Nuvia Aurora Zambrano Barros, Adolfo Hernán Elizondo Saltos. (2023). Aplicación de series de tiempo en valores de activos financieros. Religación, 8(38), p.e2301117. https://doi.org/10.46652/rgn.v8i38.1117.

Dimensions

PlumX

Article abstract page views

723

Downloads

Download data is not yet available.

Most read articles by the same author(s)