Published

2007-01-01

EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS

FORECAST EVALUATION OF THE EXCHANGE RATE USING ARTIFICIAL NEURAL NETWORKS AND ASYMMETRIC COST FUNCTIONS

Keywords:

modelos para series de tiempo, modelos no lineales, tipo de cambio extranjero (es)
Time series models, Nonlinear models, Foreign exchange (en)

Downloads

Authors

  • Munir Andrés Jalil Banco de la República / Universidad Nacional de Colombia
  • Martha Misas Banco de la República
Se comparan especificaciones lineales y no lineales (estas últimas expresadas en redes neuronales artificiales) ajustadas a la variación porcentual diaria del tipo de cambio utilizando para ello funciones de costo tradicionales (simétricas) y funciones de pérdida asimétricas. Los resultados muestran que las redes neuronales permiten obtener mejores pronósticos con ambos tipos de funciones de costos. Sin embargo, es de anotar que cuando se evalúan los pronósticos con funciones asimétricas, el modelo no lineal supera ampliamente a su contraparte lineal.
We compare forecasts obtained via linear vs. non linear specifications. The models are adjusted to the daily percentage change of the exchange rate and the comparison is done using both symmetric and asymmetric cost functions. Results show that the non linear model (which here takes the form of an Artificial Neural Network –ANN) performs better in terms of forecasting ability when evaluated with both types of cost functions. Further more, when using asymmetric costs, the ANN is a much better predictor than its linear counterpart.

Evaluación de pronósticos del tipo de cambio utilizando redes neuronales y funciones de pérdida asimétricas

Forecast Evaluation of the Exchange Rate Using Artificial Neural Networks and Asymmetric Cost Functions

MUNIR ANDRÉS JALIL1, MARTHA MISAS2

1Banco de la República, Bogotá, Colombia. Universidad Nacional de Colombia, Facultad de Economía, Bogotá. Investigador y profesor asociado. E-mail: mjalilba@banrep.gov.co
2Universidad Nacional de Colombia, Facultad de Economía, Bogotá. Econometrista principal. E-mail: mmisasar@banrep.gov.co

Resumen

Se comparan especificaciones lineales y no lineales (estas últimas expresadas en redes neuronales artificiales) ajustadas a la variación porcentual diaria del tipo de cambio utilizando para ello funciones de costo tradicionales (simétricas) y funciones de pérdida asimétricas. Los resultados muestran que las redes neuronales permiten obtener mejores pronósticos con ambos tipos de funciones de costos. Sin embargo, es de anotar que cuando se evalúan los pronósticos con funciones asimétricas, el modelo no lineal supera ampliamente a su contraparte lineal.

Palabras clave: modelos para series de tiempo, modelos no lineales, tipo de cambio extranjero.

Abstract

We compare forecasts obtained via linear vs. non linear specifications. The models are adjusted to the daily percentage change of the exchange rate and the comparison is done using both symmetric and asymmetric cost functions. Results show that the non linear model (which here takes the form of an Artificial Neural Network –ANN) performs better in terms of forecasting ability when evaluated with both types of cost functions. Further more, when using asymmetric costs, the ANN is a much better predictor than its linear counterpart.

Key words: Time series models, Nonlinear models, Foreign exchange.

Texto completo disponible en PDF

Referencias

1. Arango, C., Misas, M., López, E. & Hernández, J. N. (2004), ‘No-linealidades en la demanda de efectivo en Colombia: las redes neuronales como herramienta de pronóstico’, Ensayos sobre política económica 45, 11– 57.

2. Azoff, E. M. (1996), Neural Network. Time Series Forecasting of Financial Markets, in ‘Wiley, A Wiley Finance Edition’.

3. Christoffersen, P. & Diebold, F. X. (1997), ‘Optimal Prediction under Asymmetric Loss’, Econometric Theory 13, 806–817.

4. Diebold, F. X., Gunther, T. A. & Tay, A. S. (1998), ‘Evaluating Density Forecasts with Applications to Financial Risk Management’, International Economic Review 39, 863–883.

5. Diebold, F. X. & Nasson, J.M. (1990), ‘Nonparametric Exchange Rate Prediction’, Journal of International Economics 28, 315–332.

6. Elliott, G. & Timmermann, A. (2002), ‘Optimal Forecast Combinations under General Loss Functions and Forecast Error Distributions’, UCSD Working Paper.

7. Frankel, J. & Rose, A. (1995), Empirical Research on Nominal Exchange Rates, Handbook of International Economics, Elsevier Science, Amsterdam.

8. Franses, P. H. & Van Dijk, D. (2000), Non-linear Time Series Models in Empirical Finance, Cambridge University Press.

9. Granger, C. & Teräsvirta, T. (1993), Modelling Nonlinear Economic Relationships, Advanced Texts in Econometrics, Oxford University Press.

10. Granger, C. W. J. (1969), ‘Prediction with a Generalized Cost Function’, Operational Research 20, 199–207. Reimpreso en Ghysels, E., Swanson, N. R. & Watson, M. W. (eds.), Essays in Econometrics: Collected Papers of Clive W. J. Granger, volume I, 2001. Cambridge: Cambridge University Press.

11. Granger, C. W. J. & Newbold, P. (1986), Forecasting Economic Time Series, 2nd edn, Academic Press, Orlando.

12. Hornik, K., Stinchcombe, M. & White, H. (1989), ‘Multi-Layer Feedforward Networks are Universal Approximators’, Neural Networks 2, 359–366.

13. Isard, P. (1995), Exchange Rate Economics, Cambridge University Press, Cambridge.

14. Kuan, C. M. & Liu, T. (1995), ‘Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks’, Journal of Applied Econometrics 10, 347–364.

15. Kuan, C. M. & White, H. (1994), ‘Artificial Neural Networks: An Econometric Perspective’, Econometric Reviews 13.

16. Meese, R. & Rogoff, K. (1983), Exchange Rate and International Macroeconomics, University of Chicago Press, Chicago, chapter The Out-of-sample Failure of Empirical Exchange Rate Models.

17. Meese, R. & Roose, A. (1991), ‘An Empirical Assessment of Non-Linearities in Models of Exchange Rate Determination’, Review of Econometric Studies 58.

18. Pesaran, M. H. & Skouras, S. (2002), A Companion to Economic Forecasting,Blackwell Publishers, Oxford, chapter Decision-Based Methods for Forecast Evaluation.

19. Plasmans, J., Verkooijen,W. & Daniels, H. (1998), ‘Estimating Structural Exchange Rate Models by Artificial Neural Networks’, Applied Financial Economics 8, 541–551.

20. Rech, G. (2002), ‘Forecasting with Artificial Neural Network Models’, SSE/EFI Working paper Series in Economics and Finance 491.

21. Santana, J. C. (2006), ‘Predicción de series temporales con redes neuronales: una aplicación a la inflación colombiana’, Revista Colombiana de Estadística 29(1), 77–92.

22. Stock, J. H. (2001), A Companion to Theoretical Econometrics, in ‘Forecasting Economic Time Series’, Blackwell Publishers.

23. Swanson, N. R. & White, H. (1995), ‘A Model-Selection Approach to Assessing the Information in the Term Structure Using Linear Models and Artificial Neural Networks’, Journal of Business & Economic Statistics 13(3).

24. Swanson, N. R. & White, H. (1997a), ‘A Model Selection Approach to Real-Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks’, The Review of Economics and Statistics 79.

25. Swanson, N. R. & White, H. (1997b), ‘Forecasting Economic Time Series Using Flexible versus Fixed Specification and Linear versus Nonlinear Econometric Models’, International Journal of Forecasting 13.

26. Taylor, M. (1995), ‘The Economics of Exchange Rates’, Journal of Economic Literature 83, 13–47.

27. Tenti, P. (1996), ‘Forecasting Foreign Exchange Rates Using Recurrent Neural Networks’, Applied Artificial Intelligence 10, 567–581.

28. Van Dijk, D., Teräsvirta, T. & Franses, P. H. (2001), Smooth Transition Autoregressive Models – A Survey of Recent Developments, Working paper series in economics and finance, Stockholm School of Economics.

29. Varian, H. (1974), A Bayesian Approach to Real Estate Assessment, in S. Fienberg & A. Zellner, eds, ‘Studies in Bayesian Econometrics and Statistics in Honor of L. F. Savage’, North-Holland, Amsterdam, pp. 195–208.

30. Watson, M. (2005), Comentario sobre “What’s Real about the Business Cycle”, Technical report, Federal Reserve Bank of St. Louis Review.

31. West, K., Edison, H. & Cho, D. (1993), ‘A Utility Based Evaluation of Some Models of Exchange Rate Variability’, Journal of International Economics 35, 23–46.

32. Zellner, A. (1986), ‘Bayesian Estimation and Prediction Using Asymmetric Loss Functions’, Journal of Forecasting 8, 446–451.

How to Cite

APA

Jalil, M. A. and Misas, M. (2007). EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS. Revista Colombiana de Estadística, 30(1), 143–161. https://revistas.unal.edu.co/index.php/estad/article/view/29446

ACM

[1]
Jalil, M.A. and Misas, M. 2007. EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS. Revista Colombiana de Estadística. 30, 1 (Jan. 2007), 143–161.

ACS

(1)
Jalil, M. A.; Misas, M. EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS. Rev. colomb. estad. 2007, 30, 143-161.

ABNT

JALIL, M. A.; MISAS, M. EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS. Revista Colombiana de Estadística, [S. l.], v. 30, n. 1, p. 143–161, 2007. Disponível em: https://revistas.unal.edu.co/index.php/estad/article/view/29446. Acesso em: 15 apr. 2024.

Chicago

Jalil, Munir Andrés, and Martha Misas. 2007. “EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS”. Revista Colombiana De Estadística 30 (1):143-61. https://revistas.unal.edu.co/index.php/estad/article/view/29446.

Harvard

Jalil, M. A. and Misas, M. (2007) “EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS”, Revista Colombiana de Estadística, 30(1), pp. 143–161. Available at: https://revistas.unal.edu.co/index.php/estad/article/view/29446 (Accessed: 15 April 2024).

IEEE

[1]
M. A. Jalil and M. Misas, “EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS”, Rev. colomb. estad., vol. 30, no. 1, pp. 143–161, Jan. 2007.

MLA

Jalil, M. A., and M. Misas. “EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS”. Revista Colombiana de Estadística, vol. 30, no. 1, Jan. 2007, pp. 143-61, https://revistas.unal.edu.co/index.php/estad/article/view/29446.

Turabian

Jalil, Munir Andrés, and Martha Misas. “EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS”. Revista Colombiana de Estadística 30, no. 1 (January 1, 2007): 143–161. Accessed April 15, 2024. https://revistas.unal.edu.co/index.php/estad/article/view/29446.

Vancouver

1.
Jalil MA, Misas M. EVALUACIÓN DE PRONÓSTICOS DEL TIPO DE CAMBIO UTILIZANDO REDES NEURONALES Y FUNCIONES DE PÉRDIDA ASIMÉTRICAS. Rev. colomb. estad. [Internet]. 2007 Jan. 1 [cited 2024 Apr. 15];30(1):143-61. Available from: https://revistas.unal.edu.co/index.php/estad/article/view/29446

Download Citation

Article abstract page views

209

Downloads

Download data is not yet available.

License

Copyright (c) 2007 Revista Colombiana de Estadística

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).