Predicción de series de tiempo usando un modelo híbrido basado en la descomposición wavelet

Michael Vasquez

Resumen


El pronóstico de series de tiempo que exhiben una estructura de segundo orden que vara en función del tiempo ha recibido especial atención debido a la dificultad de obtener buenos pronósticos, especialmente cuando existe una estructura poco homogénea al final de los datos. En este trabajo, se usa una metodología adecuada para pronosticar series de tiempo, con un alto nivel de ruido que evidencien no estacionariedad. Especialmente, se combina la transformación wavelet discreta de máximo traslape (MODWT) con el modelo ARFIMA-HYGARCH y redes neuronales. Ambos modelos se aplican para pronosticar la tasa de cambio USD/COP. Los resultados sugieren que la metodología basada en wavelets y redes neuronales, proveen pronósticos más precisos para pronosticar una apreciación/depreciación del tipo de cambio.


Palabras clave


Pronóstico; modelos híbridos; ARFIMA-HYGARCH; Descomposición Wavelet; tipos de cambio

Texto completo:

PDF

Referencias


Álvarez, M. & Álvarez, A. (2004), `Predicción no lineal de los tipos de cambio. Aplicación de un algoritmo genético', Revista de Economía Aplicada 12(35), 55-64.

Baillie, R., Bollerslev, T. & Mikkelsen, H. (1996), `Fractionally integrated generalized autoregressive conditional heteroscedasticity’, Journal of Econometrics 74, 3-30.

Ben Mabrouk, A., Ben Abdallah, N. & Z., D. (2008), `Wavelet decomposition and autoregressive model for time series prediction', Applied Mathematics and Computation 199, 334-40.

Bollerslev, T. (1986), `Generalized autoregressive conditional heteroscedasticity’, Journal of Econometrics 31, 307-327.

Bollerslev, T. & Mikkelsen, H. (1996), `Modelling and pricing long memory in stock market volatility', 73, 151-184.

Box, G. & Jenkins, G. (1970), Time series analysis: Forecasting and Control, Holden-Day,San Francisco.

Castaño, E., Gómez, K. & Gallon, S. (2008), `Una nueva prueba para el parámetro de diferenciación fraccional', Revista Colombiana de Estadística 31(1), 67-84.

Cochrane, J. H. (1991), `Pitfalls and opportunities: What macroeconomists should know about unit roots: Comment', 6, 201-210.

Conejo, A. J., Plazas, M. A., Española, R. & Molina, A. B. (2005), `Day-ahead electricity price forecasting using the wavelet transform and ARIMA models', IEEE TRANSACTIONS ON POWER SYSTEMS 20, 1035-1042.

Daubechies, I. (1992), Ten Lectures on Wavelets, SIAM, Philadelphia.

Davidson, J. (2004), `Moment and memory properties of linear conditional heteroscedasticity models, and a new model', Journal of Business and Economics Statistics 22, 16-29.

Diebold, F. X. & Mariano, R. S. (1995), `Comparing predictive accuracy', Journal of Business & Economic Statistics 20(1), 134-144.

Ding, Z. & Granger, C. (1996), `Modelling volatility persistence of speculative returns: A new approach', pp. 185-215.

Engle, E. (1982), `Autoregressive conditional heteroscedasticity with estimates of the variance of united kingdom inflation', Econometrica 50, 987-1008.

Engle, R. & Bollerslev, T. (1986), `Modelling the persistence of conditional variances', Econometric Reviews 5, 1-50.

Fernandez, V. (2007), `Wavelet-and svm-based forecasts: An analysis of the U.S. metal and materials manufacturing industry', Resources Policy 32, 80-89.

Franses, P. & van Dijk, D. (2000), Non-linear time series models in empirical finance, Cambridge University Press.

Granger, C. W. J. & Joyeux, R. (1980), `An introduction to long-memory time series models and fractional differencing', Journal of Time Series Analysis 1, 15-39.

Granger, W. (1980), `Long memory relationships and the aggregation of dynamic models', Journal of Econometrics 14, 227-238.

Guo, X., Sun, L., Li, G. & Wang, S. (2008), `A hybrid wavelet analysis and support vector machines in forecasting development of manufacturing', Expert Systems with Applications 35, 415-422.

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

Hosking, J. R. M. (1981), `Fractional differencing', Biometrika 68, 165-176.

Ismail, M. T., B., A. & M., T. M. (2016), `Volatility forecasting with the wavelet transformation algorithm garch model: Evidence from african stock markets', pp. 125-135.,

Karthikeyan, L. & Nagesh Kumar, D. (2013), `Predictability of nonstationary time series using wavelet and emd based arma models', Journal of Hydrology 502, 103-119.

Kuan, C. M. & Liu, T. (1995), `Forecasting exchange rates using feedforward and recurrent neural networks', 10, 347-364.

Kwan, W., Keung, W. & Li, G. (2012), `On the estimation and diagnostic checking of the arma^ahygarch model', 56, 3632-3644.

Liu, M. (2000), `Modelling long memory in stock market volatility', pp. 139-171.

Pesaran, M. & Timmermann, A. (1992), `A simple nonparametric test of predictive performance', Journal of Business and Economic Statistics 4, 461-465.

Seo, Y., Choi, Y. & Choi, J. (2017), `River stage modeling by combining maximal overlap discrete wavelet transform, support vector machines and genetic algorithm', 9(525).

Soltani, S. (2002), `On the use of the wavelet decomposition for time series prediction', Neurocomputing 48, 267-277.

Tan, Z., Zhang, J., Wang, J. & Xu, k. (2010), `Day-ahead electricity price forecasting using wavelet transform combined with arima and garch models', Applied Energy 87, 3606-3610.

Walzack, S. (2001), `An empirical analysis of data requirements for financial forecasting with neural networks', Journal of management Information Systems 4, 203-222.

Zhu, L., Wang, Y. & Fan, Q. (2014), `Modwt-arma model for time series prediction', Applied Mathematical Modelling 38, 1859-1865.


Enlaces refback

  • No hay ningún enlace refback.


ISSN: 2027-3355 - e-ISSN: 2339-3076 - DOI: https://doi.org/10.15332/23393076