Summary
This work develops and evaluates new algorithms based on neural networks and boosting techniques, designed to model and predict heteroskedastic time series. The main novel elements of these new algorithms are as follows: a) in regard to neural networks, the simultaneous estimation of conditional mean and volatility through the likelihood maximization; b) in regard to boosting, its simultaneous application to trend and volatility components of the likelihood, and the use of likelihood-based models (e.g. GARCH) as the base hypothesis rather than gradient fitting techniques using least squares. The behavior of the proposed algorithms is evaluated over simulated data, resulting in frequent and significant improvements in relation to the ARMA-GARCH models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Audrino F, Bühlmann P (2002) Volatility estimation with functional gradient descent for very high dimensional financial time series. J Comp Finance 6:65–89
Bollerslev T (1986) Generalized autoregressive conditional heteroskedasticity. J Econometrics 31:27–37
Box GEP, Jenkins GM, Reinsel GC (1994) Time series analysis: forecasting and control. Prentice-Hall, Upper Saddle River
Engle RF (1982) Autoregressive conditional heteroskedasticity with estimates of the variance of United Kingdom inflation. Econometrica 50:987–1007
Fan J, Yao Q (2003) Nonlinear time series: nonparametric and parametric methods. Springer, Berlin/Heidelberg
Foresee FD, Hagan T (1997) Gauss-Newton approximation to Bayesian regularization. In: Proc IEEE Int Joint Conf Neural Networks, Houston, TX, USA. IEEE, Piscataway, pp 1930–1935
Friedman J (2001) Greedy function approximation: a gradient boosting machine. The Annals of Stat 39:1189-1232
Granger CWJ, Newbold P (1986) Forecasting economic time series. Academic Press, London
Granger CWJ, Teräsvirta T (1993) Modelling nonlinear economic relationships. Oxford University Press, Oxford
Medeiros MC, Teräsvirta T, Rech G (2002) Building neural networks models for time series: a statistical approach. Tech Report 461, Stockholm School of Economics, Stockholm
Miranda FG, Burgess N (1997) Modelling market volatilities: the neural network perspective. The European J Finance 3:137–157
Priestley MB (1981) Spectral analysis and time series. Academic Press, London
Refenes APN, Burgess AN, Bentz Y (1997) Neural networks in financial engineering: a study in methodology. IEEE Trans Neural Networks 8:1222–1267
Schapire RE (1990) The strength of weak learnability. Mach Learn 5:197–227
Schittenkopf C, Dorffner G, Dockner EJ (2000) Forecasting time-dependent conditional densities: a seminonparametric neural network approach. J Forecasting 19:355–374
Tino P, Schittenkopf C, Dorffner G (2001) Financial volatility trading using recurrent neural networks. IEEE Trans Neural Networks 12:865–874
Tsay RS (2001) Analysis of financial time series. John Wiley and Sons, Hoboken
Weigend AS, Gershenfeld NA (1993) Time series prediction: forecasting the future and understanding the past. Perseus Books, New York
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Matías, J.M., Febrero, M., González-Manteiga, W., Reboredo, J.C. (2008). Gradient Boosting GARCH and Neural Networks for Time Series Prediction. In: Okun, O., Valentini, G. (eds) Supervised and Unsupervised Ensemble Methods and their Applications. Studies in Computational Intelligence, vol 126. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78981-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-78981-9_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78980-2
Online ISBN: 978-3-540-78981-9
eBook Packages: EngineeringEngineering (R0)