Abstract
Improvement of time series forecasting accuracy is an active research area having significant importance in many practical domains. Extensive works in literature suggest that substantial enhancement in accuracies can be achieved by combining forecasts from different models. However, forecasts combination is a difficult as well as a challenging task due to various reasons and often simple linear methods are used for this purpose. In this paper, we propose a nonlinear weighted ensemble mechanism for combining forecasts from multiple time series models. The proposed method considers the individual forecasts as well as the correlations in pairs of forecasts for creating the ensemble. A successive validation approach is formulated to determine the appropriate combination weights. Three popular models are used to build up the ensemble which is then empirically tested on three real-world time series. Obtained forecasting results, measured through three well-known error statistics demonstrate that the proposed ensemble method provides significantly better accuracies than each individual model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Gooijer, J.G., Hyndman, R.J.: 25 Years of time series forecasting. J. Forecasting 22(3), 443–473 (2006)
Box, G.E.P., Jenkins, G.M.: Time Series Analysis: Forecasting and Control, 3rd edn. Holden-Day, California (1970)
Armstrong, J.S.: Combining Forecasts. In: Armstrong, J.S. (ed.) Principles of Forecasting: A Handbook for Researchers and Practitioners. Kluwer Academic Publishers, Norwell (2001)
Zhang, G.P.: Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)
Bates, J.M., Granger, C.W.J.: Combination of forecasts. Operational Research Quarterly 20(4), 451–468 (1969)
Clemen, R.T.: Combining forecasts: A review and annotated bibliography. J. Forecasting 5(4), 559–583 (1989)
Aksu, C., Gunter, S.: An empirical analysis of the accuracy of SA, OLS, ERLS and NRLS combination forecasts. J. Forecasting 8(1), 27–43 (1992)
Zou, H., Yang, Y.: Combining time series models for forecasting. J. Forecasting 20(1), 69–84 (2004)
Jose, V.R.R., Winkler, R.L.: Simple robust averages of forecasts: Some empirical results. International Journal of Forecasting 24(1), 163–169 (2008)
Lemke, C., Gabrys, B.: Meta-learning for time series forecasting and forecast combination. Neurocomputing 73, 2006–2016 (2010)
Bunn, D.: A Bayesian approach to the linear combination of forecasts. Operational Research Quarterly 26(2), 325–329 (1975)
Frietas, P.S., Rodrigues, A.J.: Model combination in neural-based forecasting. European Journal of Operational Research 173(3), 801–814 (2006)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with articial neural networks: The state of the art. J. Forecasting 14, 35–62 (1998)
Faraway, J., Chatfield, C.: Time series forecasting with neural networks: a comparative study using the airline data. J. Applied Statistics 47(2), 231–250 (1998)
Reidmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The rprop algorithm. In: Proceedings of the IEEE Int. Conference on Neural Networks (ICNN), San Francisco, pp. 586–591 (1993)
Demuth, M., Beale, M., Hagan, M.: Neural Network Toolbox User’s Guide. The MathWorks, Natic (2010)
Lim, C.P., Goh, W.Y.: The application of an ensemble of boosted Elman networks to time series prediction: A benchmark study. J. of Computational Intelligence 3, 119–126 (2005)
Time Series Data Library, http://robjhyndman.com/TSDL
Yahoo! Finance, http://finance.yahoo.com
Pacific FX database, http://fx.sauder.ubc.ca/data.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Adhikari, R., Agrawal, R.K. (2012). A Novel Weighted Ensemble Technique for Time Series Forecasting. In: Tan, PN., Chawla, S., Ho, C.K., Bailey, J. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2012. Lecture Notes in Computer Science(), vol 7301. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30217-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-30217-6_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30216-9
Online ISBN: 978-3-642-30217-6
eBook Packages: Computer ScienceComputer Science (R0)