Abstract
A novel hybrid algorithm based on the AFTER (Aggregated forecast through exponential re-weighting) and the modified particle swarm optimization (PSO) is proposed. The combining weights in the hybrid algorithm are trained by the modified PSO. The linear constraints are added in the PSO to ensure that the sum of the combining weights is equal to one. Simulated results on the prediction of the stocks data show the effectiveness of the hybrid algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bates, J.N., Granger, C.W.J.: The combination of forecasts. Operations Research Quarterly 20, 319–325 (1969)
Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, vol. IV (1942-1948)
Yang, Y.: Combining time series models for forecasting. International Journal of Forecasting 20(1), 69–84 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Feng, X., Liang, Y., Sun, Y., Lee, H.P., Zhou, C., Wang, Y. (2004). A Hybrid Algorithm for Combining Forecasting Based on AFTER-PSO. In: Zhang, C., W. Guesgen, H., Yeap, WK. (eds) PRICAI 2004: Trends in Artificial Intelligence. PRICAI 2004. Lecture Notes in Computer Science(), vol 3157. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28633-2_105
Download citation
DOI: https://doi.org/10.1007/978-3-540-28633-2_105
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22817-2
Online ISBN: 978-3-540-28633-2
eBook Packages: Springer Book Archive