Model combination in neural-based forecasting

Freitas, Paulo S. A.; Rodrigues, António J. L.

http://hdl.handle.net/10400.13/3565

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Model combination in neural-based forecasting.pdf		210.26 KB	Adobe PDF	Download

Send Feedback

Authors

Freitas, Paulo S. A.

Rodrigues, António J. L.

Abstract(s)

This paper discusses different ways of combining neural predictive models or neural-based forecasts. The proposed approaches consider Gaussian radial basis function networks, which can be efficiently identified and estimated through recursive/adaptive methods. The usual framework for linearly combining estimates from different models is extended, to cope with the case where the forecasting errors from those models are correlated. A prefiltering methodology is pro posed, addressing the problems raised by heavily nonstationary time series. Moreover, the paper discusses two approaches for decision-making from forecasting models: either inferring decisions from combined predictive estimates, or combining prescriptive solutions derived from different forecasting models.

Keywords

Forecasting Neural networks Model combination Adaptive methods Optimal decision-making . Faculdade de Ciências Exatas e da Engenharia

URI

http://hdl.handle.net/10400.13/3565

Citation

Freitas, P. S., & Rodrigues, A. J. (2006). Model combination in neural-based forecasting. European Journal of Operational Research, 173(3), 801-814. DOI: 10.1016/j.ejor.2005.06.057