Abstract

VELASQUEZ H., JUAN DAVID; DYNER R., ISAAC  and  SOUZA., REINALDO C.. TENDENCIES IN THE PREDICTION AND ESTIMATION OF THE CONFIDENCE INTERVALS USING MODELS OF NEURONAL NETWORKS APPLIED TO TEMPORARY SERIES. Dyna rev.fac.nac.minas [online]. 2006, vol.73, n.149, pp.141-147. ISSN 0012-7353.

In this paper, we discuss the state-of-art in estimating multiple steps ahead forecast for nonlinear time series models based on multilayer perceptrons. We review the main trends for estimating the point forecasts and confidence intervals. In addition, we argue the principal open issues for future research in time series forecasting using neural networks.

Keywords : Prediction; confidence intervals; artificial neural networks.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )