Combination of Biased Artificial Neural Network Forecasters

Author

Oliveira, Thaize F. ; De Oliveira, Ricardo T. A. ; Firmino, Paulo Renato A. ; De Mattos Neto, Paulo S. G. ; Ferreira, Tiago A. E.

Author_Institution

Dept. of Stat. & Inf., Fed. Rural Univ. of Pernambuco, Recife, Brazil

fYear

2013

fDate

8-11 Sept. 2013

Firstpage

522

Lastpage

527

Abstract

Artificial neural networks (ANN) have been paramount for modeling and forecasting time series phenomena. In this way it has been usual to suppose that each ANN model generates a white noise as prediction error. However, mostly because of disturbances not captured by each model, it is yet possible that such supposition is violated. On the other hand, to adopt a single ANN model may lead to statistical bias and underestimation of uncertainty. The present paper introduces a two-step maximum likelihood method for correcting and combining ANN models. Applications involving single ANN models for Dow Jones Industrial Average Index and S&P500 series illustrate the usefulness of the proposed framework.

Keywords

forecasting theory; maximum likelihood estimation; modelling; neural nets; time series; white noise; ANN model; biased artificial neural network forecasters; prediction error; statistical bias; time series phenomena forecasting; time series phenomena modeling; two-step maximum likelihood method; uncertainty underestimation; white noise; Artificial neural networks; Forecasting; Mathematical model; Maximum likelihood estimation; Predictive models; Time series analysis; Unified modeling language; Linear Combination of Forecast; Maximum Likelihood Estimation; Time Series Forecasting Models; Unbiased Forecasts;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and 11th Brazilian Congress on Computational Intelligence (BRICS-CCI & CBIC), 2013 BRICS Congress on

Conference_Location

Ipojuca

Type

conf

DOI

10.1109/BRICS-CCI-CBIC.2013.92

Filename

6855901