Article

A Novel Neural Network Ensemble Architecture for Time Series Forecasting

Details

Citation

Gheyas IA & Smith L (2011) A Novel Neural Network Ensemble Architecture for Time Series Forecasting. Neurocomputing, 74 (18), pp. 3855-3864. https://doi.org/10.1016/j.neucom.2011.08.005

Abstract
We propose a novel homogeneous neural network ensemble approach called Generalized Regression Neural Network (GEFTS-GRNN) Ensemble for Forecasting Time Series, which is a concatenation of existing machine learning algorithms.GEFTS use a dynamic nonlinear weighting system wherein the outputs from several base-level GRNNs are combined using a combiner GRNN to produce the final output. We compare GEFTS with the 11 most used algorithms on 30 real datasets. The proposed algorithm appears to be more powerful than existing ones. Unlike conventional algorithms, GEFTS is effective in forecasting time series with seasonal patterns.

Keywords
Time series forecasting; Generalized regression neural networks; Neural network ensemble; Curse of dimensionality; Dynamic nonlinear weighted voting; Neural networks (Computer science); Data mining

Journal
Neurocomputing: Volume 74, Issue 18

StatusPublished
Publication date30/11/2011
URLhttp://hdl.handle.net/1893/3657
PublisherElsevier
ISSN0925-2312

People (1)

People

Professor Leslie Smith

Professor Leslie Smith

Emeritus Professor, Computing Science