A Neural Network Approach to Time Series Forecasting

Citation

Gheyas IA & Smith L (2009) A Neural Network Approach to Time Series Forecasting. In: Ao S, Gelman L, Hukins D, Hunter A & Korsunsky A (eds.) Proceedings of The World Congress on Engineering 2009: Volume 2. ICCSDE'09: The 2009 International Conference of Computational Statistics and Data Engineering: London, U.K., 1-3 July, 2009, London, UK, 01.07.2009-03.07.2009. Hong Kong: Newswood Limited, pp. 1292-1296. http://www.iaeng.org/publication/WCE2009/WCE2009_pp1292-1296.pdf

Abstract
We propose a simple approach for forecasting univariate time series. The proposed algorithm is an ensemble learning technique that combines the advice from several Generalized Regression Neural Networks. We compare our algorithm with the most used algorithms on real and synthetic datasets. The proposed algorithm appears as more powerful than existing ones.

Keywords
Time series forecasting; Box-Jenkins methodology; Multilayer Perceptrons; Generalized Regression; Neural Networks.

People

Professor Leslie Smith

Emeritus Professor, Computing Science