Abstract
A forecasting approach based on Multi-Layer Perceptron (MLP) Artificial Neural Networks (named by the authors MULP) is proposed for the NN5 111 time series long-term, out of sample forecasting competition. This approach follows a direct prediction strategy and is completely automatic. It has been chosen after having been compared with other regression methods (as for example Support Vector Machines (SVMs)) and with a recursive approach to prediction. Good results have also been obtained using the ANNs forecaster together with a dimensional reduction of the input features space performed through a Principal Component Analysis (PCA) and a proper information theory based backward selection algorithm. Using this methodology we took the 10th place among the best 50% scorers in the final results table of the NN5 competition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Patterson, D.W.: Artificial Neural Networks: Theory and Applications. Prentice Hall, Singapore (1996)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Crone, S., Lessmann, S., Pietsch, S.: Forecasting with Computational Intelligence - An Evaluation of Support Vector Regression and Artificial Neural Networks for Time Series Prediction. In: Proceedings of the World Congress in Computational Intelligence, WCCI 2006, Vancouver, Canada. IEEE, New York (2006)
Pasero, E., Moniaci, W., Meindl, T., Montuori, A.: NEMEFO: NEural MEteorological Forecast. In: Proceeding of SIRWEC 2004, 12th International Road Weather Conference, Bingen (2004)
Wang, H.A., Chan, A.K.H.: A feedforward neural network model for Hang Seng Index. In: Proceedings of 4th Australian Conference on Information Systems, Brisbane, pp. 575–585 (1993)
Windsor, C.G., Harker, A.H.: Multi-variate financial index prediction -a neural network study. In: Proceedings of International Neural Network Conference, Paris, France, pp. 357–360 (1990)
White, H.: Economic prediction using Neural Networks: The case of the IBM daily stock returns. In: Proceedings of IEEE International Conference on Neural Networks, pp. 451–458 (1988)
Benvenuto, F., Marani, A.: Neural networks for environmental problems: data quality control and air pollution nowcasting. Global NEST: The International Journal 2(3), 281–292 (2000)
Perez, P., Trier, A., Reyes, J.: Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile. Atmospheric Environment 34, 1189–1196 (2000)
Božnar, M.Z., Mlakar, P., Grašič, B.: Neural Networks Based Ozone Forecasting. In: Proc. of 9th Int. Conf. on Harmonisation within Atmospheric Dispersion Modelling for Regulatory Purposes, Garmisch-Partenkirchen, Germany (2004)
Jolliffe, I.T.: Principal Component Analysis (2002)
Crone, S.: Stepwise Selection of Artificial Neural Network Models for Time Series Prediction. Journal of Intelligent Systems 14(2-3), 99–122 (2005)
Ruta, D., Gabrys, B.: Neural Network Ensembles for Time Series Prediction. In: Proc. of IJCNN 2007, Orlando, Florida, USA (2007)
Ilies, I., Jaeger, H., Kosuchinas, O., et al.: Stepping forward through echoes of the past: forecasting with Echo State Networks, NN3 Forecasting Competition results (2007), http://www.neural-forecasting-competition.com/NN3/results.htm
Simon, G., Lendasse, A., Cottrell, M., Verleysen, M.: Long-Term Time Series Forecasting Using Self-Organizing Maps: the Double Vector Quantization Method. In: ANNPR 2003 proc., IAPR-TC3, Florence, Italy, pp. 8–14 (2003)
Liao, K.-P., Fildes, R.: The accuracy of a procedural approach to specifying feedforward neural networks for forecasting. Computers & Operations Research, 2121–2169 (2005)
Adya, Collopy: How effective are neural networks at forecasting and prediction? A review and evaluation. Journal of Forecasting 17, 481–495 (1998)
Pasero, E., Moniaci, W.: Artificial Neural Networks for Meteorological Nowcast. In: Proc. of IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, pp. 36–39 (2004)
Raimondo, G., Montuori, A., Moniaci, W., Pasero, E., Almkvist, E.: A Machine Learning Tool to Forecast PM10 Level. In: Proc. of the AMS 87th Annual Meeting, San Antonio, TX, USA (2007)
Costa, M., Moniaci, W., Pasero, E.: INFO: an artificial neural system to forecast ice formation on the road. In: Proc. of IEEE International Symposium on Computational Intelligence for Measurement Systems and Applications, pp. 216–221 (2003)
Werbos, P.: Beyond regression: New tools for Prediction and Analysis in the Behavioural Sciences, Ph.D. Dissertation, Committee on Appl. Math., Harvard Univ. Cambridge, MA (November 1974)
Marquardt, D.: An algorithm for least squares estimation of nonlinear parameters. SIAM J. Appl. Math. 11, 431–441 (1963)
Demuth, H., Beale, M.: Neural Network Toolbox User’s Guide. The MathWorks, Inc. (1987) Download final NN5 Competition Datasets (including test data), http://www.neuralforecastingcompetition.com/downloads/NN5/datasets/download.htm (2005)
Fletcher, R.: Practical Methods of Optimization, 2nd edn. John Wiley & Sons, NY (1987)
Canu, S., Grandvalet, Y., Guigue, V., Rakotomamonjy, A.: SVM and Kernel Methods Matlab Toolbox. Perception Systèmes et Information, INSA de Rouen, Rouen, France (2005), http://asi.insarouen.fr/~arakotom/toolbox/index.html
Koller, D., Sahami, M.: Toward optimal feature selection. In: Proc. of 13th International Conference on Machine Learning (ICML), Bari, Italy, pp. 284–292 (1996)
Tashman, L.: Out-of-sample tests of forecasting accuracy - an analysis and review. International Journal of Forecasting 16, 437–450 (2000)
NN5 Competition Results, http://www.neural-forecasting-competition.com/results.htm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pasero, E., Raimondo, G., Ruffa, S. (2010). MULP: A Multi-Layer Perceptron Application to Long-Term, Out-of-Sample Time Series Prediction. In: Zhang, L., Lu, BL., Kwok, J. (eds) Advances in Neural Networks - ISNN 2010. ISNN 2010. Lecture Notes in Computer Science, vol 6064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13318-3_70
Download citation
DOI: https://doi.org/10.1007/978-3-642-13318-3_70
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13317-6
Online ISBN: 978-3-642-13318-3
eBook Packages: Computer ScienceComputer Science (R0)