Time series forecasting: Obtaining long term trends with self-organizing maps

  • Authors:
  • G. Simon;A. Lendasse;M. Cottrell;J. -C. Fort;M. Verleysen

  • Affiliations:
  • Machine Learning Group-DICE-Université catholique de Louvain, Place du Levant 3, B-1348 Louvain-la-Neuve, Belgium;Helsinki University of Technology-Laboratory of Computer and Information Science, Neural Networks Research Centre, P.O. Box 5400, Fin-02015 Hut, Finland;Samos-Matisse, UMR CNRS 8595, Université Paris I-Panthéon Sorbonne, Rue de Tolbiac 90, F-75634 Paris Cedex 13, France;Lab. Statistiques et Probabilités, CNRS C55830, Université Paul Sabatier Toulouse 3 Route de Narbonne 118, F-31062 Toulouse Cedex, France and Samos-Matisse, UMR CNRS 8595, Université ...;Machine Learning Group-DICE-Université catholique de Louvain, Place du Levant 3, B-1348 Louvain-la-Neuve, Belgium and Samos-Matisse, UMR CNRS 8595, Université Paris I-Panthéon Sorbo ...

  • Venue:
  • Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Kohonen self-organisation maps are a well know classification tool, commonly used in a wide variety of problems, but with limited applications in time series forecasting context. In this paper, we propose a forecasting method specifically designed for multi-dimensional long-term trends prediction, with a double application of the Kohonen algorithm. Practical applications of the method are also presented.