Abstract
In this paper, we propose a general approach for fitting and forecasting the behavior of time-dependent processes. The only hypothesis on which it is based is the stationarity of the process dynamics. The approach is clearly non-parametric, uses no kind of a priori hypothesis on the form of the process and reveals itself powerful on either deterministic processes (such linear, logarithmic or sinusoidal ones) or stochastic ones (being able to reproduce even a white noise). The fields of applications of the proposed methods are time-series prevision but also risk analysis, allowing to determine the limits between which a stochastic process will behave on a specific time-horizon.
Preview
Unable to display preview. Download preview PDF.
Bibliography
Cottrell M., Fort J.C., esEtude d'un algorithme d'auto-organisation, Annales de l Institut Poincaré, Vol. 23, 1, p. 1–20,1987.
Cottrell M., Fort J.C., Pagès G., Two or three things that we know about the Kohonen algorithm, in Proc of ESANN, M. Verleysen ED., D Facto, Bruxelles, 1994.
Cottrell M., de Bodt E., Verleysen M., Kohonen maps versus vector quantization for data analysis, in Proc of ESANN, M.Verleysen ED., D Facto, Bruxelles, 1997.
Cottrell M., de Bodt E., Grégoire Ph., Simulating Interest Rate Structure Evolution on a Long Tenu Horizon: A Kohonen Map Application, Proceedings of Neural Networks in The Capital Markets, Californian Institute of Technology, World Scientific Ed., Passadena, 1996.
Cottrell M., Fort J.C., Pagès G., Theoretical aspects of the SOM algorithm, Proc. of WSOM'97, Helsinki, 1997.
Cox J.C., Ingersoll J.E., Ross S.A., A Theory of the Term Structure of Interest Rates, Econometrica 53, p. 385–407,1985.
Kohonen T., Self-Organizing Maps, Springer Series in Information Sciences, Vol 30, Springer, Berlin, 1995.
Pagès G., Voronoï tesselation, Space quantization algorithms and numerical integration, Proc. ESANW'93, M.Verleysen Ed., Editions D Facto, Bruxelles, 221–228, 1993.
Walter J., Ritter H., Schulten K., Non-linear prediction with self-organizing maps,Proc. of IJCNN, San Diego, CA, 589–594, July 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Bodt, E., Grégoire, P., Cottrell, M. (1997). A powerful tool for fitting and forecasting deterministic and stochastic processes: The Kohonen classification. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020280
Download citation
DOI: https://doi.org/10.1007/BFb0020280
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive