Free Access
Volume 15, Number 2, 2001
Page(s) 31 - 48
DOI: 10.1051/ejess:2001114

European Journal of Economic and Social Systems 15 N° 2 (2001) 31-48

Dimension reduction of technical indicators for the prediction of financial time series - Application to the BEL20 Market Index

Amaury Lendasse1, John Lee2, Éric de Bodt3, 4, Vincent Wertz1, 4 and Michel Verleysen2, 4

1  Centre for Systems Engineering and Applied Mechanics, Engineering Faculty, Université catholique de Louvain, Louvain-la-Neuve, Belgium. E-mail:,
2  Microelectronics Laboratory, Engineering Faculty, Université catholique de Louvain, Louvain-la-Neuve, Belgium. E-mail:,
3  Institut d'Administration et de Gestion (IAG), Faculty of Economic, Social and Political Sciences, Université catholique de Louvain, Louvain-la-Neuve, Belgium and ESA - Université de Lille 2, France. E-mail:
4  Member IEEE

Prediction of financial time series using artificial neural networks has been the subject of many publications, even if the predictability of financial series remains a subject of scientific debate in the financial literature. Facing this difficulty, analysts often consider a large number of exogenous indicators, which makes the fitting of neural networks extremely difficult. In this paper, we analyze how to aggregate a large number of indicators in a smaller number using -possibly nonlinear- projection methods. Nonlinear projection methods are shown to be equivalent to the linear Principal Component Analysis when the prediction tool used on the new variables is linear. Furthermore, the computation of the nonlinear projection gives an objective way to evaluate the number of resulting indicators needed for the prediction. Finally, the advantages of nonlinear projection could be further exploited by using a subsequent nonlinear prediction model. The methodology developed in the paper is validated on data from the BEL20 market index, using systematic cross-validation results.

Key words: Time series, prediction, exogenous indicators, nonlinear projection, principal component analysis, market index, cross-validation

© EDP Sciences 2001