Free Access
Volume 14, Number 1, 2000
Neural Models in Economy and Management Science
Page(s) 81 - 91
DOI: 10.1051/ejess:2000110

European Journal of Economic and Social Systems 14 N$^\circ$ 1 (2000) 81-91

Non-linear financial time series forecasting - Application to the Bel 20 stock market index

A. Lendasse, E. de Bodt, V. Wertz and M. Verleysen

1Université catholique de Louvain, CESAME-AUTO, 4 av. G. Lemaître, 1348 Louvain-la-Neuve, Belgium, {lendasse, wertz}
2Université de Lille 2, ESA-GERME Université catholique de Louvain, IAG-FIN, Belgium,
3Université catholique de Louvain, CERTI, 3 pl. du Levant, 1348 Louvain-la-Neuve, Belgium, Michel Verleysen is a research associate of the belgian FNRS


We developed in this paper a method to predict time series with non-linear tools. The specificity of the method is to use as much information as possible as input to the model (many past values of the series, many exogenous variables), to compress this information (by a non-linear method) in order to obtain a state vector of limited size, facilitating the subsequent regression and the generalization ability of the forecasting algorithm and to fit a non-linear regressor (here a RBF neural network) on the reduced vectors. We show that this method is able to find non-linear relationships in artificial and real-world financial series. On a difficult task, which consists in forecasting the tendency of the Bel 20 stock market index, we show that this method improves the results compared both to linear models and to non-linear ones where the non-linear compression is not used.

Keywords: time series forecasting, neural networks stock index prediction, curvilinear component analysis

Copyright EDP Sciences 2000