Title :
Forecasting the IBOVESPA using NARX networks and random walk model
Author :
Oliveira, Eleonora Ma Jesus ; Ludermir, Teresa B.
Author_Institution :
Centro de Informatica, Fed. Univ. of Pernambuco, Recife, Brazil
Abstract :
The objective of this work was to apply an important class of nonlinear systems for discrete time, called NARX networks, to carry through accurate forecasts of the daily maximum price series in the IBOVESPA, since it depends on random, nonlinear and multivariate factors, making it difficult to forecast using the conventional techniques.
Keywords :
autoregressive processes; financial data processing; neural nets; random processes; stock markets; time series; IBOVESPA; daily maximum price; discrete time systems; financial market; multivariate nonlinear systems; neural networks; time series forecast; Delay effects; Least squares methods; Manipulator dynamics; Neural networks; Neurons; Newton method; Nonlinear systems; Predictive models; Recursive estimation; Surges;
Conference_Titel :
Neural Networks, 2002. SBRN 2002. Proceedings. VII Brazilian Symposium on
Print_ISBN :
0-7695-1709-9
DOI :
10.1109/SBRN.2002.1181449
