Architecture design of artificial neural networks based on Box & Jenkins models for time series prediction

Author

Diniz, Helio ; de Andrade, Luciano ; de Carvalho, André ; de Andrade, Marinho

Author_Institution

Comput. Intelligence Lab., Sao Paulo Univ., Brazil

fYear

1999

fDate

1999

Firstpage

29

Lastpage

34

Abstract

This paper reports the results of a neural architecture design approach for time series prediction. This approach applies some concepts of the Box-Jenkins (1970) method for data preprocessing and network design. The data used to verify the performance of these approaches were stock market time series of the Brazilian telecommunication company TELEBRAS

Keywords

financial data processing; forecasting theory; neural net architecture; performance evaluation; stock markets; telecommunication; time series; Box-Jenkins models; Brazilian telecommunication company; TELEBRAS; artificial neural network design; data preprocessing; neural architecture design; performance verification; stock market; time series prediction; Accuracy; Artificial neural networks; Autocorrelation; Data mining; Decision support systems; Neural networks; Predictive models; Stochastic processes; Stock markets; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Multimedia Applications, 1999. ICCIMA '99. Proceedings. Third International Conference on

Conference_Location

New Delhi

Print_ISBN

0-7695-0300-4

Type

conf

DOI

10.1109/ICCIMA.1999.798496

Filename

798496