Abstract
A number of models exist to forecast financial time series. Forecasting results are hardly encouraging if based on statistical error indicators. However, in a trading perspective, even large statistical errors could produce good trading indications. We first present a set of structural and black-box methods that are used to model short, non-stationary time series dynamics. Then, we provide a trading model rule related to data volatility forecasts obtained by applying the ARCH methodology. Finally, out-of-sample forecast comparisons confirm that the trading rule is able to give better performance results for all the estimated models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bengio Y., Training a Neural Network with a Financial Criterion rather than a Prediction Criterion, in Weigend A. S.; Abu-Mostafa Y.; Refenes A.-P. N. (eds), Decision Technologies for Financial Engineering, NNCM’ 96 Proceedings, Singapore: World Scientific, 1997.
Engle R.F., Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of United Kingdom Inflation, in Econometrica, 1982; 50: 987–1008.
Episcopos A., Davis J., Predicting Returns on Canadian Exchange Rates with Artificial Neural Networks and Egarch-M Models, in Refenes A—P.N.; Abu-Mostafa Y.; Moody J.; Weigend A., (eds), Neural Networks in Financial Engineering, NNCM’ 95 Proceedings, Singapore: World Scientific, 1996.
Leitch G., Tanner J., Economic Forecast Evaluation: Profits versus the Conventional Error Measures, in The American Economic Review, 1991; 81: 580–590.
Moody J., Wu L., Optimization of Trading Systems and Portfolios, in Weigend A. S.; Abu-Mostafa Y; Refenes A-P. N. (eds), 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Bramante, R., Colombo, R., Gabbi, G. (1998). Are Neural Network and Econometric Forecasts Good for Trading? Stochastic Variance Models as a Filter Rule. In: Refenes, AP.N., Burgess, A.N., Moody, J.E. (eds) Decision Technologies for Computational Finance. Advances in Computational Management Science, vol 2. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5625-1_33
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5625-1_33
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-8309-3
Online ISBN: 978-1-4615-5625-1
eBook Packages: Springer Book Archive