Abstract
The evaluation of the forecasting performance of a neural network is essential especially for practitioners. Measures such as mean square error (MSE in the following), mean error (ME) or mean absolute error(MAE) are widely used in applied econometrics. However, these measures are not very meaningful in forecasting, as we usually are interested in sign prediction only. On the other hand, economic performance measures (annualized return, Sharpe ratio, etc.) which are used to evaluate trading models, are sensitive to market behavior (trends, volatility) and have to be compared to benchmarks. In this paper we test for significant market timing ability in order to assess the performance of trading models based on neural nets. We use three modeling approaches and show that they have a significant influence on market timing ability.
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
Azoff M.E. Neural Network Time Series Forecasting of Financial Markets, John Wiley, New York, 1994
Bengio Y. “Training a Neural Network with a Financial Criterion Criterion Rather than a Prediction Criterion”, in: Weigend et al., Decision Technologies for Financial Engineering, Progress in Neural Processing 7,World Scientific, 1997
Choey M., Weigend A. “Nonlinear Trading ModelsThrough Sharpe Ratio Maximization”, in: Weigend et al., Decision Technologies for Financial Engineering, Progress in Neural Processing 7,World Scientific, 1997
Bishop C.M. Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995
Hendriksson R.D. and Merton R.C. On Market Timing and Investment Performance. II Statistical Procedures for Evaluating Forecasting Skills, Journal of Business, 1981, vol. 54, no.4
Hofmeister J. Kurzfristige Prognose des Bund-Futures mit neuronalen Netzen, Master Thesis, University of Ulm, May 1997
Menkhoff L. and Schlumberger M. Persistent Profitability of Technical Analysis on Foreign Exchange Markets?, Banca Nazionale del Lavoro Quaterly Review, vol. 48, no. 193,189–216, 1995
Moody J. and Wu L.Z. “Optimization of Trading Systems and Portfolios”, in: Weigend et al., Decision Technologies for Financial Engineering, Progress in Neural Processing 7,World Scientific, 1997
Reuters Technical Analysis for Unix, User Guide, London, 1994 Zimmermann H.G., and Weigend A.S. “Representing Dynamical Systems in Feed-Forward Networks: A Six Layer Architecture”, in: Weigend et al., Decision Technologies for Financial Engineering, Progress in Neural Processing 7, World Scientific, 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
Hann, T.H., Hofmeister, J. (1998). On the Market Timing Ability of Neural Networks: an Empirical Study Testing the Forecasting Performance. 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_37
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5625-1_37
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-8309-3
Online ISBN: 978-1-4615-5625-1
eBook Packages: Springer Book Archive