Zusammenfassung
Results are reported on applying neural networks to tasks of predicting economic data. These are, on the one hand, stock prices or foreign exchange rates and, on the other hand, the daily numbers of sales of a German newspaper.
Starting from our network “George”, which very successfully traded at New York stock exchange for nearly two years, our methods of evolving neural networks for forecasting tasks have been Bayesian optimization, input compression, and multitasking. The networks obtained have been applied to several markets.
Experiences with predicting sales numbers of a specific product are relatively new. The situation differs essentially from that one concerning prices or exchange rates, but the results are equally convincing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
Bishop, C. M. (1995) Neural Networks for Pattern Recognition, volume 1. Oxford University Press, New York
Braun, H. (1997) Neuronale Netze - Optimierung durch Lernen und Evolution. Springer-Verlag Berlin Heidelberg New York
Braun, H., Feulner, J., Ulrich, U. (1991) Learning strategies for solving the problem of planning using backpropagation. In: Proc. NEURO-Nimes 91, 4th International Conference on Neural Networks and their Applications
Gutjahr, St. (1997) Improving neural prediction systems by building independent committees. In: Proc. 4th International Conference on Neural Networks in the Capital Market, Pasadena, USA
Gutjahr, St. (1998) Improving the determination of the hyperparameters in Bayesian learning. In: Proc. North Australian Conference on Neural Networks (ACNN), Brisbane, Australia, 114–118
Gutjahr, St. (1999) Optimierung neuronaler Netze mit der Bayes’schen Methode. Dissertation Universität Karlsruhe
Gutjahr, St., Riedmiller, M., and Klingemann, J. (1997) Daily prediction of the foreign exchange rate between the US dollar and the German mark using neural networks. The Joint Pacific Asian Conference on Expert Systems/Singapore International Conference on Intelligent Systems
Hild, H., Feulner, J., Menzel, W. (1992) HARMONET: A neural net for harmonizing chorals in the style of J. S. Bach. In: Advances in Neural Information Processing 4 (NIPS 4), 267–274
Klingemann, J. (1994) Prognose des Dollarkurses mit neuronalen Netzen. Diplomarbeit Fakultät für Informatik, Universität Karlsruhe
Menzel, W. (1998) Problem Solving with Neural Networks. In: Ratsch, U., Richter, M., Stamatescu, I. O. (Eds.): Intelligence and Artificial Intelligence - an Interdisciplinary Debate. Springer-Verlag Berlin Heidelberg New York, 162–177
Ragg, Th. (1999) Direkte Mitteilung. Die Resultate werden in einer für das Jahr 2000 geplanten Dissertation enthalten sein.
Ragg, Th. and Gutjahr, St. (1997) Automatic Determination of Optimal Network Topologies based on Information Theory and Evolution. In: Proc. of the 23rd EUROMICRO Conference, IEEE, 549–555
Ragg, Th. and Gutjahr, St. (1997) Building High Performant Classifiers by Integrating Bayesian Learning, Mutual Information and Committee Techniques - A Case Study in Time Series Prediction. In: Proc. of the International Conference on Artificial Neural Networks, Lausanne, Switzerland, Lecture Notes in Computer Science 1327, Springer-Verlag Berlin Heidelberg New York
Riedmiller, M. (1994) Advanced supervised learning in multilayer perceptrons - From backpropagation to adaptive learning algorithms. Computer Standards and Interfaces 16, 265–278
Riedmiller, M. and Braun, H. (1993) A direct adaptive method for faster back-propagation learning: The RPROP algorithm. In: Proc. IEEE International Conference on Neural Networks (ICNN), San Francisco, USA, 586–591
Silverman, B.W. (1986) Density Estimation for Statistics and Data Analysis. Chapman and Hall
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Menzel, W. (2000). Neuronale Netze zur Prognose von Finanzzeitreihen und Absatzzahlen. In: Bol, G., Nakhaeizadeh, G., Vollmer, KH. (eds) Datamining und Computational Finance. Wirtschaftswissenschaftliche Beiträge, vol 174. Physica, Heidelberg. https://doi.org/10.1007/978-3-642-57656-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-57656-0_7
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1284-8
Online ISBN: 978-3-642-57656-0
eBook Packages: Springer Book Archive