Zusammenfassung
There are various statistical techniques to estimate the market risk of a portfolio. This will most frequently be done by identifying market risk factors and modelling the impact of changes in market risk factors on the portfolio value. One increasingly popular measure for portfolio risk is the so called Value-at-Risk (VaR). This paper aims to show how VaR estimates can be obtained using a neural network approach. Results on a US-Dollar portfolio are compared to different VaR models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bundesaufsichtsamt für das Kreditwesen: Bekanntmachung über die Änderung und Ergänzung der Grundsätze über das Eigenkapital und die Liquidität der Kreditinstitute. Entwurf, October 1997.
Basle Committee on Banking Supervision: An internal model-based approach to market risk requirements. Basle 1995.
Bishop, C. M.: Mixture density networks. Technical Report NCRG/94/004, Neural Computing Research Group, Aston University, Birmingham 1994.
Bishop, C. M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford 1995.
Brachinger, H. W.; Steinhauser, U.: Konzepte zur Messung von Risiko – vom intuitiven Risikobegriff zum Value at Risk. Dresdner Beiträge zu Quantitativen Verfahren Nr. 22/98.
Butler, J. S.; Schachter, B.: Improving value-at-risk estimates by combining kernel estimation with historical simulation. Vanderbilt University, Nashville, TN/Comptroller of the currency, Washington DC 1996.
Crnkov C.; Drachman, J.:Quality control. Risk Magazine. 9 (1996) 9, S. 138–143.
Hsieh, D. A.: Implications of nonlinear dynamics for financial risk management. In: Journal of Financial and Quantitative Analysis 28 (1993) 1, S. 39–70.
Husmeier, D.; Taylor, J. G.: Neural networks for predicting conditional probability densities: Improved training scheme combining EM and RVFL. Technical Report KCL-MTH-97–47. Dept. of Mathematics, King’s College London 1997.
Jorion, P.: Value at Risk: The new benchmark for controlling market risk. Irwin, Chicago, London, Singapore 1997.
Jordan, M. I.; Xu, L.: Convergence results for the EM approach to mixtures of experts architectures. Technical Report A.I. Memo No. 1458, MIT, November 1993.
Kupiec, P.: Techniques for verifying the accuracy of risk measurement methods. In: Journal of Derivatives 2 (1995), S. 73–84.
Locarek-Junge, H.; Prinzler, R.: Die Beurteilung von Marktrisiken mit Künstlichen Neuronalen Netzen. In: Biethahn, J.; Hoenerloh, A.; Kuhl, J.; Leisewitz, M.C.; Nissen, V; Tietze, M (Hrsg.): Betriebswirtschaftliche Anwendungen des Soft Computing: Neuronale Netze, Fuzzy Logic und Evolutionäre Algorithmen. Vieweg 1998.
Neuneier, R.; Hergert, F.; Finnoff, W.; Ormoneit, D.: Estimation of conditional densities: A comparison of neural network approaches. In: Int. Conference on Artificial Neural Networks. ICANN’94, Sorrento, Italy 1994.
Ormoneit, D.; Tresp, V.: Improved gaussian mixture density estimates using bayesian penalty terms and network averaging. Technical report, Institut für Informatik (H2) TU München, Siemens AG, Munich 1995.
J. P. Morgan/Reuters: RiskMetrics™-Technical Document. 4th edn., Morgan Guaranty Trust Company, Reuters Ltd, New York 1996.
Weigend, A. S.; Srivastava, A. N.: Predicting conditional probability distributions. In: International Journal of Neural Systems 6 (1995).
Williams, P. M.: Using neural networks to model conditional multivariate densities. In: Neural Computation 8 (1996), S. 843–854.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Locarek-Junge, H., Prinzler, R. (1998). Estimating Value-at-Risk Using Neural Networks. In: Weinhardt, C., Selhausen, H.M.z., Morlock, M. (eds) Informationssysteme in der Finanzwirtschaft. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60327-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-60327-3_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-64355-2
Online ISBN: 978-3-642-60327-3
eBook Packages: Springer Book Archive