An artificial neural network representation of the SABR stochastic volatility model
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
In this paper, the universal approximation theorem of artificial neural networks (ANNs) is applied to the stochastic alpha beta rho (SABR) stochastic volatility model in order to construct highly efficient representations. Initially, the SABR approximation of Hagan et al is considered, followed by the more accurate integration scheme of McGhee as well as a two-factor finite-difference scheme. The resulting ANN cal-culates 10 000 times faster than the finite-difference scheme while maintaining a high degree of accuracy. As a result, the ANN dispenses with the need for the commonly used SABR approximation.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Journal of Computational Finance |
Vol/bind | 25 |
Udgave nummer | 2 |
ISSN | 1460-1559 |
DOI | |
Status | Udgivet - 2021 |
Bibliografisk note
Funding Information:
The author would like to thank Romano Trabalzini, Colin Walsh, Paul McCaffrey, Christopher Potter, Vladimir Piterbarg and Katia Babbar for valuable comments made during the preparation of this paper; Chen Lyu for the closed form of the second moment of the mean integrated variance; and Hugo Hemingway-McGhee for assisting in the hardware setup and computational parallelization that made many of the calculations feasible. Thanks are also due to Rolf Poulsen and the Department of Mathematical Sciences at the University of Copenhagen for their support.
Publisher Copyright:
© 2021 Infopro Digital Risk (IP) Limited.
ID: 306673106