An artificial neural network representation of the SABR stochastic volatility model

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

An artificial neural network representation of the SABR stochastic volatility model. / McGhee, William A.

I: Journal of Computational Finance, Bind 25, Nr. 2, 2021.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

McGhee, WA 2021, 'An artificial neural network representation of the SABR stochastic volatility model', Journal of Computational Finance, bind 25, nr. 2. https://doi.org/10.21314/JCF.2021.007

APA

McGhee, W. A. (2021). An artificial neural network representation of the SABR stochastic volatility model. Journal of Computational Finance, 25(2). https://doi.org/10.21314/JCF.2021.007

Vancouver

McGhee WA. An artificial neural network representation of the SABR stochastic volatility model. Journal of Computational Finance. 2021;25(2). https://doi.org/10.21314/JCF.2021.007

Author

McGhee, William A. / An artificial neural network representation of the SABR stochastic volatility model. I: Journal of Computational Finance. 2021 ; Bind 25, Nr. 2.

Bibtex

@article{612a831fd19641e8adf09d8a6d8bcc91,
title = "An artificial neural network representation of the SABR stochastic volatility model",
abstract = "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.",
keywords = "artificial neural network, SABR approximation, SABR integration scheme, stochastic alpha beta rho (SABR) model, stochastic volatility, universal approximation theorem",
author = "McGhee, {William A.}",
note = "Publisher Copyright: {\textcopyright} 2021 Infopro Digital Risk (IP) Limited.",
year = "2021",
doi = "10.21314/JCF.2021.007",
language = "English",
volume = "25",
journal = "Journal of Computational Finance",
issn = "1460-1559",
publisher = "Incisive Media Ltd.",
number = "2",

}

RIS

TY - JOUR

T1 - An artificial neural network representation of the SABR stochastic volatility model

AU - McGhee, William A.

N1 - Publisher Copyright: © 2021 Infopro Digital Risk (IP) Limited.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - artificial neural network

KW - SABR approximation

KW - SABR integration scheme

KW - stochastic alpha beta rho (SABR) model

KW - stochastic volatility

KW - universal approximation theorem

U2 - 10.21314/JCF.2021.007

DO - 10.21314/JCF.2021.007

M3 - Journal article

AN - SCOPUS:85127611862

VL - 25

JO - Journal of Computational Finance

JF - Journal of Computational Finance

SN - 1460-1559

IS - 2

ER -

ID: 306673106