Gaussian Process Regression for a Single Underlying Autocallable Security

dc.contributor.advisorOuwehand, Peter
dc.contributor.authorHerbert, Rebecca
dc.date.accessioned2024-04-29T10:03:22Z
dc.date.available2024-04-29T10:03:22Z
dc.date.issued2023
dc.date.updated2024-04-25T14:11:18Z
dc.description.abstractTraditionally in Quantitative Finance, in order to price exotic options, particu- larly with path dependency, time consuming Monte Carlo simulations are done. This dissertation considers the use of the machine learning technique Gaussian Process Regression (GPR) as a faster pricing alternative to Monte Carlo simula- tions. The speed of calculation is of interest since prices are linked to fast moving market variables. We focus on the pricing of a single underlying autocallable under GPR against its traditional pricing under the Stochastic Local Volatility (SLV) model. An autocallable is a structured product which allows for early redemption when the underlying meets certain barrier conditions. Due to its path dependency, autocallables are typically priced using Monte Carlo simula- tions under an SLV model which captures realistic market dynamics by allowing volatility to be modelled as stochastic rather than assumed constant, but also allows for more precise calibration by including a local volatility component. We find that a desired level of accuracy is achieved only for autocallable prices under the Schobel-Zhu SLV model, with computation speeds slightly slowler than Monte Carlo simulations.
dc.identifier.apacitationHerbert, R. (2023). <i>Gaussian Process Regression for a Single Underlying Autocallable Security</i>. (). ,Faculty of Commerce ,Department of Finance and Tax. Retrieved from http://hdl.handle.net/11427/39468en_ZA
dc.identifier.chicagocitationHerbert, Rebecca. <i>"Gaussian Process Regression for a Single Underlying Autocallable Security."</i> ., ,Faculty of Commerce ,Department of Finance and Tax, 2023. http://hdl.handle.net/11427/39468en_ZA
dc.identifier.citationHerbert, R. 2023. Gaussian Process Regression for a Single Underlying Autocallable Security. . ,Faculty of Commerce ,Department of Finance and Tax. http://hdl.handle.net/11427/39468en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Herbert, Rebecca AB - Traditionally in Quantitative Finance, in order to price exotic options, particu- larly with path dependency, time consuming Monte Carlo simulations are done. This dissertation considers the use of the machine learning technique Gaussian Process Regression (GPR) as a faster pricing alternative to Monte Carlo simula- tions. The speed of calculation is of interest since prices are linked to fast moving market variables. We focus on the pricing of a single underlying autocallable under GPR against its traditional pricing under the Stochastic Local Volatility (SLV) model. An autocallable is a structured product which allows for early redemption when the underlying meets certain barrier conditions. Due to its path dependency, autocallables are typically priced using Monte Carlo simula- tions under an SLV model which captures realistic market dynamics by allowing volatility to be modelled as stochastic rather than assumed constant, but also allows for more precise calibration by including a local volatility component. We find that a desired level of accuracy is achieved only for autocallable prices under the Schobel-Zhu SLV model, with computation speeds slightly slowler than Monte Carlo simulations. DA - 2023 DB - OpenUCT DP - University of Cape Town KW - Commerce LK - https://open.uct.ac.za PY - 2023 T1 - Gaussian Process Regression for a Single Underlying Autocallable Security TI - Gaussian Process Regression for a Single Underlying Autocallable Security UR - http://hdl.handle.net/11427/39468 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/39468
dc.identifier.vancouvercitationHerbert R. Gaussian Process Regression for a Single Underlying Autocallable Security. []. ,Faculty of Commerce ,Department of Finance and Tax, 2023 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/39468en_ZA
dc.language.rfc3066Eng
dc.publisher.departmentDepartment of Finance and Tax
dc.publisher.facultyFaculty of Commerce
dc.subjectCommerce
dc.titleGaussian Process Regression for a Single Underlying Autocallable Security
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMPhil
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_com_2023_herbert rebecca.pdf
Size:
2.01 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections