Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Gaussian process regression approach to pricing multi-asset American options
This dissertation explores the problem of pricing American options in high dimensions using machine learning. In particular, the Gaussian Process Regression Monte Carlo (GPR-MC) algorithm developed by Goudenege et al (2019). is explored, and ` its performance, i.e., its accuracy and efficiency, is b...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Finance and Tax
2022
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613310611881984 |
|---|---|
| access_status_str | Open Access |
| author | Mokone, Christoffel Maboe |
| author2 | Ouwehand, Peter |
| author_browse | Mokone, Christoffel Maboe Ouwehand, Peter |
| author_facet | Ouwehand, Peter Mokone, Christoffel Maboe |
| author_sort | Mokone, Christoffel Maboe |
| collection | Thesis |
| description | This dissertation explores the problem of pricing American options in high dimensions using machine learning. In particular, the Gaussian Process Regression Monte Carlo (GPR-MC) algorithm developed by Goudenege et al (2019). is explored, and ` its performance, i.e., its accuracy and efficiency, is benchmarked against the Least Squares Regression Method (LSM) developed by Carriere (1996) and popularised by Longstaff and Schwartz (2001). In this dissertation, American options are approximated by Bermudan options due to limited computing power. To test the performance of GPR-MC, an American geometric mean basket put option, an American arithmetic mean basket put option and an American maximum call option are priced under the multi-asset Black-Scholes and Heston models, using both GPRMC and LSM. The algorithms are run a 100 times to obtain mean option values, 95% confidence intervals about the means, and average computational times. Numerical results show that the efficiency of GPR-MC is independent of the number of underlying assets, in contrast to the LSM method which is not. At 10 underlying assets, GPR-MC is shown to be more efficient than LSM. Moreover, GPR-MC is reasonably accurate, producing relative errors that are within reasonable bounds. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/36605 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:34:06.076Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Department of Finance and Tax |
| publisherStr | Department of Finance and Tax |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/36605 Gaussian process regression approach to pricing multi-asset American options Mokone, Christoffel Maboe Ouwehand, Peter finance tax This dissertation explores the problem of pricing American options in high dimensions using machine learning. In particular, the Gaussian Process Regression Monte Carlo (GPR-MC) algorithm developed by Goudenege et al (2019). is explored, and ` its performance, i.e., its accuracy and efficiency, is benchmarked against the Least Squares Regression Method (LSM) developed by Carriere (1996) and popularised by Longstaff and Schwartz (2001). In this dissertation, American options are approximated by Bermudan options due to limited computing power. To test the performance of GPR-MC, an American geometric mean basket put option, an American arithmetic mean basket put option and an American maximum call option are priced under the multi-asset Black-Scholes and Heston models, using both GPRMC and LSM. The algorithms are run a 100 times to obtain mean option values, 95% confidence intervals about the means, and average computational times. Numerical results show that the efficiency of GPR-MC is independent of the number of underlying assets, in contrast to the LSM method which is not. At 10 underlying assets, GPR-MC is shown to be more efficient than LSM. Moreover, GPR-MC is reasonably accurate, producing relative errors that are within reasonable bounds. 2022-07-04T18:16:03Z 2022-07-04T18:16:03Z 2022 2022-07-04T13:21:48Z Master Thesis Masters MPhil http://hdl.handle.net/11427/36605 eng application/pdf Department of Finance and Tax Faculty of Commerce |
| spellingShingle | finance tax Mokone, Christoffel Maboe Gaussian process regression approach to pricing multi-asset American options |
| thesis_degree_str | Master's |
| title | Gaussian process regression approach to pricing multi-asset American options |
| title_full | Gaussian process regression approach to pricing multi-asset American options |
| title_fullStr | Gaussian process regression approach to pricing multi-asset American options |
| title_full_unstemmed | Gaussian process regression approach to pricing multi-asset American options |
| title_short | Gaussian process regression approach to pricing multi-asset American options |
| title_sort | gaussian process regression approach to pricing multi asset american options |
| topic | finance tax |
| url | http://hdl.handle.net/11427/36605 |
| work_keys_str_mv | AT mokonechristoffelmaboe gaussianprocessregressionapproachtopricingmultiassetamericanoptions |