{"id":{"repo_id":"cape-town","oai_identifier":"oai:open.uct.ac.za:11427/36605"},"canonical_url":"https://search.dev.ndltd.org/etd/cape-town/oai:open.uct.ac.za:11427/36605","repository":{"repo_id":"cape-town","name":"University of Cape Town","base_url":"https://open.uct.ac.za/oai/request"},"display":{"title":"Gaussian process regression approach to pricing multi-asset American options","abstract":"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.","abstract_html":"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.","abstract_has_math":false,"creators":["Mokone, Christoffel Maboe"],"institution":"Department of Finance and Tax","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Ouwehand, Peter"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022","date_published":"2022","updated_at":"2026-07-22T22:23:22Z","subjects":["finance","tax"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11427/36605","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ouwehand, Peter"]},{"key":"dc:creator","label":"Author","values":["Mokone, Christoffel Maboe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-07-04T18:16:03Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-07-04T18:16:03Z"]},{"key":"dc:date.issued","label":"Date","values":["2022"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Department of Finance and Tax"]},{"key":"dc:type","label":"Dc Type","values":["Master Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Masters","MPhil"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["finance","tax"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11427/36605"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:title","label":"Title","values":["Gaussian process regression approach to pricing multi-asset American options"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ouwehand, Peter"],"dc:creator":["Mokone, Christoffel Maboe"],"dc:date.accessioned":["2022-07-04T18:16:03Z"],"dc:date.available":["2022-07-04T18:16:03Z"],"dc:date.issued":["2022"],"dc:description.abstract":["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."],"dc:identifier.uri":["http://hdl.handle.net/11427/36605"],"dc:publisher.department":["Department of Finance and Tax"],"dc:subject":["finance","tax"],"dc:title":["Gaussian process regression approach to pricing multi-asset American options"],"dc:type":["Master Thesis"],"dc:type.qualificationlevel":["Masters","MPhil"]},"updated_at":"2026-07-22T22:23:22Z"}