A comparative analysis of machine learning models for forecasting JSE Stock Returns

dc.contributor.advisorVan Rensburg, Paul
dc.contributor.authorMuir, Cameron James
dc.date.accessioned2026-01-09T11:14:19Z
dc.date.available2026-01-09T11:14:19Z
dc.date.issued2025
dc.date.updated2026-01-06T13:00:08Z
dc.description.abstractThis study examines the application of machine learning models to predict the cross-section of Johannesburg Stock Exchange (JSE)- listed share returns. Four models are developed and compared using monthly data from 2005 to 2021: neural networks, random forest, long short- term memory (LSTM) networks, and conventional linear regression. The explanatory variables comprise nine firm-specific financial metrics, motivated by prior research. The sample is divided into a training period (2005–2016) and a testing period (2016–2021), further split into 1-year, 3-year, and 5-year testing intervals. The results show that the LSTM model performsbest across most evaluation metrics and investment scenarios, with the random forest model close behind, offering slightly better risk-adjusted returns.
dc.identifier.apacitationMuir, C. J. (2025). <i>A comparative analysis of machine learning models for forecasting JSE Stock Returns</i>. (). University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax. Retrieved from http://hdl.handle.net/11427/42503en_ZA
dc.identifier.chicagocitationMuir, Cameron James. <i>"A comparative analysis of machine learning models for forecasting JSE Stock Returns."</i> ., University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax, 2025. http://hdl.handle.net/11427/42503en_ZA
dc.identifier.citationMuir, C.J. 2025. A comparative analysis of machine learning models for forecasting JSE Stock Returns. . University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax. http://hdl.handle.net/11427/42503en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Muir, Cameron James AB - This study examines the application of machine learning models to predict the cross-section of Johannesburg Stock Exchange (JSE)- listed share returns. Four models are developed and compared using monthly data from 2005 to 2021: neural networks, random forest, long short- term memory (LSTM) networks, and conventional linear regression. The explanatory variables comprise nine firm-specific financial metrics, motivated by prior research. The sample is divided into a training period (2005–2016) and a testing period (2016–2021), further split into 1-year, 3-year, and 5-year testing intervals. The results show that the LSTM model performsbest across most evaluation metrics and investment scenarios, with the random forest model close behind, offering slightly better risk-adjusted returns. DA - 2025 DB - OpenUCT DP - University of Cape Town KW - JSE KW - Stock returns LK - https://open.uct.ac.za PB - University of Cape Town PY - 2025 T1 - A comparative analysis of machine learning models for forecasting JSE Stock Returns TI - A comparative analysis of machine learning models for forecasting JSE Stock Returns UR - http://hdl.handle.net/11427/42503 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/42503
dc.identifier.vancouvercitationMuir CJ. A comparative analysis of machine learning models for forecasting JSE Stock Returns. []. University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax, 2025 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/42503en_ZA
dc.language.isoen
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Finance and Tax
dc.publisher.facultyFaculty of Commerce
dc.publisher.institutionUniversity of Cape Town
dc.subjectJSE
dc.subjectStock returns
dc.titleA comparative analysis of machine learning models for forecasting JSE Stock Returns
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMCom
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_com_2025_muir cameron james.pdf
Size:
2.15 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