Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility?
| dc.contributor.advisor | Huang, Chun-Sung | |
| dc.contributor.author | James, Andrew Michael | |
| dc.date.accessioned | 2025-02-13T08:58:26Z | |
| dc.date.available | 2025-02-13T08:58:26Z | |
| dc.date.issued | 2024 | |
| dc.date.updated | 2025-02-13T08:51:23Z | |
| dc.description.abstract | The aim of this study is to determine whether the inclusion of investor sentiment allows machine learning methods to produce improved predictions of volatility in equity markets. Specifically, the investor sentiment measure is constructed as an index by using search volume data of different search terms obtained from Google Trends. The resulting Financial and Economic Attitudes Revealed by Search (FEARS) index is then utilised as a feature to forecast volatility via three different machine learning (ML) techniques, namely the Random Forest, Artificial Neural Network (ANN), and Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) methods. A consolidated dataset, where all G7 countries were combined into a single series, as well as an individualised dataset, where each individual country is analysed independently, were used to test the different ML methods' volatility forecasting ability. Our results show that, for the consolidated dataset, the inclusion of the FEARS index does not provide significant additional predictive power. However, through the individualised dataset, the FEARS index was shown in certain cases to provide greater predictive accuracy. Furthermore, it was observed that the LSTM-RNN outperformed the ANN and Random Forest methods, which indicates that our volatility prediction indeed benefits from elements of prior periods' volatilities as feature variables. | |
| dc.identifier.apacitation | James, A. M. (2024). <i>Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility?</i>. (). University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax. Retrieved from http://hdl.handle.net/11427/40944 | en_ZA |
| dc.identifier.chicagocitation | James, Andrew Michael. <i>"Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility?."</i> ., University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax, 2024. http://hdl.handle.net/11427/40944 | en_ZA |
| dc.identifier.citation | James, A.M. 2024. Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility?. . University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax. http://hdl.handle.net/11427/40944 | en_ZA |
| dc.identifier.ris | TY - Thesis / Dissertation AU - James, Andrew Michael AB - The aim of this study is to determine whether the inclusion of investor sentiment allows machine learning methods to produce improved predictions of volatility in equity markets. Specifically, the investor sentiment measure is constructed as an index by using search volume data of different search terms obtained from Google Trends. The resulting Financial and Economic Attitudes Revealed by Search (FEARS) index is then utilised as a feature to forecast volatility via three different machine learning (ML) techniques, namely the Random Forest, Artificial Neural Network (ANN), and Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) methods. A consolidated dataset, where all G7 countries were combined into a single series, as well as an individualised dataset, where each individual country is analysed independently, were used to test the different ML methods' volatility forecasting ability. Our results show that, for the consolidated dataset, the inclusion of the FEARS index does not provide significant additional predictive power. However, through the individualised dataset, the FEARS index was shown in certain cases to provide greater predictive accuracy. Furthermore, it was observed that the LSTM-RNN outperformed the ANN and Random Forest methods, which indicates that our volatility prediction indeed benefits from elements of prior periods' volatilities as feature variables. DA - 2024 DB - OpenUCT DP - University of Cape Town KW - Economic Attitudes Revealed LK - https://open.uct.ac.za PB - University of Cape Town PY - 2024 T1 - Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility? TI - Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility? UR - http://hdl.handle.net/11427/40944 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/40944 | |
| dc.identifier.vancouvercitation | James AM. Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility?. []. University of Cape Town ,Faculty of Commerce ,Department of Finance and Tax, 2024 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/40944 | en_ZA |
| dc.language.rfc3066 | eng | |
| dc.publisher.department | Department of Finance and Tax | |
| dc.publisher.faculty | Faculty of Commerce | |
| dc.publisher.institution | University of Cape Town | |
| dc.subject | Economic Attitudes Revealed | |
| dc.title | Machine Learning with FEARS index: does the inclusion of investor sentiment improve a machine learning model's ability to predict volatility? | |
| dc.type | Thesis / Dissertation | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MCom |