Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | Testing stock returns predictability using option data: A machine learning approach |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Date | 2020 |
| Abstract Text | The informational content of option data has long been studied in the context of stocks’ return predictability, with research clearly showing the existence of predictive power. This thesis tries to leverage this information by extracting specific features from the implied volatility surface and use them as additional inputs in a predefined high dimensional prediction model. Nine statistical methods are implemented and compared using various performance measures. The results clearly show that none of the additional features can provide an improvement in the forecasting power of the models, which could stem from the poor features choice as well as the limited data availability inherited from using option market data. |
| Export |
BibTeX
|