Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | Can Machines Learn to Smile? Forecasting Implied Volatility Movements: A Machine Learning Approach |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Number of Pages | 81 |
| Date | 2023 |
| Abstract Text | To date, most attempts at modelling implied volatility rely on a priori assumptions about its dynamics. Machine learning methods, however, are not constrained to a pre-determined functional form. In this paper, machine learning methods are employed to forecast changes in the implied volatility of options written on S&P 500 futures. These models outperform naive predictions assessed on both standardised volatility surfaces and market quoted options, obtaining comparable performance with a benchmark deterministic model. The XGBoost model shows particularly promising results when incorporated into a minimum variance hedging strategy. In addition, the paper presents a robust adaption of the anchored eSSVI volatility surface parameterisation. |
| PDF File |
Download
|
| Export |
BibTeX
|