Publicação
Predicting the implied volatility surface via deep learning
| datacite.subject.fos | Ciências Sociais::Economia e Gestão | pt_PT |
| dc.contributor.advisor | Rodrigues, Paulo Manuel Marques | |
| dc.contributor.author | Lee, Nicolas Yong Joon | |
| dc.date.accessioned | 2025-08-07T09:23:55Z | |
| dc.date.available | 2025-08-07T09:23:55Z | |
| dc.date.issued | 2025-01-24 | |
| dc.date.submitted | 2024-12-17 | |
| dc.description.abstract | This thesis explores deep learning techniques for predicting the implied volatility surface (IVS), a critical component in options pricing and risk management. By applying ConvLSTM and Self-Attention mechanisms, the study evaluates their ability to capture spatial and temporal patterns across strikes and maturities. Results show that grid-based ConvLSTM excels in short-term forecasting, while Self-Attention enhances long-term accuracy by capturing global dependencies. The models were retrained and evaluated under volatile regimes, including the COVID-19 crash, testing their robustness in extreme market conditions. The findings contribute to improved IV surface predictions, benefiting strategies like volatility arbitrage and dynamic hedging. | pt_PT |
| dc.identifier.tid | 203961536 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/186156 | |
| dc.language.iso | eng | pt_PT |
| dc.relation | UID/ECO/00124/2013 | pt_PT |
| dc.subject | Implied volatility surface | pt_PT |
| dc.subject | ConvLSTM | pt_PT |
| dc.subject | Stochastic volatility inspired | pt_PT |
| dc.subject | Volatility forecasting | pt_PT |
| dc.subject | Deep learning | pt_PT |
| dc.subject | Self-attention mechanism | pt_PT |
| dc.subject | Neural networks | pt_PT |
| dc.subject | Volatility surface | pt_PT |
| dc.subject | IVS calibration | pt_PT |
| dc.subject | Options pricing | pt_PT |
| dc.title | Predicting the implied volatility surface via deep learning | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | A Work Project, presented as part of the requirements for the Award of a Master’s degree in Finance from the Nova School of Business and Economics | pt_PT |