Publicação
Predicting the implied volatility surface via deep learning
| Resumo: | 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. |
|---|---|
| Autores principais: | Lee, Nicolas Yong Joon |
| Assunto: | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| _version_ | 1868983477996617728 |
|---|---|
| author | Lee, Nicolas Yong Joon |
| author_facet | Lee, Nicolas Yong Joon |
| author_role | author |
| contributor_name_str_mv | Rodrigues, Paulo Manuel Marques RUN |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Lee, Nicolas Yong Joon\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | Rodrigues, Paulo Manuel Marques RUN |
| datacite.creators.creator.creatorName.fl_str_mv | Lee, Nicolas Yong Joon |
| datacite.date.Accepted.fl_str_mv | 2025-01-24T00:00:00Z |
| datacite.date.available.fl_str_mv | 2025-08-07T09:23:55Z |
| datacite.date.embargoed.fl_str_mv | 2025-08-07T09:23:55Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| datacite.titles.title.fl_str_mv | Predicting the implied volatility surface via deep learning |
| dc.contributor.none.fl_str_mv | Rodrigues, Paulo Manuel Marques RUN |
| dc.creator.none.fl_str_mv | Lee, Nicolas Yong Joon |
| dc.date.Accepted.fl_str_mv | 2025-01-24T00:00:00Z |
| dc.date.available.fl_str_mv | 2025-08-07T09:23:55Z |
| dc.date.embargoed.fl_str_mv | 2025-08-07T09:23:55Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://hdl.handle.net/10362/186156 |
| dc.language.none.fl_str_mv | eng |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| dc.title.fl_str_mv | Predicting the implied volatility surface via deep learning |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_bdcc |
| description | 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. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | masterThesis |
| fulltext.url.fl_str_mv | https://run.unl.pt/bitstreams/b6759ade-c562-4b37-91d2-274d91fdede7/download |
| id | run_1dd3bd9d3685df8173ce2ae1e00a1db8 |
| identifier.url.fl_str_mv | http://hdl.handle.net/10362/186156 |
| inst_facet_str | urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa |
| instacron_str | unl |
| institution | Universidade Nova de Lisboa |
| instname_str | Universidade Nova de Lisboa |
| language | eng |
| network_acronym_str | run |
| network_name_str | Repositório Institucional da UNL |
| oai_identifier_str | oai:run.unl.pt:10362/186156 |
| organization_str_mv | urn:organizationAcronym:unl |
| person_str_mv | Lee, Nicolas Yong Joon |
| publishDate | 2025 |
| repo_facet_str | urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL |
| reponame_str | Repositório Institucional da UNL |
| repository_id_str | urn:repositoryAcronym:run |
| service_str_mv | urn:repositoryAcronym:run |
| spelling | engpt_PTThis 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.application/pdfpt_PTPredicting the implied volatility surface via deep learningLee, Nicolas Yong JoonRodrigues, Paulo Manuel MarquesHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptURNurn:tid:2039615362025-08-07T09:23:55Z2025-01-242024-12-172025-01-24T00:00:00ZHandlehttp://hdl.handle.net/10362/186156http://purl.org/coar/access_right/c_abf2open accessImplied volatility surfaceConvLSTMStochastic volatility inspiredVolatility forecastingDeep learningSelf-attention mechanismNeural networksVolatility surfaceIVS calibrationOptions pricing4673480 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesishttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/b6759ade-c562-4b37-91d2-274d91fdede7/download |
| spellingShingle | Predicting the implied volatility surface via deep learning Lee, Nicolas Yong Joon Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| status | SINGLETON |
| subject.fl_str_mv | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| title | Predicting the implied volatility surface via deep learning |
| title_full | Predicting the implied volatility surface via deep learning |
| title_fullStr | Predicting the implied volatility surface via deep learning |
| title_full_unstemmed | Predicting the implied volatility surface via deep learning |
| title_short | Predicting the implied volatility surface via deep learning |
| title_sort | Predicting the implied volatility surface via deep learning |
| topic | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| topic_facet | Implied volatility surface ConvLSTM Stochastic volatility inspired Volatility forecasting Deep learning Self-attention mechanism Neural networks Volatility surface IVS calibration Options pricing |
| url | http://hdl.handle.net/10362/186156 |
| visible | 1 |