Model-agnostic pricing of exotic derivatives using signatures
<p>Neural networks hold out the promise of fast and reliable derivative pricing. Such an approach usually involves the supervised learning task of mapping contract and model parameters to derivative prices.</p> <p>In this work, we introduce a model-agnostic path-wise approach to de...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Association of Computing Machinery
2022
|
| _version_ | 1797110339196682240 |
|---|---|
| author | Alden, A Ventre, C Horvath, B Lee, G |
| author_facet | Alden, A Ventre, C Horvath, B Lee, G |
| author_sort | Alden, A |
| collection | OXFORD |
| description | <p>Neural networks hold out the promise of fast and reliable derivative pricing. Such an approach usually involves the supervised learning task of mapping contract and model parameters to derivative prices.</p>
<p>In this work, we introduce a model-agnostic path-wise approach to derivative pricing using higher-order distribution regression. Our methodology leverages the 2nd-order Maximum Mean Discrepancy (MMD), a notion of distance between stochastic processes based on path signatures. To overcome the high computational cost of its calculation, we pre-train a neural network that can quickly and accurately compute higher-order MMDs. This allows the combination of distribution regression with neural networks in a computationally feasible way. We test our model on down-and-in barrier options. We demonstrate that our path-wise approach extends well to the high-dimensional case by applying it to rainbow options and autocallables. Our approach has a significant speed-up over Monte Carlo pricing.</p> |
| first_indexed | 2024-03-07T07:53:35Z |
| format | Conference item |
| id | oxford-uuid:d44a481e-582a-4e3e-8b4e-a6e70d34d31f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:53:35Z |
| publishDate | 2022 |
| publisher | Association of Computing Machinery |
| record_format | dspace |
| spelling | oxford-uuid:d44a481e-582a-4e3e-8b4e-a6e70d34d31f2023-07-25T12:45:20ZModel-agnostic pricing of exotic derivatives using signaturesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d44a481e-582a-4e3e-8b4e-a6e70d34d31fEnglishSymplectic ElementsAssociation of Computing Machinery2022Alden, AVentre, CHorvath, BLee, G<p>Neural networks hold out the promise of fast and reliable derivative pricing. Such an approach usually involves the supervised learning task of mapping contract and model parameters to derivative prices.</p> <p>In this work, we introduce a model-agnostic path-wise approach to derivative pricing using higher-order distribution regression. Our methodology leverages the 2nd-order Maximum Mean Discrepancy (MMD), a notion of distance between stochastic processes based on path signatures. To overcome the high computational cost of its calculation, we pre-train a neural network that can quickly and accurately compute higher-order MMDs. This allows the combination of distribution regression with neural networks in a computationally feasible way. We test our model on down-and-in barrier options. We demonstrate that our path-wise approach extends well to the high-dimensional case by applying it to rainbow options and autocallables. Our approach has a significant speed-up over Monte Carlo pricing.</p> |
| spellingShingle | Alden, A Ventre, C Horvath, B Lee, G Model-agnostic pricing of exotic derivatives using signatures |
| title | Model-agnostic pricing of exotic derivatives using signatures |
| title_full | Model-agnostic pricing of exotic derivatives using signatures |
| title_fullStr | Model-agnostic pricing of exotic derivatives using signatures |
| title_full_unstemmed | Model-agnostic pricing of exotic derivatives using signatures |
| title_short | Model-agnostic pricing of exotic derivatives using signatures |
| title_sort | model agnostic pricing of exotic derivatives using signatures |
| work_keys_str_mv | AT aldena modelagnosticpricingofexoticderivativesusingsignatures AT ventrec modelagnosticpricingofexoticderivativesusingsignatures AT horvathb modelagnosticpricingofexoticderivativesusingsignatures AT leeg modelagnosticpricingofexoticderivativesusingsignatures |