Free Webinar: Matthew Dixon: Deep Local Volatility
Webinar
Thursday, April 30, 2020 - 06:30 PM
Until: Thursday, April 30, 2020 - 08:30 PM
(Adjusted for timezone: Europe/London)
Categories
PLEASE NOTE THAT THIS WEBINAR WILL START ON THURSDAY, 30 APRIL, 2020, AT 6:30 PM ***LONDON TIME*** (01.30 PM ***EDT***)
Deep learning for option pricing has emerged as a novel methodology for fast computations with applications in calibration and computation of Greeks. However, most of these approaches do not enforce any no-arbitrage conditions. In this talk, we develop a deep learning approach for no-arbitrage interpolation of European vanilla option prices. In particular, we demonstrate the modification of the standard deep learning methodology to enforce the no-arbitrage constraint and we specify the experimental design parameters that are needed for adequate performance. A novel component is the use of the Dupire formula to enforce bounds on the local volatility associated with (non-arbitrable) option prices, during the network fitting. Numerical results on real datasets of DAX vanilla options demonstrate the numerical error in the price, implied volatility and local volatility surface. This is joint work with Stephane Crepey and Marc Chataigner (University of Evry, Paris Saclay).
BIOGRAPHY
Assistant Professor in the Applied Math Department at the Illionois Institute of Technology. His research in computational methods for finance is funded by Intel.
Matthew began his career in structured credit trading at Lehman Brothers in London before pursuing academics and consulting for financial institutions in quantitative trading and risk modelling.
He holds a PhD in Applied Mathematics from Imperial College (2007) and has held postdoctoral and visiting professor appointments at Stanford University and UC Davis respectively.
He has published over 20 peer reviewed publications on machine learning and financial modelling, and has been cited in Bloomberg Markets and the Financial Times as an AI in fintech expert.
Matthew has also written the Springer book Machine Learning in Finance: From Theory to Practice.
To register, visit https://www.meetup.com/thalesians/events/270167217/. Link to join visible to attendees.
Deep learning for option pricing has emerged as a novel methodology for fast computations with applications in calibration and computation of Greeks. However, most of these approaches do not enforce any no-arbitrage conditions. In this talk, we develop a deep learning approach for no-arbitrage interpolation of European vanilla option prices. In particular, we demonstrate the modification of the standard deep learning methodology to enforce the no-arbitrage constraint and we specify the experimental design parameters that are needed for adequate performance. A novel component is the use of the Dupire formula to enforce bounds on the local volatility associated with (non-arbitrable) option prices, during the network fitting. Numerical results on real datasets of DAX vanilla options demonstrate the numerical error in the price, implied volatility and local volatility surface. This is joint work with Stephane Crepey and Marc Chataigner (University of Evry, Paris Saclay).
BIOGRAPHY
Assistant Professor in the Applied Math Department at the Illionois Institute of Technology. His research in computational methods for finance is funded by Intel.
Matthew began his career in structured credit trading at Lehman Brothers in London before pursuing academics and consulting for financial institutions in quantitative trading and risk modelling.
He holds a PhD in Applied Mathematics from Imperial College (2007) and has held postdoctoral and visiting professor appointments at Stanford University and UC Davis respectively.
He has published over 20 peer reviewed publications on machine learning and financial modelling, and has been cited in Bloomberg Markets and the Financial Times as an AI in fintech expert.
Matthew has also written the Springer book Machine Learning in Finance: From Theory to Practice.
To register, visit https://www.meetup.com/thalesians/events/270167217/. Link to join visible to attendees.