The Thalesians - Blanka Horvath: Deep Learning Volatility
Marriot Hotel Canary Wharf
Wednesday, April 24, 2019 - 06:30 PM
Until: Wednesday, April 24, 2019 - 08:30 PM
(Adjusted for timezone: Europe/London)
Categories
Deep Learning Volatility: On pricing and calibration of (rough) stochastic volatility models with deep neural networks
We present a powerful neural network based calibration method for a number of volatility models including the rough volatility family.
The aim of neural networks in this work is an off-line approximation of complex pricing functions, which are difficult to represent or time-consuming to evaluate by other means. We highlight how this perspective opens new horizons for quantitative modelling: The calibration bottleneck posed by a slow pricing of derivative contracts is lifted. This brings several model families (such as rough volatility models) within the scope of applicability in industry practice. As customary for machine learning, the form in which information from available data is extracted and stored is crucial for network performance. With this in mind we discuss how our approach addresses the usual challenges of machine learning solutions in a financial context (availability of training data, interpretability of results for regulators, control over generalisation errors). We present specific architectures for price approximation and calibration and optimize these with respect different objectives regarding accuracy, speed and robustness. We also find that including the intermediate step of learning pricing functions of (classical or rough) volatility models before calibration significantly improves the generalisation performance compared to the performance of deep calibration networks that are trained directly on data.
£15/ person
Further info:
https://www.meetup.com/thalesians/events/257969639/
We present a powerful neural network based calibration method for a number of volatility models including the rough volatility family.
The aim of neural networks in this work is an off-line approximation of complex pricing functions, which are difficult to represent or time-consuming to evaluate by other means. We highlight how this perspective opens new horizons for quantitative modelling: The calibration bottleneck posed by a slow pricing of derivative contracts is lifted. This brings several model families (such as rough volatility models) within the scope of applicability in industry practice. As customary for machine learning, the form in which information from available data is extracted and stored is crucial for network performance. With this in mind we discuss how our approach addresses the usual challenges of machine learning solutions in a financial context (availability of training data, interpretability of results for regulators, control over generalisation errors). We present specific architectures for price approximation and calibration and optimize these with respect different objectives regarding accuracy, speed and robustness. We also find that including the intermediate step of learning pricing functions of (classical or rough) volatility models before calibration significantly improves the generalisation performance compared to the performance of deep calibration networks that are trained directly on data.
£15/ person
Further info:
https://www.meetup.com/thalesians/events/257969639/