Abstract: The estimation of loss distributions for dynamic portfolios requires the simulation of scenarios representing realistic joint dynamics of their components. Scalability to large or heterogeneous portfolios involving multiple asset classes is particularly challenging, as is the accurate representation of tail risk.

We propose a novel data-driven approach for the simulation of realistic multi-asset scenarios with a particular focus on the accurate estimation of tail risk for a given class of static and dynamic portfolios selected by the user. By exploiting the joint elicitability property of Value-at-Risk (VaR) and Expected Shortfall (ES), we design a Generative Adversarial Network (GAN) architecture capable of learning to simulate price scenarios that preserve tail risk features for these benchmark trading strategies, leading to consistent estimators for their Value-at-Risk and Expected Shortfall. We demonstrate the accuracy and scalability of our method via extensive simulation experiments using synthetic and market data. Our results show that, in contrast to other data-driven scenario generators, our proposed scenario simulation method correctly captures tail risk for both static and dynamic portfolios.

This is based on joint work with Mihai Cucuringu (Oxford), RenYuan XU (USC) and Chao Zhang (Oxford).

Bio: Rama Cont is Professor of Mathematics and Chair of Mathematical Finance at the University of Oxford and Director of the EPSRC Centre for Doctoral Training in Mathematics of Random Systems.

Rama Cont's research focuses on stochastic analysis, stochastic processes and mathematical modeling in finance, in particular the modeling of extreme market risks, liquidity risk and systemic risk and pathwise approaches in stochastic analysis. He has co-authored more than 80 research publications, including the widely cited monograph Financial Modelling with Jump Processes (2003).

He was the founding director of the Columbia Centre for Financial Engineering and founding director of the CFM-Imperial Institute of Quantitative Finance from 2014 to 2018.

Prof. Cont was awarded the Louis Bachelier Prize by the French Academy of Sciences in 2010 for his research on mathematical modeling in finance and the Royal Society Award for Excellence in Interdisciplinary Research in 2017 for his work on systemic risk modelling. He was elected Fellow of the Society for Industrial and Applied Mathematics (SIAM) in 2017 for his 'contributions to stochastic analysis and mathematical modeling in finance.

Meeting Recording: https://ucsb.zoom.us/rec/share/wIIaihUR9iRNCybmmQcLjIQcY-1mbotCq5CRli7om9G35UTrM2P4dAAP8Qq7oYOM._XyNDePEWoy0VpqO

Access Passcode: yuR$H1j$