Deep Hedging under Rough Volatility

We investigate the performance of the Deep Hedging framework under training paths beyond the (finite dimensional) Markovian setup. In particular, we analyse the hedging performance of the original architecture under rough volatility models in view of existing theoretical results for those. Furthermore, we suggest parsimonious but suitable network architectures capable of capturing the non-Markoviantity of time-series. We also analyse the hedging behaviour in these models in terms of Profit and Loss (P&L) distributions and draw comparisons to jump diffusion models if the rebalancing frequency is realistically small.

[1]  Christian Schwarz,et al.  The Market Generator , 2019, SSRN Electronic Journal.

[3]  Magnus Wiese,et al.  Quant GANs: deep generation of financial time series , 2019, Quantitative Finance.

[4]  Terry Lyons,et al.  Generating Financial Markets With Signatures , 2020, SSRN Electronic Journal.

[5]  Paul Gassiat,et al.  On the martingale property in the rough Bergomi model , 2018, Electronic Communications in Probability.

[6]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[7]  Jorge A. León,et al.  On the short-time behavior of the implied volatility for jump-diffusion models with stochastic volatility , 2006, Finance Stochastics.

[8]  Jim Gatheral,et al.  Pricing under rough volatility , 2016 .

[9]  M. Rosenbaum,et al.  Rough volatility: Evidence from option prices , 2017, IISE Transactions.

[10]  J. Teichmann,et al.  Deep hedging , 2019, Quantitative Finance.

[11]  Magnus Wiese,et al.  Deep Hedging: Learning to Simulate Equity Option Markets , 2019, ArXiv.

[12]  Frederi Viens,et al.  A martingale approach for fractional Brownian motions and related path dependent PDEs , 2017, The Annals of Applied Probability.

[13]  T. Di Matteo Multi-scaling in finance , 2007 .

[14]  Blanka Horvath,et al.  Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models , 2021 .

[15]  Cornelis W. Oosterlee,et al.  A neural network-based framework for financial model calibration , 2019, Journal of Mathematics in Industry.

[16]  M. Kac On distributions of certain Wiener functionals , 1949 .

[17]  Christian Bayer,et al.  Deep calibration of rough stochastic volatility models , 2018, ArXiv.

[18]  T. Coleman,et al.  Calibration and hedging under jump diffusion , 2007 .

[19]  T. D. Matteo,et al.  Multi-scaling in finance , 2007 .

[20]  Deep Curve-dependent PDEs for affine rough volatility. , 2020, 1906.02551.

[21]  Bruno Dupire Functional Itô calculus† , 2019, Quantitative Finance.

[22]  Turbocharging Monte Carlo pricing for the rough Bergomi model , 2017, 1708.02563.

[23]  Artur Sepp An approximate distribution of delta-hedging errors in a jump-diffusion model with discrete trading and transaction costs , 2010 .

[24]  Andres Hernandez Model Calibration with Neural Networks , 2016 .

[25]  Fred Espen Benth,et al.  Accuracy of Deep Learning in Calibrating HJM Forward Curves , 2020 .

[26]  Ronnie Sircar,et al.  Optimal Static-Dynamic Hedges for Exotic Options under Convex Risk Measures , 2008 .

[27]  Mingxin Xu,et al.  Risk measure pricing and hedging in incomplete markets , 2006 .

[28]  Terry Lyons,et al.  A Data-Driven Market Simulator for Small Data Environments , 2020, SSRN Electronic Journal.

[29]  David Siska,et al.  Robust Pricing and Hedging via Neural SDEs , 2020, SSRN Electronic Journal.

[30]  Tianlin Xu,et al.  COT-GAN: Generating Sequential Data via Causal Optimal Transport , 2020, NeurIPS.

[31]  M. Rosenbaum,et al.  Volatility is rough , 2018 .

[32]  T. D. Matteo,et al.  Long-term memories of developed and emerging markets: Using the scaling analysis to characterize their stage of development , 2004, cond-mat/0403681.

[33]  Martin Schweizer,et al.  Variance-Optimal Hedging in Discrete Time , 1995, Math. Oper. Res..

[34]  Christa Cuchiero,et al.  A Generative Adversarial Network Approach to Calibration of Local Stochastic Volatility Models , 2020, Risks.

[35]  Rama Cont,et al.  Functional Ito calculus and stochastic integral representation of martingales , 2010, 1002.2446.

[36]  Christa Cuchiero,et al.  Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs , 2019, SIAM J. Math. Data Sci..

[37]  Masaaki Fukasawa,et al.  Asymptotic analysis for stochastic volatility: martingale expansion , 2011, Finance Stochastics.

[38]  Mikko S. Pakkanen,et al.  Hybrid scheme for Brownian semistationary processes , 2015, Finance Stochastics.