Calibrating rough volatility models: a convolutional neural network approach

DOI10.1080/14697688.2019.1654126MaRDI QIDQ4991028zbMATH OpenOpenAlexWikidataFDO

Authors Henry Stone

Publication date 2 June 2021

Published in Quantitative Finance (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1812.05315

zbMATH Keywords

estimationcalibrationconvolutional neural networksrough volatility

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Fractional processes, including fractional Brownian motion (60G22) Financial markets (91G15)

Abstract: In this paper we use convolutional neural networks to find the H"older exponent of simulated sample paths of the rBergomi model, a recently proposed stock price model used in mathematical finance. We contextualise this as a calibration problem, thereby providing a very practical and useful application.

Recommendations

• Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
• Deep Curve-Dependent PDEs for Affine Rough Volatility
• A neural network-based framework for financial model calibration
• THE FRACTIONAL VOLATILITY MODEL AND ROUGH VOLATILITY
• Pricing under rough volatility

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Deep hedging
• Deep learning
• Efficiently implementing the maximum likelihood estimator for Hurst exponent
• Estimating the Hurst parameter from short term volatility swaps: a Malliavin calculus approach
• Fractional Brownian Motions, Fractional Noises and Applications
• Pathwise large deviations for the rough Bergomi model
• Pricing under rough volatility
• Stochastic Calculus for Fractional Brownian Motion and Applications
• Volatility is rough

Cited in

(12)

• Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
• Unbiased deep solvers for linear parametric PDEs
• Fast hybrid schemes for fractional Riccati equations (rough is not so tough)
• Statistical inference for the first-order autoregressive process with the fractional Gaussian noise
• Calibration to FX triangles of the 4/2 model under the benchmark approach
• Asymptotics for volatility derivatives in multi-factor rough volatility models
• Deep Curve-Dependent PDEs for Affine Rough Volatility
• A martingale method for option pricing under a CEV-based fast-varying fractional stochastic volatility model
• Deep calibration of financial models: turning theory into practice
• Deep calibration with random grids
• Predicting critical transitions in multiscale dynamical systems using reservoir computing
• Optimal trade execution for Gaussian signals with power-law resilience

Describes a project that uses

Uses Software

• SqueezeDet
• Adam

This page was built for publication: Calibrating rough volatility models: a convolutional neural network approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4991028)