Extends rough fractional stochastic volatility to a multivariate fOU model with GMM estimation, simulation validation, and empirical analysis of realized volatility series showing correlations and spillover effects.
On deep calibration of (rough) stochastic volatility models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Techniques from deep learning play a more and more important role for the important task of calibration of financial models. The pioneering paper by Hernandez [Risk, 2017] was a catalyst for resurfacing interest in research in this area. In this paper we advocate an alternative (two-step) approach using deep learning techniques solely to learn the pricing map -- from model parameters to prices or implied volatilities -- rather than directly the calibrated model parameters as a function of observed market data. Having a fast and accurate neural-network-based approximating pricing map (first step), we can then (second step) use traditional model calibration algorithms. In this work we showcase a direct comparison of different potential approaches to the learning stage and present algorithms that provide a suffcient accuracy for practical use. We provide a first neural network-based calibration method for rough volatility models for which calibration can be done on the y. We demonstrate the method via a hands-on calibration engine on the rough Bergomi model, for which classical calibration techniques are diffcult to apply due to the high cost of all known numerical pricing methods. Furthermore, we display and compare different types of sampling and training methods and elaborate on their advantages under different objectives. As a further application we use the fast pricing method for a Bayesian analysis of the calibrated model.
representative citing papers
Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.
Truncated path signatures combined with XGBoost classify stochastic volatility model classes from simulated paths with high accuracy, including under random parameter variation and closely spaced Hurst parameters.
A hybrid deep learning approach using Price Approximator and Calibration Correction networks improves the efficiency and accuracy of Heston model calibration on S&P 500 option data.
citing papers explorer
-
Multivariate Rough Volatility
Extends rough fractional stochastic volatility to a multivariate fOU model with GMM estimation, simulation validation, and empirical analysis of realized volatility series showing correlations and spillover effects.
-
Robust financial calibration: a Bayesian approach for neural SDEs
Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.
-
Signature-based identification of volatility models from path geometry
Truncated path signatures combined with XGBoost classify stochastic volatility model classes from simulated paths with high accuracy, including under random parameter variation and closely spaced Hurst parameters.
-
Deep Learning-Enhanced Calibration of the Heston Model: A Unified Framework
A hybrid deep learning approach using Price Approximator and Calibration Correction networks improves the efficiency and accuracy of Heston model calibration on S&P 500 option data.