Data-driven hedging of stock index options via deep learning

DOI10.1016/J.ORL.2023.05.007MaRDI QIDQ6047693zbMATH OpenOpenAlexFDO

Authors

Publication date 12 September 2023

Published in Operations Research Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2111.03477, https://econpapers.repec.org/RePEc:arx:papers:2111.03477

zbMATH Keywords

data-drivendeep learninghedgingindex optionsmarket sentiment

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Derivative securities (option pricing, hedging, etc.) (91G20)

Abstract: We develop deep learning models to learn the hedge ratio for S&P500 index options directly from options data. We compare different combinations of features and show that a feedforward neural network model with time to maturity, Black-Scholes delta and a sentiment variable (VIX for calls and index return for puts) as input features performs the best in the out-of-sample test. This model significantly outperforms the standard hedging practice that uses the Black-Scholes delta and a recent data-driven model. Our results demonstrate the importance of market sentiment for hedging efficiency, a factor previously ignored in developing hedging strategies.

Recommendations

• Empirical deep hedging
• Learning minimum variance discrete hedging directly from the market
• Deep hedging
• Hedging Option Books Using Neural-SDE Market Models
• A data-driven deep learning approach for options market making

Cites work

• A closed-form solution for options with stochastic volatility with applications to bond and currency options
• A data-driven deep learning approach for options market making
• A neural network approach to understanding implied volatility movements
• A two-step framework for arbitrage-free prediction of the implied volatility surface
• Deep hedging
• Deep learning
• Deep learning for limit order books
• Deep learning for ranking response surfaces with applications to optimal stopping problems
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• DGM: a deep learning algorithm for solving partial differential equations
• Dynamic hedging under jump diffusion with transaction costs
• scientific article; zbMATH DE number 5227619 (Why is no real title available?)
• Learning minimum variance discrete hedging directly from the market
• Pure jump models for pricing and hedging VIX derivatives
• Solving high-dimensional partial differential equations using deep learning

Cited in

(2)

• Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S\&P 500
• Deep learning for enhanced index tracking

This page was built for publication: Data-driven hedging of stock index options via deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6047693)