Neural network approximation for superhedging prices

DOI10.1111/MAFI.12363MaRDI QIDQ6054449zbMATH OpenOpenAlexWikidataFDO

Authors Francesca Biagini, Lukas Gonon, Thomas Reitsam

Publication date 28 September 2023

Published in Mathematical Finance (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2107.14113

zbMATH Keywords

deep learningquantile hedgingsuperhedging

Mathematics Subject Classification ID

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

Abstract: This article examines neural network-based approximations for the superhedging price process of a contingent claim in a discrete time market model. First we prove that the $alpha$-quantile hedging price converges to the superhedging price at time $0$ for $alpha$ tending to $1$, and show that the $alpha$-quantile hedging price can be approximated by a neural network-based price. This provides a neural network-based approximation for the superhedging price at time $0$ and also the superhedging strategy up to maturity. To obtain the superhedging price process for $t>0$, by using the Doob decomposition it is sufficient to determine the process of consumption. We show that it can be approximated by the essential supremum over a set of neural networks. Finally, we present numerical results.

Recommendations

• Explainable neural network for pricing and universal static hedging of contingent claims
• Neural networks for contingent claim pricing via the Galerkin method
• Neural network regression for Bermudan option pricing
• scientific article; zbMATH DE number 1304889
• Pricing of high-dimensional American options by neural networks

Cites work

• A super-replication theorem in Kabanov's model of transaction costs
• Deep hedging
• Deep learning
• Deep optimal stopping
• Duality for pathwise superhedging in continuous time
• Dynamic Programming and Pricing of Contingent Claims in an Incomplete Market
• HEDGING AND PORTFOLIO OPTIMIZATION UNDER TRANSACTION COSTS: A MARTINGALE APPROACH¹²
• Hedging under Transaction Costs in Currency Markets: a Continuous-Time Model
• Martingale Inequalities, Optimal Martingale Transport, and Robust Superhedging
• Model-free superhedging duality
• Optional decomposition of supermartingales and hedging contingent claims in incomplete security markets
• Pathwise superhedging on prediction sets
• Quantile hedging
• Robust estimation of superhedging prices
• Robust pricing-hedging dualities in continuous time
• Robust superhedging with jumps and diffusion
• Stochastic finance. An introduction in discrete time.
• Superhedging and dynamic risk measures under volatility uncertainty
• The robust superreplication problem: a dynamic approach
• The super-replication theorem under proportional transaction costs revisited
• There is no nontrivial hedging portfolio for option pricing with transaction costs

Cited in

(6)

• Explainable neural network for pricing and universal static hedging of contingent claims
• Neural networks for contingent claim pricing via the Galerkin method
• Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
• Option pricing in the Heston model with physics inspired neural networks
• Neural network empowered liquidity pricing in a two-price economy under conic finance settings
• Computing systemic risk measures with graph neural networks

This page was built for publication: Neural network approximation for superhedging prices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6054449)