Deep Quadratic Hedging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gnoatto, Alessandro, Lavagnini, Silvia, Picarelli, Athena
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912129186004992
author Gnoatto, Alessandro
Lavagnini, Silvia
Picarelli, Athena
author_facet Gnoatto, Alessandro
Lavagnini, Silvia
Picarelli, Athena
contents We propose a novel computational procedure for quadratic hedging in high-dimensional incomplete markets, covering mean-variance hedging and local risk minimization. Starting from the observation that both quadratic approaches can be treated from the point of view of backward stochastic differential equations (BSDEs), we (recursively) apply a deep learning-based BSDE solver to compute the entire optimal hedging strategies paths. This allows us to overcome the curse of dimensionality, extending the scope of applicability of quadratic hedging in high dimension. We test our approach with a classic Heston model and with a multiasset and multifactor generalization thereof, showing that this leads to high levels of accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2212_12725
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Deep Quadratic Hedging
Gnoatto, Alessandro
Lavagnini, Silvia
Picarelli, Athena
Computational Finance
Numerical Analysis
Probability
Mathematical Finance
93E20, 65M75, 68T07, 60H10
We propose a novel computational procedure for quadratic hedging in high-dimensional incomplete markets, covering mean-variance hedging and local risk minimization. Starting from the observation that both quadratic approaches can be treated from the point of view of backward stochastic differential equations (BSDEs), we (recursively) apply a deep learning-based BSDE solver to compute the entire optimal hedging strategies paths. This allows us to overcome the curse of dimensionality, extending the scope of applicability of quadratic hedging in high dimension. We test our approach with a classic Heston model and with a multiasset and multifactor generalization thereof, showing that this leads to high levels of accuracy.
title Deep Quadratic Hedging
topic Computational Finance
Numerical Analysis
Probability
Mathematical Finance
93E20, 65M75, 68T07, 60H10
url https://arxiv.org/abs/2212.12725