Deep Hedging under Rough Volatility

Deep Hedging under Rough Volatility

We investigate the performance of the Deep Hedging framework under training paths beyond the (finite dimensional) Markovian setup. In particular, we analyse the hedging performance of the original architecture under rough volatility models in view of existing theoretical results for those. Furthermo...

Full description

Bibliographic Details
Main Authors: Blanka Horvath, Josef Teichmann, Žan Žurič
Format: Article
Language:English
Published: MDPI AG 2021-07-01
Series:Risks
Subjects:
deep learning
rough volatility
hedging
Online Access:https://www.mdpi.com/2227-9091/9/7/138
id doaj-32bfd9c35c7641bda695ecc3fac2aa4e
record_format Article
spelling doaj-32bfd9c35c7641bda695ecc3fac2aa4e2021-07-23T14:04:59ZengMDPI AGRisks2227-90912021-07-01913813810.3390/risks9070138Deep Hedging under Rough VolatilityBlanka Horvath0Josef Teichmann1Žan Žurič2Technische Universität München, King’s College London and The Alan Turing Institute, London WC2R 2LS, UKETH Zürich, 8092 Zürich, SwitzerlandFaculty of Natural Science, Imperial College London, London SW7 2AZ, UKWe investigate the performance of the Deep Hedging framework under training paths beyond the (finite dimensional) Markovian setup. In particular, we analyse the hedging performance of the original architecture under rough volatility models in view of existing theoretical results for those. Furthermore, we suggest parsimonious but suitable network architectures capable of capturing the non-Markoviantity of time-series. We also analyse the hedging behaviour in these models in terms of Profit and Loss (P&L) distributions and draw comparisons to jump diffusion models if the rebalancing frequency is realistically small.https://www.mdpi.com/2227-9091/9/7/138deep learningrough volatilityhedging
collection DOAJ
language English
format Article
sources DOAJ
author Blanka Horvath
Josef Teichmann
Žan Žurič
spellingShingle Blanka Horvath
Josef Teichmann
Žan Žurič
Deep Hedging under Rough Volatility
Risks
deep learning
rough volatility
hedging
author_facet Blanka Horvath
Josef Teichmann
Žan Žurič
author_sort Blanka Horvath
title Deep Hedging under Rough Volatility
title_short Deep Hedging under Rough Volatility
title_full Deep Hedging under Rough Volatility
title_fullStr Deep Hedging under Rough Volatility
title_full_unstemmed Deep Hedging under Rough Volatility
title_sort deep hedging under rough volatility
publisher MDPI AG
series Risks
issn 2227-9091
publishDate 2021-07-01
description We investigate the performance of the Deep Hedging framework under training paths beyond the (finite dimensional) Markovian setup. In particular, we analyse the hedging performance of the original architecture under rough volatility models in view of existing theoretical results for those. Furthermore, we suggest parsimonious but suitable network architectures capable of capturing the non-Markoviantity of time-series. We also analyse the hedging behaviour in these models in terms of Profit and Loss (P&L) distributions and draw comparisons to jump diffusion models if the rebalancing frequency is realistically small.
topic deep learning
rough volatility
hedging
url https://www.mdpi.com/2227-9091/9/7/138
work_keys_str_mv AT blankahorvath deephedgingunderroughvolatility
AT josefteichmann deephedgingunderroughvolatility
AT zanzuric deephedgingunderroughvolatility
_version_ 1721285961071984640

Similar Items