CoChat

Deep hedging

Buehler, H., Gonon, L., Teichmann, J., Wood, B. · 2019 · Quantitative Finance

The DOI matches its Crossref record; 27 of the 29 references it cites were found in a registry or an index, and 2 are not checked yet.

Abstract

We present a framework for hedging a portfolio of derivatives in the presence of market frictions such as transaction costs, liquidity constraints or risk limits using modern deep reinforcement machine learning methods. We discuss how standard reinforcement learning methods can be applied to non-linear reward structures, i.e. in our case convex risk measures. As a general contribution to the use of deep learning for stochastic processes, we also show in Section 4 that the set of constrained trading strategies used by our algorithm is large enough to ε-approximate any optimal solution. Our algorithm can be implemented efficiently even in high-dimensional situations using modern machine learning tools. Its structure does not depend on specific market dynamics, and generalizes across hedging instruments including the use of liquid derivatives. Its computational performance is largely invariant in the size of the portfolio as it depends mainly on the number of hedging instruments available. We illustrate our approach by an experiment on the S&P500 index and by showing the effect on hedging under transaction costs in a synthetic market driven by the Heston model, where we outperform the standard ‘complete-market’ solution.

Overview

Integrity signals

Registry

Crossref · 10.1080/14697688.2019.1571683

Cites

27 of 29 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 29 references

Research works printed but not linked: 13

  1. Andersen L.B.G. Jäckel P. and Kahl C. Simulation of square-root processes. In Encyclopedia of Quantitative Finance 2010 (John Wiley and Sons). · doi:10.1002/9780470061602.eqf13009
  2. Bölcskei H. Grohs P. Kutyniok G. and Petersen P. Optimal approximation with sparsely connected deep neural networks. Preprint arXiv:1705.01714 2017. · arXiv
  3. Du X. Zhai J. and Lv K. Algorithm trading using q-learning and recurrent reinforcement learning. arxiv 2009. Available online at: https://arxiv.org/pdf/1707.07338.pdf. · arXiv
  4. Dupire, B., Pricing with a smile. Risk, 1994, 7, 18–20.
  5. Gatheral J. and Schied A. Dynamical models of market impact and algorithms for order execution. In Handbook on Systemic Risk pp. 579–599 2013. · doi:10.1017/cbo9781139151184.030
  6. Goodfellow I. Bengio Y. and Courville A. Deep Learning 2016 (MIT Press). Available online at: http://www.deeplearningbook.org.
  7. Halperin I. QLBS: Q-learner in the Black–Scholes (-Merton) Worlds. arxiv 2017. Available online at: https://arxiv.org/abs/1712.04609. · arXiv · doi:10.2139/ssrn.3087076
  8. Hodges, S. and Neuberger, A., Optimal replication of contingent claims under transaction costs. Rev. Futures Markets, 1989, 8, 222–239.
  9. Ioffe S. and Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning pp. 448–456 2015.
  10. Kabanov, Y. and Safarian, M., Markets with Transaction Costs: Mathematical Theory, 2009 (Springer: Berlin, Germany).
  11. Kingma D.P. and Ba J. Adam: A method for stochastic optimization. Proceedings of the International Conference on Learning Representations (ICLR) 2015.
  12. Lu D. Agent inspired trading using recurrent reinforcement learning and LSTM neural networks. arxiv 2017. Available online at: https://arxiv.org/pdf/1707.07338.pdf. · arXiv
  13. Rogers L.C.G. Why is the effect of proportional transaction costs O(δ2/3). In Mathematics of Finance edited by G. Yin and Q. Zhang pp. 303–308 2004 (American Mathematical Society: Providence RI). · doi:10.1090/conm/351/06411

Cited by

See all 433

Metadata

Authors
Buehler, H., Gonon, L., Teichmann, J., & Wood, B.
Affiliations
  • J.P. Morgan (GB)
  • ETH Zurich (CH)
Corresponding author
Gonon, L.
Venue
Quantitative Finance
Published
2019-02-21
Volume
19
Issue
8
Pages
1271-1291
ISSN
  • 1469-7688 (ISSN-L)
  • 1469-7696
OpenAlex
W4247451115
Cited by
333
References
27
Citations by year
2026: 52 · 2025: 61 · 2024: 51 · 2023: 60 · 2022: 44 · 2021: 36 · 2020: 23 · 2019: 5
FWCI
32.70
Type
journal article
Language
en
Open access
closed
Locations
  • Quantitative Finance (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • Alexandria (UniSG) (University of St.Gallen) (submittedVersion)
Topics
  • Social Sciences › Economics, Econometrics and Finance › Finance › Stochastic processes and financial applications
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Risk and Portfolio Optimization
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
Keywords
deep hedging, derivative hedging, transaction costs, liquidity constraints, risk limits, deep reinforcement learning, convex risk measures, Heston model, incomplete markets

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Deep hedging. https://app.cochat.ai/papers/10.1080/14697688.2019.1571683
The paper
Buehler, H., Gonon, L., Teichmann, J., & Wood, B. (2019). Deep hedging. Quantitative Finance. https://doi.org/10.1080/14697688.2019.1571683

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.