The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Deep Hedging: Hedging Derivatives Under Generic Market Frictions Using Reinforcement Learning
Open accessAbstract
This article discusses a new application of reinforcement learning: to the problem of hedging a portfolio of “over-the-counter” derivatives under under market frictions such as trading costs and liquidity constraints. It is an extended version of our recent work https://www.ssrn.com/abstract=3120710, here using notation more common in the machine learning literature. The objective is to maximize a non-linear risk-adjusted return function by trading in liquid hedging instruments such as equities or listed options. The approach presented here is the first efficient and model-independent algorithm which can be used for such problems at scale. There are now some code examples on GitHub.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“DRL framework is powerful in solving dynamic decision making problems by learning through interaction with an unknown environment, and thus providing two major advantages - portfolio scalability and market model independence [5].”
From FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance (2020) · cites this paper as [5]
In the citing paper
“FinRL supports user-defined reward functions to reflect risk-aversion or market friction [6, 54] and provides commonly used ones [13] as follows:”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [6]
In the citing paper
“DRL algorithms are powerful in solving dynamic decision making problems by learning through interactions with an unknown environment, and offer two major advantages of portfolio scalability and market model independence [6].”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [6]
In the citing paper
“DRL algorithms are powerful in solving dynamic decision making problems by learning through interactions with an unknown environment, and offer two major advantages of portfolio scalability and market model independence [6].”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [6]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
The pricing of options and corporate liabilities
Black, F., & Scholes, M. (1973) · Journal of Political Economy · doi:10.1086/260062 · Cited by 29,074
Heston, S. L. (1993) · Review of Financial Studies · doi:10.1093/rfs/6.2.327 · Cited by 8,771
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
Backward Stochastic Differential Equations in Finance
Karoui, N. E., Shige Peng, A., & Quenez, M.-C. (1997) · Mathematical Finance · doi:10.1111/1467-9965.00022 · Cited by 2,340
A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks
Hutchinson, J. M., Lo, A. W., & Poggio, T. (1994) · The Journal of Finance · doi:10.1111/j.1540-6261.1994.tb00081.x · Cited by 765
Föllmer, H., & Schied, A. (2016) · De Gruyter eBooks · doi:10.1515/9783110463453 · Cited by 417
A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem
Jiang, Z., Xu, D., & Liang, J. (2017) · arXiv · doi:10.48550/arxiv.1706.10059 · Cited by 321 · cited 1×
“We want to highlight two such areas: firstly, classic portfolio optimization, 4 where, as in our case, non-linear objective functions are required, e.g., [16] and [11]; and secondly, algorithmic trading, where several authors have shown promising results, e.g. [4] and [15].”
There is no Nontrivial Hedging Portfolio for Option Pricing with Transaction Costs
Soner, H. M., Shreve, S. E., & Cvitanić, J. (1995) · The Annals of Applied Probability · doi:10.1214/aoap/1177004767 · Cited by 287
THE COST OF ILLIQUIDITY AND ITS EFFECTS ON HEDGING
Rogers, L. C. G., & Singh, S. (2010) · Mathematical Finance · doi:10.1111/j.1467-9965.2010.00413.x · Cited by 122
Hedging with temporary price impact
Bank, P., Soner, H. M., & Voß, M. (2016) · Mathematics and Financial Economics · doi:10.1007/s11579-016-0178-4 · Cited by 93
Optimization of trading systems and portfolios
Moody, J. E., & Wu, L. (2002) · IEEE Conference on Computational Intelligence for Financial Engineering & Economics · doi:10.1109/cifer.1997.618952 · Cited by 69
Buehler, H. (2010) · Wiley eBooks · doi:10.1002/9780470061602.eqf08018 · Cited by 3
Self-citation
Research works printed but not linked: 6
- Hans Buehler, 2018, Deep hedging. arxiv
- Xin Du, 2009, Algorithm trading using Q-learning and recurrent reinforcement learning. arxiv
- Igor Halperin, 2017, QLBS: Q-learner in the Black-Scholes (-Merton) worlds. arxiv
- Francis Longstaff, 2001, Valuing american options by simulation: A simple least-squares approach. The Review of Financial Studies, 14, 113
- David Lu, 2017, Agent inspired trading using recurrent reinforcement learning and LSTM neural networks. arxiv
- Richard Sutton, 1998, Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning, Bd. Du Pont d'Arve, 42
Cited by
Sorted by citations
Quant GANs: deep generation of financial time series
Wiese, M., Knobloch, R., Korn, R., & Kretschmer, P. (2020) · Quantitative Finance · doi:10.1080/14697688.2020.1730426 · Cited by 355
Neural Networks for Option Pricing and Hedging: A Literature Review
Ruf, J., & Wang, W. (2019) · The Journal of Computational Finance · doi:10.21314/jcf.2020.390 · Cited by 189
Independent Researcher, U., & Ahmadi, S. (2024) · International Journal of Current Science Research and Review · doi:10.47191/ijcsrr/v7-i1-07 · Cited by 112
Ten Applications of Financial Machine LearningPreprint
de Prado, M. L. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3365271 · Cited by 92
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance
Liu, X.-Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3737257 · Cited by 90
Metadata
- Authors
- Buehler, H., Gonon, L., Teichmann, J., Wood, B., Mohan, B., & Kochems, J.
- Affiliations
- Ludwig-Maximilians-Universität München (DE)
- ETH Zurich (CH)
- JPMorgan Chase & Co (United States) (US)
- Corresponding author
- Buehler, Hans
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2019
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W2941037157
- Cited by
- 48
- References
- 14
- Citations by year
- 2026: 1 · 2025: 6 · 2024: 6 · 2023: 13 · 2022: 2 · 2021: 13 · 2020: 4 · 2019: 3
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Swiss Finance Institute Research Paper Series (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 › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Keywords
- deep hedging, derivative hedging, over-the-counter derivatives, market frictions, trade costs, liquidity constraints, reinforcement learning, risk-adjusted returns, options
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
