IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2402.12049.html
   My bibliography  Save this paper

Reinforcement Learning for Optimal Execution when Liquidity is Time-Varying

Author

Listed:
  • Andrea Macr`i
  • Fabrizio Lillo

Abstract

Optimal execution is an important problem faced by any trader. Most solutions are based on the assumption of constant market impact, while liquidity is known to be dynamic. Moreover, models with time-varying liquidity typically assume that it is observable, despite the fact that, in reality, it is latent and hard to measure in real time. In this paper we show that the use of Double Deep Q-learning, a form of Reinforcement Learning based on neural networks, is able to learn optimal trading policies when liquidity is time-varying. Specifically, we consider an Almgren-Chriss framework with temporary and permanent impact parameters following several deterministic and stochastic dynamics. Using extensive numerical experiments, we show that the trained algorithm learns the optimal policy when the analytical solution is available, and overcomes benchmarks and approximated solutions when the solution is not available.

Suggested Citation

  • Andrea Macr`i & Fabrizio Lillo, 2024. "Reinforcement Learning for Optimal Execution when Liquidity is Time-Varying," Papers 2402.12049, arXiv.org, revised Feb 2024.
    • Handle: RePEc:arx:papers:2402.12049
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2402.12049
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jean-Philippe Bouchaud & Yuval Gefen & Marc Potters & Matthieu Wyart, 2003. "Fluctuations and response in financial markets: the subtle nature of `random' price changes," Papers cond-mat/0307332, arXiv.org, revised Aug 2003.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jean-Philippe Bouchaud & Julien Kockelkoren & Marc Potters, 2006. "Random walks, liquidity molasses and critical response in financial markets," Quantitative Finance, Taylor & Francis Journals, vol. 6(2), pages 115-123.
    2. Nicolas Huth & Frédéric Abergel, 2012. "The times change: multivariate subordination, empirical facts," Post-Print hal-00620841, HAL.
    3. Karol Wawrzyniak & Wojciech Wi'slicki, 2013. "Grand canonical minority game as a sign predictor," Papers 1309.3399, arXiv.org.
    4. Aur'elien Alfonsi & Antje Fruth & Alexander Schied, 2007. "Optimal execution strategies in limit order books with general shape functions," Papers 0708.1756, arXiv.org, revised Feb 2010.
    5. R'emy Chicheportiche & Jean-Philippe Bouchaud, 2012. "The fine-structure of volatility feedback I: multi-scale self-reflexivity," Papers 1206.2153, arXiv.org, revised Sep 2013.
    6. Svitlana Vyetrenko & David Byrd & Nick Petosa & Mahmoud Mahfouz & Danial Dervovic & Manuela Veloso & Tucker Hybinette Balch, 2019. "Get Real: Realism Metrics for Robust Limit Order Book Market Simulations," Papers 1912.04941, arXiv.org.
    7. Aurélien Alfonsi & Alexander Schied, 2010. "Optimal trade execution and absence of price manipulations in limit order book models," Post-Print hal-00397652, HAL.
    8. Olivier Guedj & Jean-Philippe Bouchaud, 2004. "Experts' earning forecasts: bias, herding and gossamer information," Science & Finance (CFM) working paper archive 500062, Science & Finance, Capital Fund Management.
    9. Adam Blazejewski & Richard Coggins, 2004. "A piecewise linear model for trade sign inference," Finance 0412012, University Library of Munich, Germany.
    10. B. Tóth & Z. Eisler & F. Lillo & J. Kockelkoren & J.-P. Bouchaud & J.D. Farmer, 2012. "How does the market react to your order flow?," Quantitative Finance, Taylor & Francis Journals, vol. 12(7), pages 1015-1024, May.
    11. Wei-Xing Zhou, 2012. "Universal price impact functions of individual trades in an order-driven market," Quantitative Finance, Taylor & Francis Journals, vol. 12(8), pages 1253-1263, June.
    12. Ted Theodosopoulos, 2004. "Uncertainty relations in models of market microstructure," Papers math/0409076, arXiv.org, revised Feb 2005.
    13. Su, Zhifang & Bao, Haohua & Li, Qifang & Xu, Boyu & Cui, Xin, 2022. "The prediction of price gap anomaly in Chinese stock market: Evidence from the dependent functional logit model," Finance Research Letters, Elsevier, vol. 47(PB).
    14. Behzad Alimoradian & Karim Barigou & Anne Eyraud-Loisel, 2022. "Derivatives under market impact: Disentangling cost and information," Working Papers hal-03668432, HAL.
    15. Emilio Said, 2022. "Market Impact: Empirical Evidence, Theory and Practice," Working Papers hal-03668669, HAL.
    16. Chiarella, Carl & Iori, Giulia, 2009. "The impact of heterogeneous trading rules on the limit order book and order flows," Journal of Economic Dynamics and Control, Elsevier, vol. 33(3), pages 525-537.
    17. Schied, Alexander & Schöneborn, Torsten, 2007. "Optimal Portfolio Liquidation for CARA Investors," MPRA Paper 5075, University Library of Munich, Germany.
    18. Demosthenes Tambakis, 2009. "Feedback trading and intermittent market turbulence," Quantitative Finance, Taylor & Francis Journals, vol. 9(4), pages 477-489.
    19. Gianluca Mattarocci, 2009. "Market Characteristics and Chaos Dynamics in Stock Markets: an International Comparison," Palgrave Macmillan Studies in Banking and Financial Institutions, in: Alessandro Carretta & Franco Fiordelisi & Gianluca Mattarocci (ed.), New Drivers of Performance in a Changing Financial World, chapter 6, pages 89-106, Palgrave Macmillan.
    20. Steffen Bohn, 2011. "The slippage paradox," Working Papers hal-00574268, HAL.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2402.12049. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.