IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2101.07107.html
   My bibliography  Save this paper

Deep Reinforcement Learning for Active High Frequency Trading

Author

Listed:
  • Antonio Briola
  • Jeremy Turiel
  • Riccardo Marcaccioli
  • Alvaro Cauderan
  • Tomaso Aste

Abstract

We introduce the first end-to-end Deep Reinforcement Learning (DRL) based framework for active high frequency trading in the stock market. We train DRL agents to trade one unit of Intel Corporation stock by employing the Proximal Policy Optimization algorithm. The training is performed on three contiguous months of high frequency Limit Order Book data, of which the last month constitutes the validation data. In order to maximise the signal to noise ratio in the training data, we compose the latter by only selecting training samples with largest price changes. The test is then carried out on the following month of data. Hyperparameters are tuned using the Sequential Model Based Optimization technique. We consider three different state characterizations, which differ in their LOB-based meta-features. Analysing the agents' performances on test data, we argue that the agents are able to create a dynamic representation of the underlying environment. They identify occasional regularities present in the data and exploit them to create long-term profitable trading strategies. Indeed, agents learn trading strategies able to produce stable positive returns in spite of the highly stochastic and non-stationary environment.

Suggested Citation

  • Antonio Briola & Jeremy Turiel & Riccardo Marcaccioli & Alvaro Cauderan & Tomaso Aste, 2021. "Deep Reinforcement Learning for Active High Frequency Trading," Papers 2101.07107, arXiv.org, revised Aug 2023.
  • Handle: RePEc:arx:papers:2101.07107
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2101.07107
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Michael Karpe & Jin Fang & Zhongyao Ma & Chen Wang, 2020. "Multi-Agent Reinforcement Learning in a Realistic Limit Order Book Market Simulation," Papers 2006.05574, arXiv.org, revised Sep 2020.
    2. Bibinger, Markus & Neely, Christopher & Winkelmann, Lars, 2019. "Estimation of the discontinuous leverage effect: Evidence from the NASDAQ order book," Journal of Econometrics, Elsevier, vol. 209(2), pages 158-184.
    3. Zihao Zhang & Stefan Zohren & Stephen Roberts, 2018. "BDLOB: Bayesian Deep Convolutional Neural Networks for Limit Order Books," Papers 1811.10041, arXiv.org.
    4. Antonio Briola & Jeremy Turiel & Tomaso Aste, 2020. "Deep Learning modeling of Limit Order Book: a comparative perspective," Papers 2007.07319, arXiv.org, revised Oct 2020.
    5. Tucker Hybinette Balch & Mahmoud Mahfouz & Joshua Lockhart & Maria Hybinette & David Byrd, 2019. "How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?," Papers 1906.12010, arXiv.org.
    6. Comerton-Forde, Carole & Putniņš, Tālis J., 2015. "Dark trading and price discovery," Journal of Financial Economics, Elsevier, vol. 118(1), pages 70-92.
    7. Justin Sirignano & Rama Cont, 2019. "Universal features of price formation in financial markets: perspectives from deep learning," Quantitative Finance, Taylor & Francis Journals, vol. 19(9), pages 1449-1459, September.
    8. Zihao Zhang & Stefan Zohren & Stephen Roberts, 2019. "Extending Deep Learning Models for Limit Order Books to Quantile Regression," Papers 1906.04404, arXiv.org.
    9. Thibaut Th'eate & Damien Ernst, 2020. "An Application of Deep Reinforcement Learning to Algorithmic Trading," Papers 2004.06627, arXiv.org, revised Oct 2020.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Wang, Yuanrong & Aste, Tomaso, 2023. "Dynamic portfolio optimization with inverse covariance clustering," LSE Research Online Documents on Economics 117701, London School of Economics and Political Science, LSE Library.
    2. Yuanrong Wang & Tomaso Aste, 2022. "Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series," Papers 2203.03991, arXiv.org.
    3. David Vidal-Tom'as & Antonio Briola & Tomaso Aste, 2023. "FTX's downfall and Binance's consolidation: The fragility of centralised digital finance," Papers 2302.11371, arXiv.org, revised Dec 2023.
    4. Jinan Zou & Qingying Zhao & Yang Jiao & Haiyao Cao & Yanxi Liu & Qingsen Yan & Ehsan Abbasnejad & Lingqiao Liu & Javen Qinfeng Shi, 2022. "Stock Market Prediction via Deep Learning Techniques: A Survey," Papers 2212.12717, arXiv.org, revised Feb 2023.
    5. Zihao Zhang & Bryan Lim & Stefan Zohren, 2021. "Deep Learning for Market by Order Data," Papers 2102.08811, arXiv.org, revised Jul 2021.
    6. Adrian Millea, 2021. "Deep Reinforcement Learning for Trading—A Critical Survey," Data, MDPI, vol. 6(11), pages 1-25, November.
    7. Peer Nagy & Jan-Peter Calliess & Stefan Zohren, 2023. "Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets," Papers 2301.08688, arXiv.org, revised Sep 2023.
    8. Hong Guo & Jianwu Lin & Fanlin Huang, 2023. "Market Making with Deep Reinforcement Learning from Limit Order Books," Papers 2305.15821, arXiv.org.
    9. Zihao Zhang & Stefan Zohren, 2021. "Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units," Papers 2105.10430, arXiv.org, revised Aug 2021.
    10. Antonio Briola & Tomaso Aste, 2022. "Dependency structures in cryptocurrency market from high to low frequency," Papers 2206.03386, arXiv.org, revised Dec 2022.

    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. Zihao Zhang & Stefan Zohren, 2021. "Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units," Papers 2105.10430, arXiv.org, revised Aug 2021.
    2. Zihao Zhang & Bryan Lim & Stefan Zohren, 2021. "Deep Learning for Market by Order Data," Papers 2102.08811, arXiv.org, revised Jul 2021.
    3. Zihao Zhang & Stefan Zohren & Stephen Roberts, 2019. "Deep Reinforcement Learning for Trading," Papers 1911.10107, arXiv.org.
    4. Antonio Briola & Jeremy Turiel & Tomaso Aste, 2020. "Deep Learning modeling of Limit Order Book: a comparative perspective," Papers 2007.07319, arXiv.org, revised Oct 2020.
    5. Eghbal Rahimikia & Stefan Zohren & Ser-Huang Poon, 2021. "Realised Volatility Forecasting: Machine Learning via Financial Word Embedding," Papers 2108.00480, arXiv.org, revised Nov 2024.
    6. Hong Guo & Jianwu Lin & Fanlin Huang, 2023. "Market Making with Deep Reinforcement Learning from Limit Order Books," Papers 2305.15821, arXiv.org.
    7. Hamza Bodor & Laurent Carlier, 2024. "A Novel Approach to Queue-Reactive Models: The Importance of Order Sizes," Papers 2405.18594, arXiv.org.
    8. Yufei Wu & Mahmoud Mahfouz & Daniele Magazzeni & Manuela Veloso, 2021. "Towards Robust Representation of Limit Orders Books for Deep Learning Models," Papers 2110.05479, arXiv.org, revised Dec 2022.
    9. Buti, Sabrina & Rindi, Barbara & Werner, Ingrid M., 2010. "Diving into Dark Pools," Working Paper Series 2010-10, Ohio State University, Charles A. Dice Center for Research in Financial Economics.
    10. O'Hara, Maureen & Alex Zhou, Xing, 2021. "The electronic evolution of corporate bond dealers," Journal of Financial Economics, Elsevier, vol. 140(2), pages 368-390.
    11. Xu, Liao & Xu, Lu & Zhao, Jing & Zhao, Yang, 2020. "Information-based trading and information propagation: Evidence from the exchange traded fund market," International Review of Financial Analysis, Elsevier, vol. 70(C).
    12. Petrescu, Monica & Wedow, Michael, 2017. "Dark pools in European equity markets: emergence, competition and implications," Occasional Paper Series 193, European Central Bank.
    13. Eric Benhamou & David Saltiel & Sandrine Ungari & Abhishek Mukhopadhyay & Jamal Atif, 2020. "AAMDRL: Augmented Asset Management with Deep Reinforcement Learning," Papers 2010.08497, arXiv.org.
    14. Michael Karpe, 2020. "An overall view of key problems in algorithmic trading and recent progress," Papers 2006.05515, arXiv.org.
    15. Anindya Goswami & Nimit Rana, 2024. "A market resilient data-driven approach to option pricing," Papers 2409.08205, arXiv.org.
    16. Comerton-Forde, Carole & Grégoire, Vincent & Zhong, Zhuo, 2019. "Inverted fee structures, tick size, and market quality," Journal of Financial Economics, Elsevier, vol. 134(1), pages 141-164.
    17. Xu, Liao & Pu, Wenyan, 2022. "ETFs, arbitrage activity, and stock market efficiency: Evidence from Chinese CSI 300 ETFs," Economic Analysis and Policy, Elsevier, vol. 73(C), pages 1-9.
    18. Garvey, Ryan & Huang, Tao & Wu, Fei, 2016. "Why do traders choose dark markets?," Journal of Banking & Finance, Elsevier, vol. 68(C), pages 12-28.
    19. Antonio Briola & Silvia Bartolucci & Tomaso Aste, 2024. "Deep Limit Order Book Forecasting," Papers 2403.09267, arXiv.org, revised Jun 2024.
    20. Tourani-Rad, Alireza & Gilbert, Aaron & Chen, Jun, 2016. "Are foreign IPOs really foreign? Price efficiency and information asymmetry of Chinese foreign IPOs," Journal of Banking & Finance, Elsevier, vol. 63(C), pages 95-106.

    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:2101.07107. 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.