IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2005.13665.html
   My bibliography  Save this paper

Deep Learning for Portfolio Optimization

Author

Listed:
  • Zihao Zhang
  • Stefan Zohren
  • Stephen Roberts

Abstract

We adopt deep learning models to directly optimise the portfolio Sharpe ratio. The framework we present circumvents the requirements for forecasting expected returns and allows us to directly optimise portfolio weights by updating model parameters. Instead of selecting individual assets, we trade Exchange-Traded Funds (ETFs) of market indices to form a portfolio. Indices of different asset classes show robust correlations and trading them substantially reduces the spectrum of available assets to choose from. We compare our method with a wide range of algorithms with results showing that our model obtains the best performance over the testing period, from 2011 to the end of April 2020, including the financial instabilities of the first quarter of 2020. A sensitivity analysis is included to understand the relevance of input features and we further study the performance of our approach under different cost rates and different risk levels via volatility scaling.

Suggested Citation

  • Zihao Zhang & Stefan Zohren & Stephen Roberts, 2020. "Deep Learning for Portfolio Optimization," Papers 2005.13665, arXiv.org, revised Jan 2021.
    • Handle: RePEc:arx:papers:2005.13665
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2005.13665
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Daniel Fernholz & Ioannis Karatzas, 2010. "On optimal arbitrage," Papers 1010.4987, arXiv.org.
    2. Yann LeCun & Yoshua Bengio & Geoffrey Hinton, 2015. "Deep learning," Nature, Nature, vol. 521(7553), pages 436-444, May.
    3. Alexei Chekhlov & Stanislav Uryasev & Michael Zabarankin, 2005. "Drawdown Measure In Portfolio Optimization," International Journal of Theoretical and Applied Finance (IJTAF), World Scientific Publishing Co. Pte. Ltd., vol. 8(01), pages 13-58.
    4. Alexander J. McNeil & Rüdiger Frey & Paul Embrechts, 2015. "Quantitative Risk Management: Concepts, Techniques and Tools Revised edition," Economics Books, Princeton University Press, edition 2, number 10496.
    5. Robert Fernholz & Ioannis Karatzas & Constantinos Kardaras, 2005. "Diversity and relative arbitrage in equity markets," Finance and Stochastics, Springer, vol. 9(1), pages 1-27, January.
    6. Ludan Theron & Gary van Vuuren, 2018. "The maximum diversification investment strategy: A portfolio performance comparison," Cogent Economics & Finance, Taylor & Francis Journals, vol. 6(1), pages 1427533-142, January.
    7. Zihao Zhang & Stefan Zohren & Stephen Roberts, 2019. "Extending Deep Learning Models for Limit Order Books to Quantile Regression," Papers 1906.04404, arXiv.org.
    8. Ting-Kam Wong, 2015. "Optimization of relative arbitrage," Annals of Finance, Springer, vol. 11(3), pages 345-382, November.
    9. Chien Yi Huang, 2018. "Financial Trading as a Game: A Deep Reinforcement Learning Approach," Papers 1807.02787, arXiv.org.
    10. Francesco Bertoluzzo & Marco Corazza, 2012. "Reinforcement Learning for automatic financial trading: Introduction and some applications," Working Papers 2012:33, Department of Economics, University of Venice "Ca' Foscari", revised 2012.
    11. Bryan Lim & Stefan Zohren & Stephen Roberts, 2019. "Enhancing Time Series Momentum Strategies Using Deep Neural Networks," Papers 1904.04912, arXiv.org, revised Sep 2020.
    12. Moskowitz, Tobias J. & Ooi, Yao Hua & Pedersen, Lasse Heje, 2012. "Time series momentum," Journal of Financial Economics, Elsevier, vol. 104(2), pages 228-250.
    13. Robert Fernholz, 1999. "Portfolio Generating Functions," World Scientific Book Chapters, in: Marco Avellaneda (ed.), Quantitative Analysis In Financial Markets Collected Papers of the New York University Mathematical Finance Seminar, chapter 15, pages 344-367, World Scientific Publishing Co. Pte. Ltd..
    14. Yves-Laurent Kom Samo & Alexander Vervuurt, 2016. "Stochastic Portfolio Theory: A Machine Learning Perspective," Papers 1605.02654, arXiv.org.
    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. Mykola Babiak & Jozef Barunik, 2020. "Deep Learning, Predictability, and Optimal Portfolio Returns," CERGE-EI Working Papers wp677, The Center for Economic Research and Graduate Education - Economics Institute, Prague.
    2. Bruno Spilak & Wolfgang Karl Hardle, 2020. "Tail-risk protection: Machine Learning meets modern Econometrics," Papers 2010.03315, arXiv.org, revised Aug 2021.

    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 & Stephen Roberts, 2019. "Deep Reinforcement Learning for Trading," Papers 1911.10107, arXiv.org.
    2. Alexander Vervuurt & Ioannis Karatzas, 2015. "Diversity-weighted portfolios with negative parameter," Annals of Finance, Springer, vol. 11(3), pages 411-432, November.
    3. Alexander Vervuurt & Ioannis Karatzas, 2015. "Diversity-Weighted Portfolios with Negative Parameter," Papers 1504.01026, arXiv.org, revised Jul 2015.
    4. Alexander Schied & Leo Speiser & Iryna Voloshchenko, 2016. "Model-free portfolio theory and its functional master formula," Papers 1606.03325, arXiv.org, revised May 2018.
    5. Ting-Kam Leonard Wong, 2017. "On portfolios generated by optimal transport," Papers 1709.03169, arXiv.org, revised Sep 2017.
    6. Soumik Pal & Ting-Kam Leonard Wong, 2016. "Exponentially concave functions and a new information geometry," Papers 1605.05819, arXiv.org, revised May 2017.
    7. Alexander Vervuurt, 2015. "Topics in Stochastic Portfolio Theory," Papers 1504.02988, arXiv.org.
    8. Ting-Kam Leonard Wong, 2014. "Optimization of relative arbitrage," Papers 1407.8300, arXiv.org, revised Nov 2014.
    9. Christa Cuchiero, 2017. "Polynomial processes in stochastic portfolio theory," Papers 1705.03647, arXiv.org.
    10. Ali Al-Aradi & Sebastian Jaimungal, 2018. "Outperformance and Tracking: Dynamic Asset Allocation for Active and Passive Portfolio Management," Papers 1803.05819, arXiv.org, revised Jul 2018.
    11. Erhan Bayraktar & Donghan Kim & Abhishek Tilva, 2023. "Quantifying dimensional change in stochastic portfolio theory," Papers 2303.00858, arXiv.org, revised Apr 2023.
    12. Julien Hambuckers & Marie Kratz & Antoine Usseglio-Carleve, 2023. "Efficient Estimation In Extreme Value Regression Models Of Hedge Fund Tail Risks," Working Papers hal-04090916, HAL.
    13. Paolo Guasoni & Miklós Rásonyi, 2015. "Fragility of arbitrage and bubbles in local martingale diffusion models," Finance and Stochastics, Springer, vol. 19(2), pages 215-231, April.
    14. Winslow Strong & Jean-Pierre Fouque, 2011. "Diversity and arbitrage in a regulatory breakup model," Annals of Finance, Springer, vol. 7(3), pages 349-374, August.
    15. Ali Al-Aradi & Sebastian Jaimungal, 2018. "Outperformance and Tracking: Dynamic Asset Allocation for Active and Passive Portfolio Management," Applied Mathematical Finance, Taylor & Francis Journals, vol. 25(3), pages 268-294, May.
    16. Chao Zhang & Zihao Zhang & Mihai Cucuringu & Stefan Zohren, 2021. "A Universal End-to-End Approach to Portfolio Optimization via Deep Learning," Papers 2111.09170, arXiv.org.
    17. Martin Larsson & Johannes Ruf, 2021. "Relative arbitrage: Sharp time horizons and motion by curvature," Mathematical Finance, Wiley Blackwell, vol. 31(3), pages 885-906, July.
    18. Johannes Ruf, 2010. "Hedging under arbitrage," Papers 1003.4797, arXiv.org, revised May 2011.
    19. Ali Al-Aradi & Sebastian Jaimungal, 2019. "Active and Passive Portfolio Management with Latent Factors," Papers 1903.06928, arXiv.org.
    20. Aleksandar Mijatović & Mikhail Urusov, 2012. "Deterministic criteria for the absence of arbitrage in one-dimensional diffusion models," Finance and Stochastics, Springer, vol. 16(2), pages 225-247, April.

    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:2005.13665. 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.