Skip to main content
SpringerLink
Log in

DRICORN-K: A Dynamic RIsk CORrelation-driven Non-parametric Algorithm for Online Portfolio Selection

  • Conference paper
  • First Online:
Book cover Artificial Intelligence Research (SACAIR 2021)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1342))

Included in the following conference series:

Abstract

Online Portfolio Selection is regarded as a fundamental problem in Computational Finance. Pattern-Matching methods, and the CORN-K algorithm in particular, have provided promising results. Despite making notable progress, there exists a gap in the current state of the art – systematic risk is not considered. The lack of attention to systematic risk could lead to poor investment returns, especially in volatile markets. In response to this, we extend the CORN-K algorithm to present DRICORN-K – a Dynamic RIsk CORrelation-driven Non-parametric algorithm. DRICORN-K continuously adjusts a portfolio’s market sensitivity based on the current market conditions. We measure market sensitivity using the \(\beta \) measure. DRICORN-K aims to take advantage of upward market trends and protect portfolios against downward market trends. To this end, we implement a number of market classification methods. We find that an exponentially weighted moving linear regression method provides the best classification of current market conditions. We further conducted an empirical analysis on five real world stock indices: the JSE Top 40, Bovespa, DAX, DJIA and Nikkei 225 against twelve state of the art algorithms. The results show that DRICORN-K can deliver improved performance over the current state of the art, as measured by cumulative return, Sharpe ratio and maximum drawdown. The experimental results lead us to conclude that the addition of dynamic systematic risk adjustments to CORN-K can result in improved portfolio performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://finance.yahoo.com.

References

  1. Paskaramoorthy, A.B., Gebbie, T.J., van Zyl, T.L.: A framework for online investment decisions. Invest. Anal. J. 49, 215–231 (2020)

    Article  Google Scholar 

  2. Li, B., Hoi, S.: Online portfolio selection: a survey. ACM Comput. Surv. 46, 12 (2012)

    Google Scholar 

  3. Agarwal, A., Hazan, E., Kale, S., Schapire, R.E.: Algorithms for portfolio management based on the newton method. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 9–16 (2006)

    Google Scholar 

  4. Borodin, A., El-Yaniv, R., Gogan, V.: Can we learn to beat the best stock. J. Artif. Intell. Res. 21, 579–594 (2004)

    Article  MathSciNet  Google Scholar 

  5. Li, B., Zhao, P., Hoi, S.C.H., et al.: PAMR: passive aggressive mean reversion strategy for portfolio selection. Mach. Learn. 87, 221–258 (2012). https://doi.org/10.1007/s10994-012-5281-z

    Article  MathSciNet  MATH  Google Scholar 

  6. Györfi, L., Lugosi, G., Udina, F.: Nonparametric kernel-based sequential investment strategies. Math. Finan. Int. J. Math. Stat. Finan. Econ. 16(2), 337–357 (2006)

    MathSciNet  MATH  Google Scholar 

  7. Györfi, L., Udina, F., Walk, H., et al.: Nonparametric nearest neighbor based empirical portfolio selection strategies. Stat. Decis. 26(2), 145–157 (2008)

    MathSciNet  MATH  Google Scholar 

  8. Li, B., Hoi, S.C.H., Gopalkrishnan, V.: CORN: correlation-driven nonparametric learning approach for portfolio selection. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 1–29 (2011)

    Article  Google Scholar 

  9. Wang, Y., Wang, D., Zheng, T.F.: Racorn-k: risk-aversion pattern matching-based portfolio selection. In: 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1816–1820. IEEE (2018)

    Google Scholar 

  10. Das, P., Banerjee, A.: Meta optimization and its application to portfolio selection. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1163–1171 (2011)

    Google Scholar 

  11. Gooding, A.E., O’Malley, T.P.: Market phase and the stationarity of beta. J. Financ. Quant. Anal. 12(5), 833–857 (1977)

    Article  Google Scholar 

  12. Snow, D.: Machine learning in asset management–part 1: portfolio construction–trading strategies. J. Financ. Data Sci. 2(1), 10–23 (2020)

    Article  Google Scholar 

  13. Snow, D.: Machine learning in asset management–part 2: portfolio construction–weight optimization. J. Financ. Data Sci. 2(1), 10–23 (2020)

    Article  Google Scholar 

  14. James, F.E.: Monthly moving averages-an effective investment tool? J. Financ. Quant. Anal. 3(3), 315–326 (1968)

    Article  Google Scholar 

  15. Li, B., Sahoo, D., Hoi, S.C.H.: OLPS: a toolbox for on-line portfolio selection. J. Mach. Learn. Res. 17(1), 1242–1246 (2016)

    MathSciNet  Google Scholar 

  16. Sharpe, W.F.: Mutual fund performance. J. Bus. 39(1), 119–138 (1966)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa

    Shivaar Sooklal & Andrew Paskaramoorthy

  2. Institute for Intelligent Systems, University of Johannesburg, Johannesburg, South Africa

    Terence L. van Zyl

Authors
  1. Shivaar Sooklal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Terence L. van Zyl
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrew Paskaramoorthy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shivaar Sooklal .

Editor information

Editors and Affiliations

  1. University of Pretoria, Pretoria, South Africa

    Aurona Gerber

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Sooklal, S., van Zyl, T.L., Paskaramoorthy, A. (2020). DRICORN-K: A Dynamic RIsk CORrelation-driven Non-parametric Algorithm for Online Portfolio Selection. In: Gerber, A. (eds) Artificial Intelligence Research. SACAIR 2021. Communications in Computer and Information Science, vol 1342. Springer, Cham. https://doi.org/10.1007/978-3-030-66151-9_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-66151-9_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-66150-2

  • Online ISBN: 978-3-030-66151-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation