Skip to main content
SpringerLink
Log in

Risk management strategies for finding universal portfolios

  • S.I.: APMOD 2014
  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

We consider Cover’s universal portfolio and the problem of risk management in a distribution-free setting when learning from experts. We aim to find optimal portfolios without modelling the financial market at the outset. Although it exists, the price distribution of the constituent assets is neither known nor given as part of the input. We consider the portfolio selection problem from the perspective of online algorithms that process input piece-by-piece in a serial fashion. Under the minimax regret criterion, we propose two risk-adjusted algorithms that track the expert with the lowest maximum drawdown. We obtain upper bounds on the worst-case performance of our algorithms that equal the bounds obtained by Cover (Math Finance 1(1):1–29, 1991). We also present computational evidence using NYSE data over a 22-year period, which shows superior performance of investment strategies that take risk management into account.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. \(\textit{CRP}\) holds an a priori fixed portfolio, i.e., maintains a constant fraction of the total wealth in each of the underlying m assets. Widely-used is the Uniform \(\textit{CRP}\) (\(\textit{UCRP}\)), where \(b_t=(\frac{1}{m},\dots ,\frac{1}{m})\). \(\textit{UCRP}\) is also known as \(\big (\frac{1}{m}\big )\)-portfolio and/or naive diversification.

  2. For a model allowing short sales see Vovk and Watkins (1998).

  3. Equivalent to the average logarithmic wealth (\(\frac{1}{T}\ln W_T(P)\)) (Borodin et al. 2000).

  4. Not to be mistaken with the game in which the players make wagers on the outcome of a pair of dice (Turner 2005).

  5. Download via http://www.cs.technion.ac.il/~rani/portfolios/NYSE.zip.

  6. \(R_f\) risk-free return fixed at 0 % in this work; \(\hat{\sigma }_i\) standard deviation of the (daily) returns of the i-th asset; \(\hat{\sigma }^2_{ij}\) sample covariance between two assets i and j.

  7. For further details on the performance of the considered algorithms see Dochow (2016).

References

  • Agarwal, A., Hazan, E., Kale, S., Schapire, R. (2006). Algorithms for portfolio management based on the newton method. In Proceedings of the 23rd international conference on machine learning (pp. 9–16).

  • Ahmad, I., Mohr, E., & Schmidt, G. (2014). Competitive ratio as coherent measure of risk. In S. Helber, M. Breitner, D. Rösch, C. Schön, J. M. Graf von der Schulenburg, P. Sibbertsen, M. Steinbach, S. Weber, & A. Wolter (Eds.), Operations research proceedings 2012 (pp. 63–69). Berlin: Springer.

  • Algoet, P. (1992). Universal schemes for prediction, gambling and portfolio selection. The Annals of Probability, 20(2), 901–941.

    Article  Google Scholar 

  • Ball, M. O., & Queyranne, M. (2009). Toward robust revenue management: Competitive analysis of online booking. Operations Research, 57(4), 950–963.

    Article  Google Scholar 

  • Best, M., & Grauer, R. (1991). Sensitivity analysis for mean-variance portfolio problems. Management Science, 37(8), 980–989.

    Article  Google Scholar 

  • Borodin, A., El-Yaniv, R., Gogan, V. (2000). On the competitive theory and practice of portfolio selection (extended abstract). In Proceedings of the fourth Latin American symposium on theoretical informatics (LATIN’00) (pp. 173–196).

  • Borodin, A., El-Yaniv, R., & Gogan, V. (2004). Can we learn to beat the best stock. Journal of Artificial Intelligence Research, 21, 579–594.

    Google Scholar 

  • Breiman, L. (1962). Optimal gambling systems for favorable games. In Fourth Berkeley symposium on mathematical statistics and probability (pp. 65–78).

  • Cai, X., Teo, K. L., Yang, X., & Zhou, X. (2000). Portfolio optimization under a minimax rule. Management Science, 46(7), 957–972.

    Article  Google Scholar 

  • Cesa-Bianchi, N., & Lugosi, G. (2006). Prediction, learning, and games. New York: Cambridge University Press.

    Book  Google Scholar 

  • Cover, T. (1991). Universal portfolios. Mathematical Finance, 1(1), 1–29.

    Article  Google Scholar 

  • Cover, T., & Ordentlich, E. (1996). Universal portfolios with side information. IEEE Transactions on Information Theory, 42(2), 348–368.

    Article  Google Scholar 

  • Cover, T. (1991). Elements of information theory. Hoboken: Wiley.

    Book  Google Scholar 

  • Deng, X. T., Li, Z. F., & Wang, S. Y. (2005). A minimax portfolio selection strategy with equilibrium. European Journal of Operational Research, 166(1), 278–292.

    Article  Google Scholar 

  • Dochow, R. (2016). Online algorithms for the portfolio selection problem. Wiesbaden: Springer Gabler.

    Book  Google Scholar 

  • Dochow, R., Mohr, E., & Schmidt, G. (2014). Risk-adjusted on-line portfolio selection. In D. Huisman, I. Louwerse, & A. P. M. Wagelmans (Eds.), Operations research proceedings 2013 (pp. 113–119). Berlin: Springer.

    Google Scholar 

  • Gaivoronski, A., & Stella, F. (2000). Stochastic nonstationary optimization for finding universal portfolios. Annals of Operations Research, 100, 165–188.

    Article  Google Scholar 

  • Gülpinar, N., & Rustem, B. (2007). Worst-case robust decisions for multi-period mean-variance portfolio optimization. European Journal of Operational Research, 183(3), 981–1000.

    Article  Google Scholar 

  • Helmbold, D., Schapire, R., Singer, Y., & Warmuth, M. (1998). On-line portfolio selection using multiplicative updates. Mathematical Finance, 8(4), 325–347.

    Article  Google Scholar 

  • Huang, X. (2008). Portfolio selection with a new definition of risk. European Journal of Operational Research, 186(1), 351–357.

    Article  Google Scholar 

  • Kelly, J. L, Jr. (1956). A new interpretation of information rate. IRE Transactions on Information Theory, 2(3), 185–189.

    Article  Google Scholar 

  • Li, B., Hoi, S. (2014). Online portfolio selection: A survey. ACM Computing Surveys, 46(3), Article No. 35.

  • Markowitz, H. (1952). Portfolio selection. Journal of Finance, 7(1), 77–91.

    Google Scholar 

  • O’Sullivan, P., & Edelman, D. (2015). Adaptive universal portfolios. The European Journal of Finance, 21(4), 337–351.

    Article  Google Scholar 

  • Perakis, G., & Roels, G. (2008). Regret in the newsvendor model with partial information. Operations Research, 56(1), 188–203.

    Article  Google Scholar 

  • Polak, G., Rogers, D., & Sweeney, D. (2010). Risk management strategies via minimax portfolio optimization. European Journal of Operational Research, 207(1), 409–419.

    Article  Google Scholar 

  • Rubinstein, M. (2002). Markowitz’s ‘portfolio selection’: A fifty-year retrospective. The Journal of Finance, 57(3), 1041–1045.

    Article  Google Scholar 

  • Sharpe, W. (1971). A linear programming approximation for the general portfolio analysis problem. Journal of Financial and Quantitative Analysis, 6(5), 1263–1275.

    Article  Google Scholar 

  • Steinbach, M. (2001). Markowitz revisited: Mean-variance models in financial portfolio analysis. SIAM Review, 43(1), 31–85.

    Article  Google Scholar 

  • Stone, B. (1973). A linear programming formulation of the general portfolio selection problem. The Journal of Financial and Quantitative Analysis, 8(4), 621–636.

    Article  Google Scholar 

  • Teo, K., & Yang, X. (2001). Portfolio selection problem with minimax type risk function. Annals of Operations Research, 101(1–4), 333–349.

    Article  Google Scholar 

  • Turner, N. (2005). Sucker’s progress: An informal history of gambling in America. Journal of Gambling Issues, 13, 1–8.

    Article  Google Scholar 

  • Vecer, J. (2007). Preventing portfolio losses by hedging maximum drawdown. Wilmott, 5(4), 1–8.

    Google Scholar 

  • Vovk, V., Watkins, C. (1998). Universal portfolio selection. In: Proceedings of the eleventh annual conference on computational learning theory (pp. 12–23).

  • Young, M. (1998). A minimax portfolio selection rule with linear programming solution. Management Science, 44(5), 673–683.

    Article  Google Scholar 

Download references

Acknowledgments

The authors thank the editors, the anonymous referees, and Günter Schmidt for their insightful comments, which have significantly improved this paper. Preparation of this paper was supported, in part, by the ‘RiSC—Research Seed Capital Program’ of the Ministry of Science, Research and the Arts (MWK) Baden-Württemberg and the University of Mannheim, Germany. The APMOD conference presentation of this paper was funded by the Julius-Paul-Stiegler Gedächtnis Stiftung.

Author information

Authors and Affiliations

  1. University of Mannheim, Mannheim, Germany

    Esther Mohr

  2. Saarland University, Saarbrücken, Germany

    Robert Dochow

Authors
  1. Esther Mohr
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Robert Dochow
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Esther Mohr.

Additional information

The material in this paper was presented in part at the International Conference on Operations Research (OR2013), Erasmus University Rotterdam, NL; see also Dochow et al. (2014).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mohr, E., Dochow, R. Risk management strategies for finding universal portfolios. Ann Oper Res 256, 129–147 (2017). https://doi.org/10.1007/s10479-016-2176-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10479-016-2176-6

Keywords

Search

Navigation