Threshold Accepting Approach to Improve Bound-based Approximations for Portfolio Optimization

  • Daniel Kuhn
  • Panos Parpas
  • Berç Rustem

Abstract

A discretization scheme for a portfolio selection problem is discussed. The model is a benchmark relative, mean-variance optimization problem in continuous time. In order to make the model computationally tractable, it is discretized in time and space. This approximation scheme is designed in such a way that the optimal values of the approximate problems yield bounds on the optimal value of the original problem. The convergence of the bounds is discussed as the granularity of the discretization is increased. A threshold accepting algorithm that attempts to find the most accurate discretization among all discretizations of a given complexity is also proposed. Promising results of a numerical case study are provided.

Key words

Portfolio optimization stochastic programming time discretization bounds threshold accepting 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ash, R.B.: 1972, Real Analysis and Probability, Probability and Mathematical Statistics, Academic Press, Berlin.Google Scholar
  2. Birge, J.R. and Louveaux, F.: 1997, Introduction to Stochastic Programming, Springer-Verlag, New York.Google Scholar
  3. Dueck, G. and Scheuer, T.: 1990, Threshold accepting: a general purpose optimization algorithm appearing superior to simulated annealing, J. Comput. Phys. 90(1), 161–175.CrossRefGoogle Scholar
  4. Dupacová, J.: 1966, On minimax solutions of stochastic linear programming problems, Casopis pro Pestování Matematiky 91, 423–429.Google Scholar
  5. Edirisinghe, N.C.P. and Ziemba, W.T.: 1994a, Bounding the expectation of a saddle function with application to stochastic programming, Math. Oper. Res. 19, 314–340.CrossRefGoogle Scholar
  6. Edirisinghe, N.C.P. and Ziemba, W.T.: 1994b, Bounds for two-stage stochastic programs with fixed recourse, Math. Oper. Res. 19, 292–313.Google Scholar
  7. Frauendorfer, K.: 1994, Multistage stochastic programming: Error analysis for the convex case, Z. Oper. Res. 39(1), 93–122.Google Scholar
  8. Frauendorfer, K.: 1995, The stochastic programming extension of the Markowitz model, Int. J. Neural Mass-Parallel Comput. Inform. Syst. 5, 449–460.Google Scholar
  9. Frauendorfer, K.: 1996, Barycentric scenario trees in convex multistage stochastic programming, Math. Program. 75(2), 277–294.CrossRefGoogle Scholar
  10. Frauendorfer, K. and Siede, H.: 2000, Portfolio selection using multi-stage stochastic programming, Central European J. Oper. Res. 7, 277–290.Google Scholar
  11. Gertz, E.M. and Wright, S.J.: 2003, Object-oriented software for quadratic programming, A CM Trans. Math. Software 29(1), 58–81.CrossRefGoogle Scholar
  12. Gilli, M. and Këllezi, E.: 2002, The Threshold Accepting Heuristic for Index Tracking, in P. Pardalos and V.K. Tsitsiringos (eds), Financial Engineering, E-Commerce and Supply Chain, Applied Optimization Series, Kluwer Academic Publishers, Boston, pp. 1–18.Google Scholar
  13. Gilli, M., Këllezi, E. and Hysi, H.: 2006, A data-driven optimization heuristic for downside risk minimization, Journal of Risk 8(4), 1–18.Google Scholar
  14. Gilli, M. and Winker, P.: 2007, Heuristic optimization methods in econometrics, in E.J. Kontoghiorghes and D. Belsley (eds), Handbook of Computational Econometrics, Handbooks series of Computing and Statistics with Applications, Elsevier. In preparation.Google Scholar
  15. Gülpinar, N. and Rustern, B.: 2006, Worst-case robust decisions for multiperiod mean-variance portfolio optimization, European J. Oper. Res.. In press.Google Scholar
  16. Gülpinar, N., Rustem, B. and Settergren, R.: 2002, Multistage stochastic programming in computational finance, in E. J. Kontoghiorghes, B. Rustem and S. Siokos (eds), Computational Methods in Decision-Making, Economics and Finance, Vol. 74 of Applied Optimization, Kluwer Academic Publishers, pp. 33–45.Google Scholar
  17. Gülpinar, N., Rustem, B. and Settergren, R.: 2004, Optimization and sinmulation approaches to scenario tree generation, J. Econ. Dyn. Control 28(7), 1291–1315.CrossRefGoogle Scholar
  18. Hochreiter, R. and Pflug, G.C.: 2007, Financial scenario generation for stochastic multi-stage decision processes as facility location problems, Ann. Oper. Res. 156(1), 257–272.CrossRefGoogle Scholar
  19. Kall, P. and Wallace, S.W.: 1994, Stochastic Programming, John Wiley & Sons, Chichester.Google Scholar
  20. Kuhn, D.: 2007a, Aggregation and discretization in multistage stochastic programming, Math. Program. A. Online First.Google Scholar
  21. Kuhn, D.: 2007b, Convergent bounds for stochastic programs with expected value constraints, The Stochastic Programming E-Print Series (SPEPS).Google Scholar
  22. Madansky, A.: 1960, Inequalities for stochastic linear programming problems, Manage. Sci. 6, 197–204.Google Scholar
  23. Markowitz, H.M.: 1952, Portfolio selection, Journal of Finance 7(1), 77–91.CrossRefGoogle Scholar
  24. Merton, R.C.: 1992, Continuous Time Finance, Basil Blackwell, Cambridge, MA.Google Scholar
  25. Rockafellar, R.T. and Wets, R.J.-B.: 1978, The optimal recourse problem in discrete time: L1-multipliers for inequality constraints, SIAM J. Control Optimization 16, 16–36.CrossRefGoogle Scholar
  26. Rosenblatt, M.: 1952, Remarks on a multivariate transformation, Ann. Math. Stat. 23(3), 470–472.CrossRefGoogle Scholar
  27. Steinbach, M.C.: 2001, Markowitz revisited: mean-variance models in financial portfolio analysis, SIAM Rev. 43(1), 31–85.CrossRefGoogle Scholar
  28. Wright, S.E.: 1994, Primal-dual aggregation and disaggregation for stochastic linear programs, Math. Oper. Res. 19(4), 893–908.Google Scholar
  29. Zhou, X.Y. and Li, D.: 2000, Continuous time mean-variance portfolio selection: A stochastic LQ framework, Appl. Math. Optim. 42, 19–33.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Daniel Kuhn
    • 1
  • Panos Parpas
    • 1
  • Berç Rustem
    • 1
  1. 1.Department of ComputingImperial College LondonLondonUK

Personalised recommendations