A Clustering Application in Portfolio Management

  • Jin ZhangEmail author
  • Dietmar Maringer
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 60)


This chapter presents a new asset allocation model which combines a clustering technique with traditional asset allocation methods to improve portfolio Sharpe ratios and portfolio weights stability. The approach identifies optimal clustering patterns in different cluster number cases by using a population-based evolutionary method, namely Differential Evolution. Traditional asset allocations are used to compute the portfolio weights with the clustering. According to the experiment results, it is found that clustering contributes to higher Sharpe ratios and lower portfolio instability than that without clustering. Market practitioners may employ the clustering technique to improve portfolio weights stability and risk-adjusted returns, or for other optimization purposes while distributing the asset weights.


Clustering optimization asset allocation sharpe ratio weights instability differential evolution 


  1. 1.
    Benartzi, S., Thaler, R.H.: Naive diversification strategies in defined contribution saving plans. Am. Econ. Rev. 91, 79–98 (2001)CrossRefGoogle Scholar
  2. 2.
    Brucker, P.: On the complexity of clustering problems. In: Optimization and Operations Research,  Chapter 2, pp. 45–54. Springer, Germany (1977)Google Scholar
  3. 3.
    Farrelly, T.: Asset allocation for robust portfolios. J. Investing 15, 53–63 (2006)CrossRefGoogle Scholar
  4. 4.
    Gilli, M., Maringer, D., Winker, P.: Applications of Heuristics in finance. In: Handbook on Information Technology in Finance,  Chapter 26, pp. 635–653. Springer, Germany (2008)Google Scholar
  5. 5.
    Gilli, M., Winker, P.: A review of Heuristic optimization methods in econometrics. Working papers, Swiss Finance Institute Research Paper Series, No. 8–12 (2008)Google Scholar
  6. 6.
    Harris, R.D.F., Yilmaz, F.: Estimation of the conditional variance – covariance matrix of returns using the intraday range. Working Papers, XFi Centre for Finance and Investment (2007)Google Scholar
  7. 7.
    Lisi, F., Corazza, M.: Clustering financial data for mutual fund management. In: Mathematical and Statistical Methods in Insurance and Finance,  Chapter 20, pp. 157–164. Springer, Germany (2008)Google Scholar
  8. 8.
    Maringer, D.: Constrained index tracking under loss aversion using differential evolution. In: Natural Computing in Computational Finance,  Chapter 2, pp. 7–24. Springer, Germany (2008)Google Scholar
  9. 9.
    Pattarin, F., Paterlinib, S., Minervac, T.: Clustering financial time series: an application to mutual funds style analysis. Comput. Stat. Data An. 47, 353–372 (2004)zbMATHCrossRefGoogle Scholar
  10. 10.
    Storn, R., Price, K.: Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11, 341–359 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Windcliff, H., Boyle, P.: The 1/N pension investment puzzle. N. Am. Actuarial J. 8, 32–45 (2004)zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  1. 1.Centre for Computational Finance and Economic AgentsUniversity of EssexColchesterUK
  2. 2.Faculty of Economics and Business AdministrationUniversity of BaselBaselSwitzerland

Personalised recommendations