Advertisement

A Novel Hybrid Nature-Inspired Scheme for Solving a Financial Optimization Problem

  • Alexandros Tzanetos
  • Vassilios VassiliadisEmail author
  • Georgios Dounias
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10334)

Abstract

Hybrid intelligent approaches have proven their potential in demanding problem settings. The financial domain provides some challenging problem set-ups, mostly because of non-linearity conditions and conflicting objectives and binding restrictions. In this study, a novel hybrid algorithm, which stems from Nature-Inspired Intelligence, is applied in a specific portfolio optimization problem. The proposed algorithm comprises of an Ant Colony Optimization Algorithm (ACO) for detecting optimal combination of assets and a Gravitational Search Algorithm (GSA), for optimal capital allocation in the portfolio. Results from the proposed hybrid scheme are compared to previous findings, in the same optimization problem and dataset, from another hybrid NII algorithm, namely ACO Algorithm with Firefly Algorithm (FA). Experimental findings indicate that the proposed hybrid scheme yields a promising distribution of fitness values from independent simulation runs. What is more, in terms of best solution found, the proposed hybrid scheme yielded a solution that is 7.2% worst than the benchmark approach’s one. However, in terms of execution time, the proposed algorithm was faster. Taking into consideration both the above aspects, the difference of the two hybrid algorithms, in terms of best solution, can be characterized as insignificant. The main aim of the paper is to highlight the advantages of the proposed hybrid scheme, as well as the great potential of Nature-Inspired Intelligent algorithms for the financial portfolio optimization problem.

Keywords

Hybrid NII Ant Colony Optimization Gravitational Search Algorithm Financial portfolio optimization 

References

  1. 1.
    Maringer, D.: Portfolio Management with Heuristic Optimization. Advances in Computational Science. Springer, Heidelberg (2005)zbMATHGoogle Scholar
  2. 2.
    Vassiliadis, V., Dounias, G.: Nature-inspired intelligence: a review of selected methods and applications. Int. J. Artif. Intell. Tools 18(4), 487–516 (2009)CrossRefGoogle Scholar
  3. 3.
    Giannakouris, G., Vassiliadis, V., Dounias, G.: Experimental study on a hybrid nature-inspired algorithm for financial portfolio optimization. In: Konstantopoulos, S., Perantonis, S., Karkaletsis, V., Spyropoulos, Constantine D., Vouros, G. (eds.) SETN 2010. LNCS, vol. 6040, pp. 101–111. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-12842-4_14 CrossRefGoogle Scholar
  4. 4.
    Shapcott, J.: Index tracking: genetic algorithms for investment portfolio selection. EPCC-SS92-24, pp. 1–24 (1992)Google Scholar
  5. 5.
    Gomez, M. A., Flores, C.X., Osorio, M.A.: Hybrid search for cardinality constrained portfolio optimization. In: GECCO 2006, pp. 1865–1866 (2006)Google Scholar
  6. 6.
    Markowitz, H.: Portfolio selection. J. Finan. 7(1), 77–91 (1952)Google Scholar
  7. 7.
    Vassiliadis, V., Thomaidis, N., Dounias, G.: Active portfolio management under a downside risk framework: comparison of a hybrid nature – inspired scheme. In: Corchado, E., Wu, X., Oja, E., Herrero, Á., Baruque, B. (eds.) HAIS 2009. LNCS, vol. 5572, pp. 702–712. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-02319-4_85 CrossRefGoogle Scholar
  8. 8.
    Chen, W., Zhang, R.T., Cai, Y.M., Xu, F.S.: Particle swarm optimization for constrained portfolio selection problems. In: 5th International Conference on Machine Learning and Cybernetics, pp. 2425–2429 (2006)Google Scholar
  9. 9.
    Thomaidis, N.S., Angelidis, T., Vassiliadis, V., Dounias, G.: Active portfolio management with cardinality constraints: an application of particle swarm optimization. New Math. Nat. Comput. 5(03), 535–555 (2009)CrossRefzbMATHGoogle Scholar
  10. 10.
    Dorigo, M., Stultze, M.: Ant Colony Optimization. The MIT Press, Cambridge (2004)zbMATHGoogle Scholar
  11. 11.
    Yang, X.S.: Nature-Inspired Metaheuristic Algorithm. Luniver Press, Bristol (2008)Google Scholar
  12. 12.
    Rashedi, E., Nezamabadi-Pour, H., Saryazdi, S.: GSA: a gravitational search algorithm. Inf. Sci. 179(13), 2232–2248 (2009)CrossRefzbMATHGoogle Scholar
  13. 13.
    Xing, B., Gao, W.-J.: Gravitational search algorithm. In: Xing, B., Gao, W.-J. (eds.) Innovative Computational Intelligence: A Rough Guide to 134 Clever Algorithms. ISRL, vol. 62, pp. 355–364. Springer, Cham (2014). doi: 10.1007/978-3-319-03404-1_22 CrossRefGoogle Scholar
  14. 14.
    Sabri, N.M., Puteh, M., Mahmood, M.R.: A review of gravitational search algorithm. Int. J. Adv. Soft Comput. Appl. 5(3), 1–39 (2013)Google Scholar
  15. 15.
    Kuhn, J.: Optimal Risk-Return Tradeoffs of Commercial Banks and the Suitability of Profitability Measures for Loan Portfolios. Springer, Berlin (2006)zbMATHGoogle Scholar
  16. 16.
    Sharpe, W.F.: The sharpe ratio. J. Portfolio Manage. 21(1), 49–58 (1994)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Alexandros Tzanetos
    • 1
  • Vassilios Vassiliadis
    • 1
    Email author
  • Georgios Dounias
    • 1
  1. 1.Management and Decision Engineering Laboratory, Department of Financial and Management EngineeringUniversity of the AegeanChiosGreece

Personalised recommendations