Advertisement

Neural Computing and Applications

, Volume 31, Issue 3, pp 923–937 | Cite as

A new multi-period investment strategies method based on evolutionary algorithms

  • Anton Aguilar-Rivera
  • Manuel Valenzuela-RendónEmail author
Original Article
  • 164 Downloads

Abstract

This work introduces a new algorithmic trading method based on evolutionary algorithms and portfolio theory. The limitations of traditional portfolio theory are overcome using a multi-period definition of the problem. The model allows the inclusion of dynamic restrictions like transaction costs, portfolio unbalance, and inflation. A Monte Carlo method is proposed to handle these types of restrictions. The investment strategies method is introduced to make trading decisions based on the investor’s preference and the current state of the market. Preference is determined using heuristics instead of theoretical utility functions. The method was tested using real data from the Mexican market. The method was compared against buy-and-holds and single-period portfolios for metrics like the maximum loss, expected return, risk, the Sharpe’s ratio, and others. The results indicate investment strategies perform trading with less risk than other methods. Single-period methods attained the lowest performance in the experiments due to their high transaction costs. The conclusion was investment decisions that are improved when information providing from many different sources is considered. Also, profitable decisions are the result of a careful balance between action (transaction) and inaction (buy-and-hold).

Keywords

Evolutionary algorithms Portfolio optimization Algorithmic trading Multi-objective 

Notes

Acknowledgements

The authors are with the Research Group with Strategic Focus on Intelligent Systems of the National School of Engineering and Sciences at the Tecnológico de Monterrey and gratefully acknowledge its support. The first author thanks the Consejo Nacional de Ciencia y Tecnología (CONACyT) for its financial support through the PNPC program.

Compliance with ethical standards

Conflict of interest

The authors declare they have no conflict of interest.

References

  1. 1.
    Aguilar-Rivera R, Valenzuela-Rendón M, Rodríguez-Ortiz JJ (2015) Genetic algorithms and Darwinian approaches in financial applications: a survey. Expert Syst Appl 42(21):7684–7697CrossRefGoogle Scholar
  2. 2.
    Almgren R, Chriss N (2001) Optimal execution of portfolio transactions. J Risk 3:5–40CrossRefGoogle Scholar
  3. 3.
    Çanakoğlu E, Özekici S (2009) Portfolio selection in stochastic markets with exponential utility functions. Ann Oper Res 166(1):281–297MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Chen AH, Fabozzi FJ, Huang D (2012) Portfolio revision under mean-variance and mean-CVaR with transaction costs. Rev Quant Financ Account 39(4):509–526CrossRefGoogle Scholar
  5. 5.
    Chen AH, Jen FC, Zionts S (1971) The optimal portfolio revision policy. J Bus 44(1):51–61CrossRefGoogle Scholar
  6. 6.
    Corne DW, Knowles JD, Oates MJ (2000) The Pareto envelope-based selection algorithm for multiobjective optimization. Parallel problem solving from nature PPSN VI. Springer, BerlinGoogle Scholar
  7. 7.
    Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2):182–197CrossRefGoogle Scholar
  8. 8.
    Elton EJ, Gruber MJ (1974) The multi-period consumption investment problem and single period analysis. Oxford Econ Pap 26(2):289–301CrossRefGoogle Scholar
  9. 9.
    World Federation of Exchanges database (2015). http://www.world-exchanges.org
  10. 10.
    Finkelstein M, Whitley R (1981) Optimal strategies for repeated games. Adv Appl Probab 13(02):415–428MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Gupta P, Mehlawat MK, Mittal G (2012) Asset portfolio optimization using support vector machines and real-coded genetic algorithm. J Glob Optim 53(2):297–315MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Hibiki N (2006) Multi-period stochastic optimization models for dynamic asset allocation. J Bank Financ 30(2):365–390CrossRefGoogle Scholar
  13. 13.
    Dow Jones Industrial Average (2015). https://finance.yahoo.com/quote/DJI
  14. 14.
    Knowles J, Corne D (1999) The Pareto archived evolution strategy: A new baseline algorithm for Pareto multiobjective optimisation. In: Proceedings of the 1999 congress on evolutionary computation, vol 1, pp 98–105Google Scholar
  15. 15.
    Köppen M, Yoshida K (2007) Substitute distance assignments in NSGA-II for handling many-objective optimization problems. In: Evolutionary multi-criterion optimization. Springer, Berlin, pp 727–741Google Scholar
  16. 16.
    Li D, Ng WL (2000) Optimal dynamic portfolio selection: multiperiod mean-variance formulation. Math Financ 10(3):387–406MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Lo A, Mamaysky H, Wang J (2000) Foundations of technical analysis: computational algorithms, statistical inference, and empirical implementation. J Financ 55(4):1705–1770CrossRefGoogle Scholar
  18. 18.
    Lwin K, Qu R, Kendall G (2014) A learning-guided multi-objective evolutionary algorithm for constrained portfolio optimization. Appl Soft Comput 24:757–772CrossRefGoogle Scholar
  19. 19.
    Ma I, Wong T, Sankar T, Siu R (2004) Forecasting the volatility of a financial index by wavelet transform and evolutionary algorithm. IEEE Int Conf Syst Man Cybern 6:5824–5829Google Scholar
  20. 20.
    Markowitz HM (1968) Portfolio selection: efficient diversification of investments (vol 16). Yale University Press, New HavenGoogle Scholar
  21. 21.
    Markowitz HM, Lacey R, Plymen J, Dempster MAH, Tompkins RG (1994) The general mean-variance portfolio selection problem [and discussion]. Philos Trans Phys Sci Eng 347(1684):543–549Google Scholar
  22. 22.
    McDonald J (2015) Handbook of biological statistics, vol 2. Sparky House Publishing, BatimoreGoogle Scholar
  23. 23.
    Ponsich A, Jaimes AL, Coello CAC (2013) A survey on multiobjective evolutionary algorithms for the solution of the portfolio optimization problem and other finance and economics applications. IEEE Trans Evol Comput 17(3):321–344CrossRefGoogle Scholar
  24. 24.
    Ranković V, Drenovak M, Stojanović B, Kalinić Z, Arsovski Z (2014) The mean-value at risk static portfolio optimization using genetic algorithm. Comput Sci Inform Syst 11(1):89–109CrossRefGoogle Scholar
  25. 25.
    Sharpe WF, Alexander GJ, Bailey JV (1999) Investments. Prentice Hall, Upper Saddle RiverGoogle Scholar
  26. 26.
    Valenzuela-Rendón M (2003) The virtual gene genetic algorithm. In: Genetic and evolutionary computation conference, Springer, Berlin, pp 1457–1468Google Scholar
  27. 27.
    Valenzuela-Rendón M, Uresti-Charre E (1997) A non-generational genetic algorithm for multiobjective optimization. In: Proceedings of the seventh international conference on genetic algorithmsGoogle Scholar
  28. 28.
    Wang W, Hu J, Dong N (2015) A convex-risk-measure based model and genetic algorithm for portfolio selection. Math Probl Eng 2015:8. doi: 10.1155/2015/451627
  29. 29.
    Yi L (2010) Multi-period portfolio selection with transaction costs. In: 2nd IEEE international conference on information and financial engineering, 2010 , pp 98–103Google Scholar
  30. 30.
    Zhang XL, Zhang KC (2009) Using genetic algorithm to solve a new multi-period stochastic optimization model. J Comput Appl Math 231(1):114–123MathSciNetCrossRefzbMATHGoogle Scholar
  31. 31.
    Zhou X, Yang C, Gui W (2014) Nonlinear system identification and control using state transition algorithm. Appl Math Comput 226:169–179MathSciNetzbMATHGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.School of Engineering and ScienceTecnológico de MonterreyMonterreyMexico

Personalised recommendations