Soft Computing

, Volume 21, Issue 16, pp 4707–4720 | Cite as

Detecting structural breaks in time series via genetic algorithms

  • Benjamin Doerr
  • Paul Fischer
  • Astrid Hilbert
  • Carsten Witt
Methodologies and Application


Detecting structural breaks is an essential task for the statistical analysis of time series, for example, for fitting parametric models to it. In short, structural breaks are points in time at which the behaviour of the time series substantially changes. Typically, no solid background knowledge of the time series under consideration is available. Therefore, a black-box optimization approach is our method of choice for detecting structural breaks. We describe a genetic algorithm framework which easily adapts to a large number of statistical settings. To evaluate the usefulness of different crossover and mutation operations for this problem, we conduct extensive experiments to determine good choices for the parameters and operators of the genetic algorithm. One surprising observation is that use of uniform and one-point crossover together gave significantly better results than using either crossover operator alone. Moreover, we present a specific fitness function which exploits the sparse structure of the break points and which can be evaluated particularly efficiently. The experiments on artificial and real-world time series show that the resulting algorithm detects break points with high precision and is computationally very efficient. A reference implementation with the data used in this paper is available as an applet at the following address: It has also been implemented as package SBRect for the statistics language R.


Genetic Algorithms Statistics Break points Experimentation  Time series Range trees 



Paul Fischer gratefully acknowledges support by DTU’s Corrit travel grant. Benjamin Doerr was supported through grant WI 3552/1-1 by the German Research Foundation (DFG) while visiting the Technical University of Denmark in 2012.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. Bäck T, Fogel DB, Michalewicz Z (eds) (1997) Handbook of Evolutionary Computation, 1st edn. IOP Publishing Ltd., BristolzbMATHGoogle Scholar
  2. Bardet JM, Kengne W, Wintenberger O (2012) Multiple breaks detection in general causal time series using penalized quasi-likelihood. Electron J Stat 6:435–477MathSciNetCrossRefzbMATHGoogle Scholar
  3. Bentley JL (1979) Decomposable searching problems. Inf Process Lett 8(5):244–251MathSciNetCrossRefzbMATHGoogle Scholar
  4. Chen Y, Härdle WK, Pigorsch U (2010) Localized realized volatility modeling. J Am Stat Assoc 105(492):1376–1393MathSciNetCrossRefzbMATHGoogle Scholar
  5. de Berg M, van Krefeld M, Overmars M, Schwarzkopf O (2000) Computational Geometry: Algorithms and Applications, 2nd edn. SpringerGoogle Scholar
  6. Davis R, Lee T, Rodriguez-Yam G (2006) Structural break estimation for nonstatinary time series models. J Am Stat Assoc 101(473):223–239CrossRefzbMATHGoogle Scholar
  7. Davis R, Lee T, Rodriguez-Yam G (2008) Break detection for a class of nonlinear time series models. J Time Ser Anal 29:834–867MathSciNetCrossRefzbMATHGoogle Scholar
  8. De Grauwe P, Ji Y (2012) Mispricing of sovereign risk and multiple equilibria in the eurozone. Centre for European Policy Working Paper 361Google Scholar
  9. De Wachter S, Tzavalis E (2012) Detection of structural breaks in linear dynamic panel data models. Comput Stat Data Anal 56(11):3020–3034MathSciNetCrossRefzbMATHGoogle Scholar
  10. Deb K, Mohan M, Mishra S (2005) Evaluating the domination based multiobjective evolutionary algorithm for a quick computation of pareto-optimal solutions. Evol Comput J 13(4):501–525CrossRefGoogle Scholar
  11. Fischer J, Heun V (2011) Space-efficient preprocessing schemes for range minimum queries on static arrays. SIAM J Comput 40:465–492MathSciNetCrossRefzbMATHGoogle Scholar
  12. Fischer P, Hilbert A (2014) Fast detection of structural breaks. In: Proceedings of 21th International Conference on Computational Statistics 2014, pp 9–16Google Scholar
  13. Gaetan C (2000) Subset arma model identification using genetic algorithms. J Time Ser Anal 21(5):559–570MathSciNetCrossRefzbMATHGoogle Scholar
  14. Hillebrand E, Medeiros MC (2014) Nonlinearity, breaks, and long-range dependence in time-series models. J Bus Econ Stat (just-accepted):00–00Google Scholar
  15. Jansen T, Zarges C (2011) Analysis of evolutionary algorithms: From computational complexity analysis to algorithm engineering. In: Proceedings of the 11th ACM SIGEVO Workshop on Foundations of Genetic Algorithms (FOGA 2011), ACM Press, pp 1–14Google Scholar
  16. Jong K, Marchiori E, van der Vaart A, Ylstra B, Weiss M, Meijer G (2003) Chromosomal breakpoint detection in human cancer. In: Proceedings Applications of Evolutionary Computing, EvoWorkshop 2003: EvoBIO, EvoCOP, EvoIASP, EvoMUSART, EvoROB, and EvoSTIM, Essex, UK, April 14-16, 2003, pp 54–65. doi: 10.1007/3-540-36605-9_6
  17. Kanpur_Genetic_Algorithms_Laboratory (2005-2015) Kangal. Website,
  18. Knuth D (1969) The Art of Computer Programming, vol II. Addison-WesleyGoogle Scholar
  19. Lee TC (2002) Automatic smoothing for discontinuous regression functions. Stat Sin 12(3):823–842MathSciNetzbMATHGoogle Scholar
  20. Meligkotsidou L, Vrontos ID (2014) Detecting structural breaks in multivariate financial time series: evidence from hedge fund investment strategies. J Stat Comput Simul 84(5):1115–1135MathSciNetCrossRefGoogle Scholar
  21. Morales L, Gassie E (2011) Structural breaks and financial volatility: Lessons from bric countries. Leibniz-Institut für Agrarentwicklung in Mittel- und Osteuropa (IAMO), Halle (Saale), no. 13 in IAMO Forum 2011.
  22. Nunkesser R, Morell O (2010) An evolutionary algorithm for robust regression. Comput Stat Data Anal 54(12):3242–3248MathSciNetCrossRefzbMATHGoogle Scholar
  23. Preuß P, Puchstein R, Dette H (2015) Detection of multiple structural breaks in multivariate time series. J Am Stat Assoc 110:654–668MathSciNetCrossRefGoogle Scholar
  24. Rapach DE, Wohar ME (eds) (2008) Frontiers of Economics and Globalization, vol 3, Forecasting in the Presence of Structural Breaks and Model Uncertainty. EmeraldGoogle Scholar
  25. Rubner Y, Tomasi C, Guibas L (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vis 40(2):99–121. doi: 10.1023/A:1026543900054 CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Benjamin Doerr
    • 1
  • Paul Fischer
    • 2
  • Astrid Hilbert
    • 3
  • Carsten Witt
    • 2
  1. 1.École PolytechniquePalaiseauFrance
  2. 2.DTU Compute Technical University of DenmarkLyngbyDenmark
  3. 3.Mathematics Linnaeus UniversityVäxjöSweden

Personalised recommendations