Exploring Market Behaviors with Evolutionary Mixed-Games Learning Model

  • Yu Du
  • Yingsai Dong
  • Zengchang Qin
  • Tao Wan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6922)


The minority game (MG) is a simple model for understanding collective behavior of agents competing for a limited resource. In our previous work, we assumed that collective data can be generated from combination of behaviors of variant groups of agents and proposed the minority game data mining (MGDM) model. In this paper, to further explore collective behaviors, we propose a new behavior learning model called Evolutionary Mixed-games Learning (EMGL) model, based on evolutionary optimization of mixed-games, which assumes there are variant groups of agents playing majority games as well as the minority games. Genetic Algorithms then are used to optimize group parameters to approximate the decomposition of the original system and use them to predict the outcomes of the next round. In experimental studies, we apply the EMGL model to real-world time-series data analysis by testing on a few stocks from Chinese stock market and the USD-RMB exchange rate. The results suggest that the EMGL model can predict statistically better than the MGDM model for most of the cases and both models perform significantly better than a random guess.


Exchange Rate Collective Behavior Chinese Stock Market Random Guess Memory Length 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mantegna, R., Stanley, H.: An Introduction to Econophysics: Correlations and Complexity in Finance. Cambridge University Press, Cambridge (1999)CrossRefzbMATHGoogle Scholar
  2. 2.
    Gode, D., Sunder, S.: Allocative efficiency of markets with zero-intelligence traders: Market as a partial substitute for individual rationality. Journal of Political Economy 101(1), 119–137 (1993)CrossRefGoogle Scholar
  3. 3.
    Johnson, N., Jefferies, P., Hui, P.: Financial Market Complexity. Oxford University Press, Oxford (2003)CrossRefGoogle Scholar
  4. 4.
    Qin, Z.: Market mechanism designs with heterogeneous trading agents. In: Proceedings of Fifth International Conference on Machine Learning and Applications (ICMLA), Orlando, Florida, USA, pp. 69–74 (2006)Google Scholar
  5. 5.
    Challet, D., Zhang, Y.: Emergence of cooperation in an evolutionary game. Physica A: Statistical and Theoretical Physics 246(3-4), 407–418 (1997)CrossRefGoogle Scholar
  6. 6.
    Li, G., Ma, Y., Dong, Y., Qin, Z.: Behavior learning in minority games. In: Guttmann, C., Dignum, F., Georgeff, M. (eds.) CARE 2009/2010. LNCS (LNAI), vol. 6066, pp. 125–136. Springer, Heidelberg (2011)Google Scholar
  7. 7.
    Ma, Y., Li, G., Dong, Y., Qin, Z.: Minority Game Data Mining for Stock Market Predictions. In: Cao, L., Bazzan, A.L.C., Gorodetsky, V., Mitkas, P.A., Weiss, G., Yu, P.S. (eds.) ADMI 2010. LNCS, vol. 5980, pp. 178–189. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Gou, C.: Dynamic Behaviors of Mix-game Models and Its Application (2005),
  9. 9.
    Gou, C.: Agents Play Mix-game. In: Econophysics of Stock and Other Markets. LNCS, Part II, pp. 123–132 (2006)Google Scholar
  10. 10.
    Savit, R., Koelle, K., Treynor, W., Gonzalez, R.: In: Tumer, Wolpert (eds.) Collectives and the Design of Complex System, pp. 199–212. Springer, Heidelberg (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Yu Du
    • 1
  • Yingsai Dong
    • 1
  • Zengchang Qin
    • 1
    • 2
  • Tao Wan
    • 2
  1. 1.Intelligent Computing and Machine Learning Lab, School of Automation Science and Electrical EngineeringBeihang UniversityBeijingChina
  2. 2.Robotics InstituteCarnegie Mellon UniversityUSA

Personalised recommendations