Genetic Algorithm as a Tool for Stock Market Modelling

  • Urszula Markowska-Kaczmar
  • Halina Kwasnicka
  • Marcin Szczepkowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5097)


The paper describes the model of virtual stock market which is evolved by a genetic algorithm. The model consists of cooperating Agents that imitate behaviour of real investors. They act on the virtual market buying or selling stocks. The aim of the model is to generate stocks prices on a virtual market that are similar to real ones for a short period of time. Each Agent is described by its unique characteristics which determine his performance. The details of the model are presented in the paper. The applied genetic algorithm is generic one. Its main components such as: an individual, genetic operators and fitness function are described here, as well. The results of experiments investigating the role of genetic algorithm parameters are presented in the paper. Agent’s ability to predict the quotations values are presented and analysed. Future plans referring to the further development of the system are presented at the end of the paper.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Grothmann, R.: Multi-Agent Market Modeling based on Neural Networks. PhD thesis, University of Bremen, Germany (2002)Google Scholar
  2. 2.
    Schoreels, C., Logan, B., Garibaldi, J.: Agent based genetic algorithm employing financial technical analysis for making trading decisions using historical equity market data. In: Proc. of the IEEE/WIC/ACM Int’l Conf. on Intelligent Agent Technology 2004 (IAT 2004), Beijing, China, pp. 421–424 (2004)Google Scholar
  3. 3.
    Blok, H.: On the nature of the stock market: Simulations and experiments. PhD thesis, The University of British Columbia, Canada (2001)Google Scholar
  4. 4.
    Neuberg, L., Bertels, K.: An artificial stock market. In: Proceedings of the IASTED International Conference, pp. 308–313 (2002)Google Scholar
  5. 5.
    Ankenbrand, T., Tomassini, M.: Agent based simulation of multiple financial markets. Neural Network World 4, 397–405 (1997)Google Scholar
  6. 6.
    Schoreels, C., Garibaldi, J.: Genetic algorithm evolved agent-based equity trading using technical analysis and the capital asset pricing mode. In: Proc. 6th Int’l Conf. on Recent Advances in Soft Computing 2006 (RASC 2006), pp. 194–199 (2006)Google Scholar
  7. 7.
    Schulenburg, S., Ross, P.: Advances in Learning Classifier Systems. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) Explorations in LCS Models of Stock Trading, vol. 2321, pp. 150–179 (2002)Google Scholar
  8. 8.
    Tokinaga, S.: Modeling and analysis of agent-based artificial demand-supply market by using the genetic programming and its applications. Journal of political economy 71, 107–118 (2004)Google Scholar
  9. 9.
    Kendall, G., Su, Y.: Learning with imperfections-a multi-agent neural-genetic trading system with differing levels of social learning. In: Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems, pp. 47–52 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Urszula Markowska-Kaczmar
    • 1
  • Halina Kwasnicka
    • 1
  • Marcin Szczepkowski
    • 1
  1. 1.Wroclaw University of TechnologyPoland

Personalised recommendations