Stocks’ Trading System Based on the Particle Swarm Optimization Algorithm

  • Jovita Nenortaite
  • Rimvydas Simutis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3039)


One of the central problems in financial markets is to make the profitable stocks trading decisions using historical stocks’ market data. This paper presents the decision-making method which is based on the application of neural networks (NN) and swarm intelligence technologies and is used to generate one-step ahead investment decisions. In brief, the analysis of historical stocks prices variations is made using “single layer” NN, and subsequently the Particle Swarm Optimization (PSO) algorithm is applied in order to select ”global best” NN for the future investment decisions and to adapt the weights of other networks towards the weights of the best network. The experimental investigations were made considering different number of NN, moving time intervals and commission fees. The experimental results presented in the paper show that the application of our proposed method lets to achieve better results than the average of the market.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bartholdson, K., Mauboussin, J.M.: Thoughts on Organizing for Investing Success. Credit Suisse First Boston Equity Research (2002)Google Scholar
  2. 2.
    Carlisle, A., Dozier, G.: Adapting Particle Swarm Optimization to Dynamic Environments. In: 2000 ICAI Proceedings, Las Vegas, pp. 429–434 (2000)Google Scholar
  3. 3.
    Engelbrecht, A.D.: Computational Intelligence (An Introduction). John Wiley & Sons, London (2002)Google Scholar
  4. 4.
    Hellstrom, T.: Optimizing the Sharpe Ration for a Rank Based Trading System. In: Brazdil, P.B., Jorge, A.M. (eds.) EPIA 2001. LNCS (LNAI), vol. 2258, p. 130. Springer, Heidelberg (2001)Google Scholar
  5. 5.
    Interactive Brokers: Current as of February 9 (2004),
  6. 6.
    Kaastra, I., Milton, B.: Designing a Neural Network for Forecasting Financial and Economic Time Series. Neurocomputing (1996)Google Scholar
  7. 7.
    Kennedy, J., Spears, W.M.: Matching Algorithms to Problems: An Experimental Test of the Particle Swarm and Some Genetic Algorithms on the Multimodal Problem Generator, (Current as of December 15, 2003)
  8. 8.
    Khalil, A.S.: An Investigation into Optimization Strategies of Genetic Algorithms and Swarm Intelligence. Artificial Life (2001)Google Scholar
  9. 9.
    Lowe, D., Webb, A.R.: Time Series Prediction by Adaptive Networks: A Dynamical Systems Perspective. IEEE Computer Society Press, Los Alamitos (1991)Google Scholar
  10. 10.
    Pavlidis, N.G., Tasoulis, D., Vrahatis, M.N.: Financial Forecasting Through Unsupervised Clustering and Evolutionary Trained Neural Networks. In: 2003 Congress on Evolutionary Computation, Canberra Australia (2003)Google Scholar
  11. 11.
    Simutis, R.: Stock Trading Systems Based on Stock’s Price Ranks (in Lithuanian). Ekonomika (2003)Google Scholar
  12. 12.
    White, H.: Economic Prediction Using Neural Networks: The Case of IBM Daily Stock Returns. In: IEEE International Conference on Neural Networks, San Diego (1988)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jovita Nenortaite
    • 1
  • Rimvydas Simutis
    • 1
  1. 1.Kaunas Faculty of HumanitiesVilnius UniversityKaunasLithuania

Personalised recommendations