• DocumentCode
    3082362
  • Title

    A neural network based time series forecasting system

  • Author

    Kozarzewski, Bohdan

  • Author_Institution
    Univ. of Inf. Technol. & Manage., Rzeszów, Poland
  • fYear
    2010
  • fDate
    13-15 May 2010
  • Firstpage
    59
  • Lastpage
    62
  • Abstract
    Neural network based system is proposed as a tool supporting time series forecasting. Wavelets analysis is suggested for raw data preprocessing. The preprocessed data are fed into SOM neural networks for clustering. The system has been tested as a tool supporting stock market investment decisions and shows good prediction accuracy of the method. However effectiveness, measured by income from shares trading according to the system, is not satisfactory to the same extend.
  • Keywords
    forecasting theory; investment; self-organising feature maps; stock markets; time series; SOM neural networks; shares trading; stock market investment; time series forecasting system; wavelets analysis; Artificial neural networks; Autocorrelation; Data preprocessing; Economic forecasting; Information technology; Investments; Neural networks; Stock markets; Technology forecasting; Time series analysis; Artificial neural networks; stock market prediction; wavelets decomposition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Human System Interactions (HSI), 2010 3rd Conference on
  • Conference_Location
    Rzeszow
  • Print_ISBN
    978-1-4244-7560-5
  • Type

    conf

  • DOI
    10.1109/HSI.2010.5514591
  • Filename
    5514591