• DocumentCode
    1654448
  • Title

    Notice of Retraction
    Predicting stock market volatility by Bayesian treed Gaussian processes based on GARCH model

  • Author

    PhichHang Ou ; Hengshan Wang

  • Author_Institution
    Bus. Sch., Univ. of Shanghai for Sci. & Technol., Shanghai, China
  • Volume
    1
  • fYear
    2010
  • Firstpage
    440
  • Lastpage
    444
  • Abstract
    Notice of Retraction

    After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

    We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

    The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

    We propose to predict financial volatility by a new treed Gaussian processes based on GARCH model. Three correlation functions, isotropic exponential power, separable power and Matérn families, are applied in the proposed hybrid treed GP models and stationary Gaussian processes. The empirical results show that the hybrid approaches generate better predictive capability than the stationary GARCH models; particularly, the treed Gaussian processes with Matérn family correlation structure yields superior performance among the others.
  • Keywords
    Bayes methods; Gaussian processes; forecasting theory; stock markets; trees (mathematics); Bayesian tree; GARCH model; Gaussian process; Matérn family correlation function; financial volatility prediction; isotropic exponential power; separable power; stock market; Artificial neural networks; Biological system modeling; Bayesian Tree; GARCH; Gaussian Process; Volatility;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Management Science (ICAMS), 2010 IEEE International Conference on
  • Conference_Location
    Chengdu
  • Print_ISBN
    978-1-4244-6931-4
  • Type

    conf

  • DOI
    10.1109/ICAMS.2010.5553120
  • Filename
    5553120