• DocumentCode
    1893274
  • Title

    A Risk Prediction Model of Construction Enterprise Human Resources Based on Support Vector Machine

  • Author

    Li, Wanqing ; XU, Shipeng ; Meng, Wenqing

  • Author_Institution
    Sch. of Econ. & Manage., HeBei Univ. of Eng., Handan, China
  • Volume
    1
  • fYear
    2009
  • fDate
    10-11 Oct. 2009
  • Firstpage
    945
  • Lastpage
    948
  • Abstract
    In order to solve the problem of large Sample and low resolution problems in predicting the risk of human resource of construction enterprises, a new method based on support vector machine is proposed in this paper. By introducing the theoretical base of SVM (support vector machine), the model based on SVM can rationally solve the large sample and low resolution problems in genetic algorithm and other prediction method. For illustration, a risk prediction of human resource in construction enterprises example is utilized to show the feasibility of the SVM model in solving predicting problem. The final results show that the SVM model is a new and effectual method for predicting the risk of human resource in construction enterprises and provide a new research thought and method for predicting risk in other fields.
  • Keywords
    human resource management; risk management; support vector machines; construction enterprise human resources; genetic algorithm; risk prediction model; support vector machine; Human resource management; Learning systems; Machine intelligence; Machine learning algorithms; Management training; Mathematical model; Predictive models; Risk management; Statistical learning; Support vector machines; Support Vector Machines; construction enterprises; prediction; risk of human resources;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
  • Conference_Location
    Changsha, Hunan
  • Print_ISBN
    978-0-7695-3804-4
  • Type

    conf

  • DOI
    10.1109/ICICTA.2009.235
  • Filename
    5287531