• DocumentCode
    2065531
  • Title

    Decision precising fuzzy technology to evaluate the credit risks of investment projects

  • Author

    Sirbiladze, Gia ; Khutsishvili, Irina ; Dvalishvili, Pridon

  • Author_Institution
    Dept. of Comput. Sci., Iv. Javakhishvili Tbilisi State Univ., Tbilisi, Georgia
  • fYear
    2010
  • fDate
    Nov. 29 2010-Dec. 1 2010
  • Firstpage
    103
  • Lastpage
    108
  • Abstract
    This work proposes a decision support technology to minimize risks while choosing among competitive investment projects. The technology combines two fuzzy-statistical methods, providing two stages of investment projects´ evaluation. At the first stage preliminary selection of projects with small risks is made on the basis of the expertons method [2],[3]. The second stage makes more precise decisions using the method of possibilistic discrimination analysis. This is a new method that represents a generalization of the fuzzy discrimination analysis [6]. The method is applied to a relatively small number of projects, selected during first stage, to compare and sort out high-quality projects. For the latter, the recommendations to provide credits are made. The article provides calculation examples that explain the work of the offered technology.
  • Keywords
    credit transactions; decision support systems; fuzzy set theory; investment; statistical analysis; credit risk; decision support technology; expertons method; fuzzy discrimination analysis; fuzzy-statistical method; investment project evaluation; possibilistic discrimination analysis; Decision making; Investment project risks; expert estimates; expertons; positive and negative measures of discrimination; possibility distribution;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Systems Design and Applications (ISDA), 2010 10th International Conference on
  • Conference_Location
    Cairo
  • Print_ISBN
    978-1-4244-8134-7
  • Type

    conf

  • DOI
    10.1109/ISDA.2010.5687282
  • Filename
    5687282