• DocumentCode
    2165257
  • Title

    Research on BP Neural Network Evaluation Model of Credit Risk of Bank Clients

  • Author

    Zhu, Chunsheng ; Zhan, Yuanrui ; Jia, Shijun

  • Author_Institution
    Sch. of Manage., Tianjin Univ., Tianjin, China
  • fYear
    2010
  • fDate
    24-26 Aug. 2010
  • Firstpage
    1
  • Lastpage
    5
  • Abstract
    Credit is the cornerstone of modern market economy. Credit risk is one of the most important risks which the banks are facing to. Credit risk Evaluation virtually is a non-linear classification matter. The banks evaluate and classify the clients according to their information data, then according to the results of classification to decide whether to authorize the loans. This article established the artificial BP neural network evaluation model and achieved intelligence of the bank´s credit risk assessment and increased the scientific of bank credit evaluation and management. It is very significant that using trade credit division to determine the credit rating for dealing with bank´s non-linear complicated credit management. And we select part of the clients´ information of several banks´ real estate industry to establish the evaluation model for the empirical test.
  • Keywords
    backpropagation; banking; credit transactions; neural nets; risk management; artificial BP neural network evaluation model; bank clients; bank credit evaluation; bank credit management; bank credit risk assessment; credit rating; information data; loans; market economy; nonlinear classification matter; nonlinear complicated credit management; real estate industry; trade credit division; Analytical models; Artificial neural networks; Biological system modeling; Neurons; Risk management; Training;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Management and Service Science (MASS), 2010 International Conference on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-5325-2
  • Electronic_ISBN
    978-1-4244-5326-9
  • Type

    conf

  • DOI
    10.1109/ICMSS.2010.5576862
  • Filename
    5576862