A Dynamic Hybrid RBF/Elman Neural Networks for Credit Scoring Using Big Data

  • Yacine DjemaielEmail author
  • Nadia Labidi
  • Noureddine Boudriga
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 255)


The evaluation of credit applications is among processes that should be conducted in an efficient manner in order to prevent incorrect decisions that may lead to a loss even for the bank or for the credit applicant. Several approaches have been proposed in this context in order to ensure the enhancement of the credit evaluation process by using various artificial intelligence approaches. Even if the proposed schemes have shown their efficiency, the provided decision regarding a credit is not correct in most cases due to the lack of information for a provided criteria, incorrect defined weights for credit criteria, and a missing information regarding a credit applicant. In this paper, we propose a hybrid neural network that ensures the enhancement of the decision for credit applicants data based on a credit scoring by considering the big data related to the context associated to credit criterion which is collected through a period of time. The proposed model ensures the evaluation of credit by using a set of collectors that are deployed through interconnected networks. The efficiency of the proposed model is illustrated through a conducted simulation based on a set of credit applicant’s data.


Credit Neural networks Big data Credit scoring Collectors Context Decision 


  1. 1.
    Al Douri, B., Beurouti, M.: Credit scoring model based on back propagation neural network using various activation and error function. Int. J. Comput. Sci. Netw. Secur. 14(3), 16–24 (2014)Google Scholar
  2. 2.
    Edelman, D.B., Crook, J.N., Thomas, L.C.: Recent developments in consumer credit risk assessment. Eur. J. Oper. Res. 183(3), 1447–1465 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Lee, T.C., Chen, I.: A two stage hybrid credit scoring using artificial neural networks and multivariate adaptive regression splines. Expert Syst. Appl. 28, 743–752 (2005)CrossRefGoogle Scholar
  4. 4.
    Martens, J., Sutskever, I.: Learning recurrent neural network with hassian-free optimization. In: The 28th International Confrence on Learning Machine, Bellevue, WA, USA (2011)Google Scholar
  5. 5.
    Pradhan, S.K., Pradhan, M., Sahu, S.K.: Anomaly detection using artificial neural network. Int. J. Eng. Sci. Emerg. Technol. 2(1), 29–36 (2012)Google Scholar
  6. 6.
    Wang, Z., Tong, X., Yu, H.: A research using hybrid RBF/Elman neural networks for intrusion detection system secure model. Comput. Phys. 180, 1795–1801 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yacine Djemaiel
    • 1
    Email author
  • Nadia Labidi
    • 1
  • Noureddine Boudriga
    • 1
  1. 1.Communication Networks and Security Research Lab, Sup’ComUniversity of CarthageTunisTunisia

Personalised recommendations