Defect Prediction in Software Repositories with Artificial Neural Networks

  • Ana M. BautistaEmail author
  • Tomas San Feliu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 405)


One of the biggest challenges that software developers face it is to make an accurate defect prediction. Radial basis function neural networks have been used to defect prediction. Software repositories like GitHub repository have been mined to get data about projects and their issues. The number of closed issues could be a useful tool for software managers. In order to predict the number of closed issues in a project, different neural networks have been implemented. The dataset has been segmented by the criterion of project size. The designed neural networks have obtained high correlation coefficients.


Data mining Software repositories Artificial neural networks Defect prediction 



This work is sponsored by everis Aeroespacial y Defensa, and the Universidad Politecnica de Madrid through the Research Chair of Software Process Improvement for Spain and Latin American Region.


  1. 1.
    Bissyande, T.F., et al.: Got issues? Who cares about it? A large scale investigation of issue trackers from github. In: 2013 IEEE 24th International Symposium on Software Reliability Engineering (ISSRE), pp. 188–197. IEEE (2013)Google Scholar
  2. 2.
    Rana, R.: Software defect prediction techniques in automotive domain: evaluation, selection and adoption. Doctoral dissertation, University of Gothenburg (2015)Google Scholar
  3. 3.
    Menzies, T., Greenwald, J., Frank, A.: Data mining static code attributes to learn defect predictors. IEEE Trans. Softw. Eng. 33(1), 2–13 (2007)CrossRefGoogle Scholar
  4. 4.
    Gondra, I.: Applying machine learning to software fault-proneness prediction. J. Syst. Softw. 81(2), 186–195 (2008)CrossRefGoogle Scholar
  5. 5.
    Fenton, N., Neil, M., Marsh, W., Hearty, P., Radliński, Ł., Krause, P.: On the effectiveness of early life cycle defect prediction with Bayesian Nets. Empir. Softw. Eng. 13(5), 499–537 (2008)CrossRefGoogle Scholar
  6. 6.
    Gareth, J., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning. Springer, New York (2013)zbMATHGoogle Scholar
  7. 7.
    Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of Machine Learning. MIT Press, Cambridge (2012)Google Scholar
  8. 8.
    Broomhead, D.S., Lowe, D. Radial basis functions, multi-variable functional interpolation and adaptative networks. (No. RSRE-MEMO 4148) Royal Signals and radar Establishment Malvern, UK(1988)Google Scholar
  9. 9.
    Bautista, A.M., Castellanos, A. San Feliu, T.: Software effort estimation using radial basis function neural networks. Inf. Theor. Appl. 319 (2014)Google Scholar
  10. 10.
    Bautista, A.M., San Feliu, T: A process to mining issues of software repositories. In: 2015 10th Iberian Conference on Information Systems and Technologies (CISTI). IEEE (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Lenguajes Y Sistemas Informaticos E Ingenieria Del SoftwareUniversidad Politécnica de MadridMadridSpain

Personalised recommendations