Less is More: Temporal Fault Predictive Performance over Multiple Hadoop Releases

  • Mark Harman
  • Syed Islam
  • Yue Jia
  • Leandro L. Minku
  • Federica Sarro
  • Komsan Srivisut
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8636)


We investigate search based fault prediction over time based on 8 consecutive Hadoop versions, aiming to analyse the impact of chronology on fault prediction performance. Our results confound the assumption, implicit in previous work, that additional information from historical versions improves prediction; though G-mean tends to improve, Recall can be reduced.


Support Vector Machine Fault Prediction Radial Basis Function Random Guessing Fault Prediction Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Afzal, W., Torkar, R.: On the application of genetic programming for software engineering predictive modeling: A systematic review. Expert Systems Applications 38(9), 11984–11997 (2011)CrossRefGoogle Scholar
  2. 2.
    Arcuri, A., Briand, L.: A practical guide for using statistical tests to assess randomized algorithms in software engineering. In: ICSE, pp. 1–10 (2011)Google Scholar
  3. 3.
    Bouktif, S., Sahraoui, H., Antoniol, G.: Simulated annealing for improving software quality prediction. In: GECCO, vol. 2, pp. 1893–1900 (2006)Google Scholar
  4. 4.
    Chidamber, S.R., Kemerer, C.F.: A metrics suite for object oriented design. IEEE TSE 20(6), 476–493 (1994)Google Scholar
  5. 5.
    Di Martino, S., Ferrucci, F., Gravino, C., Sarro, F.: A genetic algorithm to configure support vector machines for predicting fault-prone components. In: Caivano, D., Oivo, M., Baldassarre, M.T., Visaggio, G. (eds.) PROFES 2011. LNCS, vol. 6759, pp. 247–261. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Elish, K.O., Elish, M.O.: Predicting defect-prone software modules using support vector machines. JSS 81(5), 649–660 (2008)Google Scholar
  7. 7.
    Ferrucci, F., Harman, M., Sarro, F.: Search based software project management. In: Ruhe, G., Wohlin, C. (eds.) Software Project Management in a Changing World, Springer (to appear, 2014)Google Scholar
  8. 8.
    Gondra, I.: Applying machine learning to software fault-proneness prediction. JSS 81(2), 186–195 (2008)Google Scholar
  9. 9.
    Hall, T., Beecham, S., Bowes, D., Gray, D., Counsell, S.: A systematic literature review on fault prediction performance in software engineering. IEEE TSE 38(6), 1276–1304 (2012)Google Scholar
  10. 10.
    Harman, M.: How SBSE can support construction and analysis of predictive models (keynote). In: PROMISE (2010)Google Scholar
  11. 11.
    Harman, M., Burke, E., Clark, J.A., Yao, X.: Dynamic adaptive search based software engineering. In: ESEM, pp. 1–8 (2012)Google Scholar
  12. 12.
    Harman, M., McMinn, P., de Souza, J.T., Yoo, S.: Search based software engineering: Techniques, taxonomy, tutorial. In: Meyer, B., Nordio, M. (eds.) LASER Summer School 2008-2010. LNCS, vol. 7007, pp. 1–59. Springer, Heidelberg (2012)Google Scholar
  13. 13.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE TKDE 21(9), 1263–1284 (2009)Google Scholar
  14. 14.
    Krogmann, K., Kuperberg, M., Reussner, R.: Using genetic search for reverse engineering of parametric behaviour models for performance prediction. IEEE TSE 36(6), 865–877 (2010)Google Scholar
  15. 15.
    Minku, L., Yao, X.: Can cross-company data improve performance in software effort estimation? In: PROMISE, pp. 69–78 (2012)Google Scholar
  16. 16.
    Minku, L., Yao, X.: How to make best use of cross-company data in software effort estimation? In: ICSE, pp. 446–456 (2014)Google Scholar
  17. 17.
    Ostrand, T.J., Weyuker, E.J.: How to measure success of fault prediction models. In: SOQUA 2007, pp. 25–30. ACM (2007)Google Scholar
  18. 18.
    Rodríguez, D., Ruiz, R., Riquelme, J.C., Harrison, R.: Subgroup discovery for defect prediction. In: Cohen, M.B., Ó Cinnéide, M. (eds.) SSBSE 2011. LNCS, vol. 6956, pp. 269–270. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  19. 19.
    Sarro, F., Di Martino, S., Ferrucci, F., Gravino, C.: A further analysis on the use of genetic algorithm to configure support vector machines for inter-release fault prediction. In: ACM-SAC, pp. 1215–1220 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Mark Harman
    • 1
  • Syed Islam
    • 1
  • Yue Jia
    • 1
  • Leandro L. Minku
    • 2
  • Federica Sarro
    • 1
  • Komsan Srivisut
    • 3
  1. 1.CRESTUniversity College LondonUK
  2. 2.CERCIAUniversity of BirminghamUK
  3. 3.Department of Computer ScienceUniversity of YorkUK

Personalised recommendations