Using the Random Tree Classifier to Improve the Project’s Cost Predictability in the Earned Value Management: An Empirical Study

  • Ana C. da S. Fernandes
  • Adler Diniz de Souza
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 800)


This paper proposes the selection of historical cost performance data of processes using the Random Tree classifier and the application of the calculation proposed by [20], to improve the predictability of projects cost. The proposed technique was evaluated through an empirical study, which evaluated the implementation of the proposed technique in 23 software development projects. The proposed technique has been applied in real projects with the aim of evaluating the accuracy and variation of the CPIAccum and consequently the EAC. Then it was compared to the EVM traditional technique. Hypotheses tests with 95% significance level were performed, and the proposed technique was more accurate and more stable (less variation) than the traditional technique for calculating the Cost Performance Index – CPI.


Earned value management Cost performance index – CPI Random tree Measurement and analysis High maturity 


  1. 1.
    Anbari, F.T.: (2003) Earned value project management method and extensions. Project Manag. J. 34(4), 12–23 (2003)CrossRefGoogle Scholar
  2. 2.
    Boehm, B.W., Madachy, A.C., Brown, A.W., Chulani, S., Bradford, K.C., Horowitz, E., Madachy, R., Reifer, D.J., Steece, B.: Software Cost Estimation with COCOMO II, 1st edn. Prentice Hall, New Jersey (2000)Google Scholar
  3. 3.
    Christensen, D.S., Heise. S.R.: Cost performance index stability. Natl. Contract Manag. J. 25(1), 7 (1992)Google Scholar
  4. 4.
    de Souza, A.D.: Uma proposta para melhoria da previsibilidade de custo de projetos, utilizando a técnica de gerenciamento de valor agregado e dados históricos de custo e qualidade. Ph.D. Dissertation. Universidade Federal do Rio de Janeiro (2014)Google Scholar
  5. 5.
    de Souza, A.D., Rocha, A.R.C.: A proposal for the improvement predictability of cost using earned value management and quality data. In: European Conference on Software Process Improvement. Springer, pp. 190–201 (2013)Google Scholar
  6. 6.
    Fenton, N., Marsh, W., Neil, M., Cates, P., Forey, S., Tailor, M.: Making resource decisions for software projects. In: 26th International Conference on Software Engineering, ICSE 2004. Proceedings. IEEE, pp. 397–406 (2004)Google Scholar
  7. 7.
    Henderson, K., Zwikael, O.: Does project performance stability exist? A re-examination of CPI and evaluation of SPI(t) stability. Crosstalk. 21, 1–13 (2008)Google Scholar
  8. 8.
    Lipke, W.: Statistical methods applied to EVM…the next frontier. Meas. News 19, 18–30 (2006)Google Scholar
  9. 9.
    Lipke, W., Zwikael, O., Henderson, K., Anbari, F.: Prediction of project outcome: the application of statistical methods to earned value management and earned schedule performance indexes. Int. J. Proj. Manag. 27(4), 400–407 (2009)CrossRefGoogle Scholar
  10. 10.
    Sei, S.E.I.: CMMI® for Development (CMMIDEV), V1. 2, CMU/SEI-2006-TR-008. Software Engineering Institute (2006)Google Scholar
  11. 11.
    Smith, J.: The Estimation of Effort Based on Use Cases, Rational Software, Cupertino, TP-171 (1999)Google Scholar
  12. 12.
    Souza, A.D., Rocha, A.R.C.: A proposal for the improvement the predictability of project cost using EVM and Historical Data of Cost. In: 35th International Conference of Software Engineering-ICSE. ACM SRC, San Francisco. Accepted Feb 2013Google Scholar
  13. 13.
    Zwikael, O., Globerson, S., Raz, T.: Evaluation of models for forecasting the final cost of a project. Project Manag. J. 31(1), 53–57 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ana C. da S. Fernandes
    • 1
  • Adler Diniz de Souza
    • 1
  1. 1.Universidade Federal de ItajubaItajubaBrazil

Personalised recommendations