A GA-based feature selection and parameters optimization for support vector regression applied to software effort estimation

ABSTRACT

The precision of the estimation of the effort of software projects is very important for the competitiveness of software companies. Machine learning methods have recently been applied for this task, included methods based on support vector regression (SVR). This paper proposes and investigates the use of a genetic algorithm approach for simultaneously (1) select an optimal feature subset and (2) optimize SVR parameters, aiming to improve the precision of the software effort estimates. We report on experiments carried out using two datasets of software projects. In both datasets, the simulations have shown that the proposed GA-based approach was able to improve substantially the performance of SVR and outperform some recent results reported in the literature.

REFERENCES

• 1: P. L. Braga, A. L. I. Oliveira, G. H. T. Ribeiro, and S. R. L. Meira. Bagging predictors for estimation of software project effort. IEEE International Joint Conference on Neural Networks, IJCNN', 2007.
• 2: Petronio L. Braga , Adriano L. I. Oliveira , Silvio R. L. Meira, Software Effort Estimation Using Machine Learning Techniques with Robust Confidence Intervals, Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Vol.1 (ICTAI 2007), p.181-185, October 29-31, 2007 [doi>10.1109/ICTAI.2007.167]
• 3: C. J. Burgess and M. Lefley. Can genetic programming improve software effort estimation? A comparative evaluation. Information & Software Technology, 43(14):863--873, 2001.
• 4: Corinna Cortes , Vladimir Vapnik, Support-Vector Networks, Machine Learning, v.20 n.3, p.273-297, Sept. 1995 [doi>10.1023/A:1022627411411]
• 5: Andries P. Engelbrecht, Fundamentals of Computational Swarm Intelligence, John Wiley & Sons, 2006
• 6: C.-L. Huang and C.-J. Wang. A ga-based feature selection and parameters optimization for support vector machines. Expert Systems with Applications, 31(2):231--240, 2006.
• 7: Adriano L. I. Oliveira, Letters: Estimation of software project effort with support vector regression, Neurocomputing, v.69 n.13-15, p.1749-1753, August, 2006 [doi>10.1016/j.neucom.2005.12.119]
• 8: Miyoung Shin , Amrit L. Goel, Empirical Data Modeling in Software Engineering Using Radial Basis Functions, IEEE Transactions on Software Engineering, v.26 n.6, p.567-576, June 2000 [doi>10.1109/32.852743]
• 9: Alex J. Smola , Bernhard Schölkopf, A tutorial on support vector regression, Statistics and Computing, v.14 n.3, p.199-222, August 2004 [doi>10.1023/B:STCO.0000035301.49549.88]
• 10: Standish. Project success rates improved over 10 years. Technical report, Standish Group, http//www.softwaremag.com/L.cfm? Doc=newsletter/2004-01-15/Standish, 2004.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search

Additional Classification:
  D. Software
  D.2 SOFTWARE ENGINEERING
      D.2.9 Management

Keywords:
feature selection, genetic algorithm, software effort estimation, support vector regression