The Adoption of Machine Learning Techniques for Software Defect Prediction: An Initial Industrial Validation

Existing methods for predicting reliability of software are static and need manual maintenance to adjust to the evolving data sets in software organizations. Machine learning has a potential to address the problem of manual maintenance but can also require changes in how companies works with defect prediction. In this paper we address the problem of identifying what the benefits of machine learning are compared to existing methods and which barriers exist for adopting them in practice.

[1]  Andreas Zeller,et al.  Mining metrics to predict component failures , 2006, ICSE.

[2]  Bill C. Hardgrave,et al.  Toward an information systems development acceptance model: the case of object-oriented systems development , 2003, IEEE Trans. Engineering Management.

[3]  Mun Y. Yi,et al.  Predicting the use of web-based information systems: self-efficacy, enjoyment, learning goal orientation, and the technology acceptance model , 2003, Int. J. Hum. Comput. Stud..

[4]  Iker Gondra,et al.  Applying machine learning to software fault-proneness prediction , 2008, J. Syst. Softw..

[5]  I. Ajzen,et al.  Understanding Attitudes and Predicting Social Behavior , 1980 .

[6]  Claes Wohlin,et al.  Experimentation in Software Engineering , 2012, Springer Berlin Heidelberg.

[7]  Ming Li,et al.  A Ranking of Software Engineering Measures Based on Expert Opinion , 2003, IEEE Trans. Software Eng..

[8]  Per Runeson,et al.  Guidelines for conducting and reporting case study research in software engineering , 2009, Empirical Software Engineering.

[9]  Rakesh Rana,et al.  A framework for adoption of machine learning in industry for software defect prediction , 2014, 2014 9th International Conference on Software Engineering and Applications (ICSOFT-EA).

[10]  Fred D. Davis.  A technology acceptance model for empirically testing new end-user information systems : theory and results , 1985 .

[11]  William Marsh,et al.  Predicting software defects in varying development lifecycles using Bayesian nets , 2007, Inf. Softw. Technol..

[12]  Norman E. Fenton,et al.  A Critique of Software Defect Prediction Models , 1999, IEEE Trans. Software Eng..

[13]  Jeffrey J. P. Tsai,et al.  Machine Learning and Software Engineering , 2004, Software Quality Journal.

[14]  Miroslaw Staron,et al.  A method for forecasting defect backlog in large streamline software development projects and its industrial evaluation , 2010, Inf. Softw. Technol..

[15]  A. P. Nikora,et al.  How simple is software defect detection , 2003 .

[16]  Tim Menzies,et al.  Data Mining Static Code Attributes to Learn Defect Predictors , 2007 .

[17]  Detmar W. Straub,et al.  Gender Differences in the Perception and Use of E-Mail: An Extension to the Technology Acceptance Model , 1997, MIS Q..

[18]  William Marsh,et al.  On the effectiveness of early life cycle defect prediction with Bayesian Nets , 2008, Empirical Software Engineering.

[19]  Kar Yan Tam,et al.  Factors Affecting the Adoption of Open Systems: An Exploratory Study , 1997, MIS Q..

[20]  Linda G. Wallace,et al.  The adoption of software measures: A technology acceptance model (TAM) perspective , 2014, Inf. Manag..

[21]  M. Fleischer,et al.  processes of technological innovation , 1990 .