Software quality prediction and data mining techniques play an important role in the field of software engineering. To the best of our knowledge, despite the high number of publications it is unavailable a comprehensive study about practical aspects of software analytic models. In our study, we aim at providing a methodology to perform software defect prediction in the scientific environment that minimizes human effort. Geant4 and ROOT constitute two valid test cases for this purpose since they play a key role in a wide range of experimental physics applications. Furthermore, they are representative of different software development processes and are open source.
Paper
Full text
Data mining techniques for software quality prediction: a comparative study
Semantic Scholar · Computer Science · 2018
Abstract
Software quality prediction and data mining techniques play an important role in the field of software engineering. To the best of our knowledge, despite the high number of publications it is unavailable a comprehensive study about practical aspects of software analytic models. In our study, we aim at providing a methodology to perform software defect prediction in the scientific environment that minimizes human effort. Geant4 and ROOT constitute two valid test cases for this purpose since they play a key role in a wide range of experimental physics applications. Furthermore, they are representative of different software development processes and are open source.