Improvement of the Fault-prone class prediction precision by the process metrics use
Nobuko Koketsu, Jyunichi Nomura, Naomi Honda, Makoto Nonaka, Shinya Kawamura · 2011
The general purpose of our study is to introduce a more precise and effective quality assurance practice into our software development organization that has been applying quality assurance activities mainly focusing on process metrics. The fault-prone (FP) module prediction technique is one of promising techniques that meets our goal. In this paper, we explain our attempt to build several FP class prediction models to predict defects that would be detected in a functional testing phase by using our actual product development data. We also discuss practical consideration of how to apply the FP technique to a testing phase in practice to stabilize software quality earlier than before.