COMPARATIVE ANALYSIS OF CLASSIFICATION METHODS FOR PREDICTION SOFTWARE
FAULT PRONENESS USING PROCESS METRICS
Abstract
As we all know a lot of research has been done in the field of software
defect prediction but most of them uses static code metrics as their
independent variable. In this paper the main objective is to analyze the
effect of process metrics on prediction performance using various
classification and ensemble techniques. Also in this i have used both
AUC and MCC measure to analyze the results. We can conclude that process
metrics are as effective as static code metrics.