Assessing software defection prediction performance
Jingxiu Yao, Martin Shepperd
Abstract
Context: There is considerable diversity in the range and design of computational experiments to assess classifiers for software defect prediction. This is particularly so, regarding the choice of classifier performance metrics. Unfortunately some widely used metrics are known to be biased, in particular F1.
Topics & Concepts
Pairwise comparisonComputer scienceMetric (unit)Classifier (UML)Software metricMachine learningSoftwareSoftware bugArtificial intelligenceCorrelationData miningContext (archaeology)Software qualitySoftware developmentMathematicsEngineeringOperations managementGeometryProgramming languagePaleontologyBiologySoftware Engineering ResearchSoftware Reliability and Analysis ResearchImbalanced Data Classification Techniques