Empirical validation of object-oriented metrics on cross-projects with different severity levels

Abstract

An object-oriented (OO) metrics has become crucial desideratum for software effort and fault predictions. To strengthen the adequacy of object-oriented metrics, it becomes important to know relationship between OO metrics and fault proneness at different levels of severity. It is inconceivable to build model of accurate estimate due to the inherent uncertainty in development projects. Empirical validation of software metrics is essential issue to determine applicability of prediction model. In this study, empirical validation is done on OO metrics given by Chidamber and Kemerer (CK suite) for predicting faults at different severity levels. This paper also instanced on defect prediction using cross-projects (CP) because of the unpredictability in selection of software attributes by analogy-based approach that deliver imprecise and ambiguous solution. This paper depicts detection of fault-proneness by extracting the relevant OO metrics and such models helps to focus on fault-prone modules of new projects by allocating more resources to them with use of regression and other machine learning methods. Combination of CP data with regression techniques improves effectiveness of prediction by extracting similar features impacted by all datasets.