Cascade Generalization-based Classifiers for Software Defect Prediction

TL;DR

This paper introduces a cascade generalization approach to improve machine learning models for software defect prediction, significantly enhancing accuracy and AUC over baseline and ensemble methods.

Contribution

It proposes a novel cascade generalization technique that extends sample space to boost predictive performance of ML-based SDP models.

Findings

CG-based models outperform baseline models in accuracy and AUC.

CG-NB shows +11.06% accuracy improvement.

CG-DT and CG-kNN show +3.91% and +5.14% accuracy improvements.

Abstract

The process of software defect prediction (SDP) involves predicting which software system modules or components pose the highest risk of being defective. The projections and discernments derived from SDP can then assist the software development team in effectively allocating its finite resources toward potentially susceptible defective modules. Because of this, SDP models need to be improved and refined continuously. Hence, this research proposes the deployment of a cascade generalization (CG) function to enhance the predictive performances of machine learning (ML)-based SDP models. The CG function extends the initial sample space by introducing new samples into the neighbourhood of the distribution function generated by the base classification algorithm, subsequently mitigating its bias. Experiments were conducted to investigate the effectiveness of CG-based Na\"ive Bayes (NB), Decision Tree (DT), and k-Nearest Neighbor (kNN) models on NASA software defect datasets. Based on the experimental results, the CG-based models (CG-NB, CG-DT, CG-kNN) were superior in prediction performance when compared with the baseline NB, DT, and kNN models respectively. Accordingly, the average accuracy value of CG-NB, CG-DT, and CG-kNN models increased by +11.06%, +3.91%, and +5.14%, respectively, over baseline NB, DT, and kNN models. A similar performance was observed for the area under the curve (AUC) value with CG-NB, CG-DT, and CG-kNN recording an average AUC value of +7.98%, +26%, and +24.9% improvement over the baseline NB, DT, and kNN respectively. In addition, the suggested CG-based models outperformed the Bagging and Boosting ensemble variants of the NB, DT, and kNN models as well as existing computationally diverse SDP models.