Weighted SVMBoost based Hybrid Rule Extraction Methods for Software Defect Prediction

Related Work

Researchers used different analysis techniques ranging from Statistics to Machine Learning (Nam, 2014) (Kamei & Shihab, 2016) for effective prediction models. Recently, Li et al., categorized the recent SDP efforts in to machine learning-based prediction algorithms, methods to manipulating the data and mechanisms for effort-aware prediction (Li, Jing, & Zhu, 2018). Nagappan and Ball applied (Nagappan & Ball, 2005) PREfast and PREfix statistical analysis tools for predicting defects and reported 82.91% accuracy of the model. From the studies, which adopted machine learning techniques, Naive Bayes (Menzies, Greenwald, & Frank, 2007) reported 71% accuracy, a Bayesian network of Metrics and Defect Proneness (Okutan et al., 2014) reported 72.5% average accuracy. The Support Vector Machines (Gray et al., 2009) as base learners achieved 80% accuracy. From the combined models of Support Vector Machines (SVM) and Probabilistic Neural Network (PNN) (Al-Jamimi & Ghouti, 2011) reported 87.62% accuracy. Neural Network (NN), Decision Tree (DT), PART, Logistic Regression (LR) and Ada Boost (Arisholm, Briand, & Johannessen, 2010) and achieved 75.6% average Accuracy.