Software defect prediction using wrapper-based dynamic arithmetic optimization for feature selection

Software Defect Prediction (SDP) empowers the creators to diagnose and unscramble defects in the introductory legs of the software evolution process to reduce the effort and cost invested in creating high-quality software. Feature Selection (FS) is critical to pinpoint the most pertinent features for defect prediction. This paper intends to employ a peculiar wrapper-based FS mode, dubbed DAOAFS, rooted on the dynamic arithmetic optimization algorithm (DAOA). Subsequently, this work evaluates the competence of the proposed FS mode using ten benchmark NASA datasets on four supervised learning classifiers, namely NB, DT, SVM, and KNN using accuracy and error curve as the standard performance measure metrics. This paper also correlates the proposed FS mode's conduct with existing FS techniques based on widely utilized meta-heuristic approaches such as GA, PSO, DE, ACO, FA, and SWO. This work employed Friedman and Holm test to ratify the proposed FS mode's statistical connotation. The investigatory outcomes supported the assertion that the recommended DAOAFS mode was effective in enhancing the efficacy of the defect forecasting model by achieving the highest mean accuracy of 94.76%. The findings also revealed that the proposed approach established its supremacy over the other studied FS techniques with bettered veracity in most instances.