An Empirical Study for Method-Level Refactoring Prediction by Ensemble Technique and SMOTE to Improve Its Efficiency

Abstract

Code refactoring is the modification of structure without altering its functionality. The refactoring task is critical for enhancing the qualities for non-functional attributes, such as efficiency, understandability, reusability, and flexibility. The research aims to build an optimized model for refactoring prediction at the method level with seven ensemble techniques and varieties of SMOTE techniques. This research has considered five open source java projects to investigate the accuracy of the proposed model, which forecasts refactoring applicants by the use of ensemble techniques (BAG-KNN, BAG-DT, BAG-LOGR, ADABST, EXTC, RANF, GRDBST). Data imbalance issues are handled using three sampling techniques (SMOTE, BLSMOTE, SVSMOTE) to improve refactoring prediction efficiency and also focused all features and significant features. The mean accuracy of the classifiers like BAG-DT is 99.53%, RANF is 99.55%, and EXTC is 99.59%. The mean accuracy of the BLSMOTE is 97.21%. The performance of classifiers and sampling techniques are shown in terms of the box-plot diagram.