Akademik Veri Yönetim Sistemi
Materials Today: Proceedings, cilt.81, ss.18-25, 2023 (Scopus)
© 2022Software quality prediction is used at various stages of projects. There are several metrics that provide the quality measure with respect to different types of software. In this study, defect density is used as the feature that represents the quality. The aim of this study is to predict software quality with higher accuracy than previous studies. The study shows that data pre-processing, feature extraction and machine learning algorithms provide more accurate results in predicting the quality of the software. Algorithms were applied on three datasets that include software metrics. The obtained accuracy values were compared with the existing ones in the literature. Ensemble methods, which enable the use of different machine learning algorithms together, contributed to obtaining results with higher accuracy rates in software quality prediction. In EBSPM dataset, logistic regression produced the best accuracy value as 96.67%. On the other hand, in ISBSG dataset and in PROMISE dataset, the ensemble methods Soft Voting & Stacking and Gradient Boosting & Bagging generated the best results respectively with the values 96.31% and 94.59%.