The influence of machine learning on the predictive performance of cross-project defect prediction: empirical analysis

• Main Authors: Bala, Yahaya Zakariyau, Samat, Pathiah Abdul, Sharif, Khaironi Yatim, Manshor, Noridayu
• 格式: Article
• 語言: English
• 出版: Universitas Ahmad Dahlan 2024
• 在線閱讀: http://psasir.upm.edu.my/id/eprint/113069/1/113069.pdf; http://psasir.upm.edu.my/id/eprint/113069/; https://telkomnika.uad.ac.id/index.php/TELKOMNIKA/article/view/25916

This empirical investigation delves into the influence of machine learning (ML) algorithms in the realm of cross-project defect prediction, employing the AEEEEM dataset as a foundation. The primary objective is to discern the nuanced influences of various algorithms on predictive performance, with a specific focus on the F1 score metric as evaluation criterion. Four ML algorithms have been carefully assessed in this study: random forest (RF), support vector machines (SVM), k-nearest neighbors (KNN), and logistic regression (LR). The choice of these algorithms reflects their prevalence in software defect prediction literature and their diversity. Through rigorous experimentation and analysis, the investigation unveils compelling evidence affirming the superiority of RF over its counterparts. The F1 score utilized as evaluation metric, capturing the delicate balance between precision and recall, essential in defect prediction scenarios. The nuanced examination of algorithmic efficacy provides practical insights for developers and practitioners navigating the challenges of cross-project defect prediction. By leveraging the rich and diverse AEEEEM dataset, this study ensures a comprehensive exploration of algorithmic influences across varied software projects. The findings not only contribute to the academic discourse on defect prediction but also offer practical guidance for real-world application, emphasizing the pivotal role of RF as a tool in enhancing predictive accuracy and reliability.