Can We Predict the Change in Code in a Software Product Line Project?

作     者：Yasser Ali Alshehri Yasser Ali Alshehri

作者机构：Computer Science and Engineering Department Yanbu University College Royal Commission Yanbu Saudi Arabia 

出 版 物：《Journal of Software Engineering and Applications》 (软件工程与应用（英文）)

年 卷 期：2020年第13卷第6期

页      面：91-103页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Software Change Proneness Software Quality Machine Learning Decision Tree J48 Logistic Regression Naïve Bayes Random Forest Data Mining 

摘      要：Software programs are always prone to change for several reasons. In a software product line, the change is more often as many software units are carried from one release to another. Also, other new files are added to the reused files. In this work, we explore the possibility of building a model that can predict files with a high chance of experiencing the change from one release to another. Knowing the files that are likely to face a change is vital because it will help to improve the planning, managing resources, and reducing the cost. This also helps to improve the software process, which should lead to better software quality. Also, we explore how different learners perform in this context, and if the learning improves as the software evolved. Predicting change from a release to the next release was successful using logistic regression, J48, and random forest with accuracy and precision scored between 72% to 100%, recall scored between 74% to 100%, and F-score scored between 80% to 100%. We also found that there was no clear evidence regarding if the prediction performance will ever improve as the project evolved.