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