Predicting Issue Resolution Time of OSS Using Multiple Features

Abstract

Developers utilize issue tracking systems to track ideas, feedback, tasks, and bugs for projects in the open-source software ecosystem of GitHub. In this context, extensive bug reports and feature requests are raised as issues that need to be resolved. This makes issue resolution prediction become more and more important in project management. To address this problem, this paper constructed a multiple feature set from the perspectives of project, issue, and developer, by combining static and dynamic features of issues. Then, we refine a feature set based on the feature's importance. Furthermore, we proposed a method to explore what features and how these features affect the prediction of issue resolution time. Experiments are conducted on a dataset of 46,735 resolved issues from 18 popular GitHub projects to validate the effectiveness of the refined feature set. The results show that our prediction method outperforms the baseline methods.