Skip to main content
placeholder image

Predicting the delay of issues with due dates in software projects

Journal Article


Abstract


  • Issue-tracking systems (e.g. JIRA) have increasingly been used in many software projects. An issue could represent a software bug, a new requirement or a user story, or even a project task. A deadline can be imposed on an issue by either explicitly assigning a due date to it, or implicitly assigning it to a release and having it inherit the release┬┐s deadline. This paper presents a novel approach to providing automated support for project managers and other decision makers in predicting whether an issue is at risk of being delayed against its deadline. A set of features (hereafter called risk factors) characterizing delayed issues were extracted from eight open source projects: Apache, Duraspace, Java.net, JBoss, JIRA, Moodle, Mulesoft, and WSO2. Risk factors with good discriminative power were selected to build predictive models to predict if the resolution of an issue will be at risk of being delayed. Our predictive models are able to predict both the the extend of the delay and the likelihood of the delay occurrence. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 79 % precision, 61 % recall, 68 % F-measure, and 83 % Area Under the ROC Curve. Our predictive models also have low error rates: on average 0.66 for Macro-averaged Mean Cost-Error and 0.72 Macro-averaged Mean Absolute Error.

UOW Authors


  •   Choetkiertikul, Morakot (external author)
  •   Dam, Hoa
  •   Tran, Truyen (external author)
  •   Ghose, Aditya

Publication Date


  • 2017

Citation


  • Choetkiertikul, M., Dam, H. Khanh., Tran, T. & Ghose, A. (2017). Predicting the delay of issues with due dates in software projects. Empirical Software Engineering, 1-41.

Scopus Eid


  • 2-s2.0-85009932087

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/6518

Has Global Citation Frequency


Number Of Pages


  • 40

Start Page


  • 1

End Page


  • 41

Place Of Publication


  • United States

Abstract


  • Issue-tracking systems (e.g. JIRA) have increasingly been used in many software projects. An issue could represent a software bug, a new requirement or a user story, or even a project task. A deadline can be imposed on an issue by either explicitly assigning a due date to it, or implicitly assigning it to a release and having it inherit the release┬┐s deadline. This paper presents a novel approach to providing automated support for project managers and other decision makers in predicting whether an issue is at risk of being delayed against its deadline. A set of features (hereafter called risk factors) characterizing delayed issues were extracted from eight open source projects: Apache, Duraspace, Java.net, JBoss, JIRA, Moodle, Mulesoft, and WSO2. Risk factors with good discriminative power were selected to build predictive models to predict if the resolution of an issue will be at risk of being delayed. Our predictive models are able to predict both the the extend of the delay and the likelihood of the delay occurrence. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 79 % precision, 61 % recall, 68 % F-measure, and 83 % Area Under the ROC Curve. Our predictive models also have low error rates: on average 0.66 for Macro-averaged Mean Cost-Error and 0.72 Macro-averaged Mean Absolute Error.

UOW Authors


  •   Choetkiertikul, Morakot (external author)
  •   Dam, Hoa
  •   Tran, Truyen (external author)
  •   Ghose, Aditya

Publication Date


  • 2017

Citation


  • Choetkiertikul, M., Dam, H. Khanh., Tran, T. & Ghose, A. (2017). Predicting the delay of issues with due dates in software projects. Empirical Software Engineering, 1-41.

Scopus Eid


  • 2-s2.0-85009932087

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/6518

Has Global Citation Frequency


Number Of Pages


  • 40

Start Page


  • 1

End Page


  • 41

Place Of Publication


  • United States