On the Use of Machine Learning for Predicting Defect Fix Time Violations

Ümit Kanoğlu, Ümit Kanoğlu, Can Dolaş, Can Dolaş, Hasan Sözer

2022

Abstract

Accurate prediction of defect fix time is important for estimating and coordinating software maintenance efforts. Likewise, it is useful to predict whether or not the initially estimated defect fix time will be exceeded during the maintenance process. We present an empirical evaluation on the use of machine learning for predicting defect fix time violations. We conduct an industrial case study based on real projects from the telecommunications domain. We prepare a dataset with 69,000 defect reports regarding 293 projects being maintained between 2015 and 2021. We employ 7 machine learning algorithms. We experiment with 3 subsets of 25 features derived from defects as well as the corresponding projects. Gradient boosted classifiers perform the best by reaching up to 72% accuracy.

Paper Citation

in Harvard Style

Kanoğlu Ü., Dolaş C. and Sözer H. (2022). On the Use of Machine Learning for Predicting Defect Fix Time Violations. In Proceedings of the 17th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE, ISBN 978-989-758-568-5, pages 119-127. DOI: 10.5220/0011059900003176

in Bibtex Style

@conference{enase22,
author={Ümit Kanoğlu and Can Dolaş and Hasan Sözer},
title={On the Use of Machine Learning for Predicting Defect Fix Time Violations},
booktitle={Proceedings of the 17th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,},
year={2022},
pages={119-127},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011059900003176},
isbn={978-989-758-568-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,
TI - On the Use of Machine Learning for Predicting Defect Fix Time Violations
SN - 978-989-758-568-5
AU - Kanoğlu Ü.
AU - Dolaş C.
AU - Sözer H.
PY - 2022
SP - 119
EP - 127
DO - 10.5220/0011059900003176