Just-in-time defect prediction for mobile applications: using shallow or deep learning?

<p dir="ltr">Just-in-time defect prediction (JITDP) research is increasingly focused on program changes instead of complete program modules within the context of continuous integration and continuous testing paradigm. Traditional machine learning-based defect prediction models have b...

Full description

Saved in:
Bibliographic Details
Main Author: Raymon van Dinter (10521952) (author)
Other Authors: Cagatay Catal (6897842) (author), Görkem Giray (5291287) (author), Bedir Tekinerdogan (6897839) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513530575716352
author Raymon van Dinter (10521952)
author2 Cagatay Catal (6897842)
Görkem Giray (5291287)
Bedir Tekinerdogan (6897839)
author2_role author
author
author
author_facet Raymon van Dinter (10521952)
Cagatay Catal (6897842)
Görkem Giray (5291287)
Bedir Tekinerdogan (6897839)
author_role author
dc.creator.none.fl_str_mv Raymon van Dinter (10521952)
Cagatay Catal (6897842)
Görkem Giray (5291287)
Bedir Tekinerdogan (6897839)
dc.date.none.fl_str_mv 2023-06-09T03:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s11219-023-09629-1
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Just-in-time_defect_prediction_for_mobile_applications_using_shallow_or_deep_learning_/24997700
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Machine learning
Software engineering
Just-in-time defect prediction
Shallow learning
XGBoost
Deep learning
Imbalanced learning
dc.title.none.fl_str_mv Just-in-time defect prediction for mobile applications: using shallow or deep learning?
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Just-in-time defect prediction (JITDP) research is increasingly focused on program changes instead of complete program modules within the context of continuous integration and continuous testing paradigm. Traditional machine learning-based defect prediction models have been built since the early 2000s, and recently, deep learning-based models have been designed and implemented. While deep learning (DL) algorithms can provide state-of-the-art performance in many application domains, they should be carefully selected and designed for a software engineering problem. In this research, we evaluate the performance of traditional machine learning algorithms and data sampling techniques for JITDP problems and compare the model performance with the performance of a DL-based prediction model. Experimental results demonstrated that DL algorithms leveraging sampling methods perform significantly worse than the decision tree-based ensemble method. The XGBoost-based model appears to be 116 times faster than the multilayer perceptron-based (MLP) prediction model. This study indicates that DL-based models are not always the optimal solution for software defect prediction, and thus, shallow, traditional machine learning can be preferred because of better performance in terms of accuracy and time parameters.</p><h2>Other Information</h2><p dir="ltr">Published in: Software Quality Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11219-023-09629-1" target="_blank">https://dx.doi.org/10.1007/s11219-023-09629-1</a></p>
eu_rights_str_mv openAccess
id Manara2_2cfe3ca87abb93082fd644a05fa4b913
identifier_str_mv 10.1007/s11219-023-09629-1
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24997700
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Just-in-time defect prediction for mobile applications: using shallow or deep learning?Raymon van Dinter (10521952)Cagatay Catal (6897842)Görkem Giray (5291287)Bedir Tekinerdogan (6897839)Information and computing sciencesMachine learningSoftware engineeringJust-in-time defect predictionShallow learningXGBoostDeep learningImbalanced learning<p dir="ltr">Just-in-time defect prediction (JITDP) research is increasingly focused on program changes instead of complete program modules within the context of continuous integration and continuous testing paradigm. Traditional machine learning-based defect prediction models have been built since the early 2000s, and recently, deep learning-based models have been designed and implemented. While deep learning (DL) algorithms can provide state-of-the-art performance in many application domains, they should be carefully selected and designed for a software engineering problem. In this research, we evaluate the performance of traditional machine learning algorithms and data sampling techniques for JITDP problems and compare the model performance with the performance of a DL-based prediction model. Experimental results demonstrated that DL algorithms leveraging sampling methods perform significantly worse than the decision tree-based ensemble method. The XGBoost-based model appears to be 116 times faster than the multilayer perceptron-based (MLP) prediction model. This study indicates that DL-based models are not always the optimal solution for software defect prediction, and thus, shallow, traditional machine learning can be preferred because of better performance in terms of accuracy and time parameters.</p><h2>Other Information</h2><p dir="ltr">Published in: Software Quality Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11219-023-09629-1" target="_blank">https://dx.doi.org/10.1007/s11219-023-09629-1</a></p>2023-06-09T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s11219-023-09629-1https://figshare.com/articles/journal_contribution/Just-in-time_defect_prediction_for_mobile_applications_using_shallow_or_deep_learning_/24997700CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/249977002023-06-09T03:00:00Z
spellingShingle Just-in-time defect prediction for mobile applications: using shallow or deep learning?
Raymon van Dinter (10521952)
Information and computing sciences
Machine learning
Software engineering
Just-in-time defect prediction
Shallow learning
XGBoost
Deep learning
Imbalanced learning
status_str publishedVersion
title Just-in-time defect prediction for mobile applications: using shallow or deep learning?
title_full Just-in-time defect prediction for mobile applications: using shallow or deep learning?
title_fullStr Just-in-time defect prediction for mobile applications: using shallow or deep learning?
title_full_unstemmed Just-in-time defect prediction for mobile applications: using shallow or deep learning?
title_short Just-in-time defect prediction for mobile applications: using shallow or deep learning?
title_sort Just-in-time defect prediction for mobile applications: using shallow or deep learning?
topic Information and computing sciences
Machine learning
Software engineering
Just-in-time defect prediction
Shallow learning
XGBoost
Deep learning
Imbalanced learning