Cover Image

Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning

Deep Q-Network (DQN) is a popular deep reinforcement learning algorithm that has demonstrated promising results across a variety of domains. DQN presents a promising solution to the challenge of lowering false positives in software defect prediction, thereby enhancing the reliability of the predicti...

Full description

Saved in:
Bibliographic Details
Main Authors: Ismail, Ahmad Muhaimin, Ab Hamid, Siti Hafizah, Sani, Asmiza Abdul, Daud, Nur Nasuha Mohd
Format: Article
Published: Institute of Electrical and Electronics Engineers 2024
Subjects:
QA75 Electronic computers. Computer science
QA76 Computer software
Online Access:http://eprints.um.edu.my/45862/
https://doi.org/10.1109/ACCESS.2024.3382991
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.45862
record_format eprints
spelling my.um.eprints.458622024-11-13T04:38:08Z http://eprints.um.edu.my/45862/ Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning Ismail, Ahmad Muhaimin Ab Hamid, Siti Hafizah Sani, Asmiza Abdul Daud, Nur Nasuha Mohd QA75 Electronic computers. Computer science QA76 Computer software Deep Q-Network (DQN) is a popular deep reinforcement learning algorithm that has demonstrated promising results across a variety of domains. DQN presents a promising solution to the challenge of lowering false positives in software defect prediction, thereby enhancing the reliability of the prediction performance. In software defect prediction, false positives occur when the prediction model incorrectly predicts code changes to be defective. Consequently, developers waste time and resources on non-existent defects. This paper advocates for employing DQN in software defect prediction, focusing on minimizing false positives and maximizing the prediction performance. Throughout the training phase, the model learns to predict defect-prone following a reward policy aimed at reducing false results. Experimental findings show that the proposed DQN outperforms baseline classifier, improving the prediction accuracy of true defects by up to 27% when using only 20% efforts. The results show that the effectiveness of DQN in tackling false positives, thereby emphasizing the significance of incorporating dynamic reward in predicting software defects. Institute of Electrical and Electronics Engineers 2024 Article PeerReviewed Ismail, Ahmad Muhaimin and Ab Hamid, Siti Hafizah and Sani, Asmiza Abdul and Daud, Nur Nasuha Mohd (2024) Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning. IEEE Access, 12. pp. 47568-47580. ISSN 2169-3536, DOI https://doi.org/10.1109/ACCESS.2024.3382991 <https://doi.org/10.1109/ACCESS.2024.3382991>. https://doi.org/10.1109/ACCESS.2024.3382991 10.1109/ACCESS.2024.3382991
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QA75 Electronic computers. Computer science
QA76 Computer software
spellingShingle QA75 Electronic computers. Computer science
QA76 Computer software
Ismail, Ahmad Muhaimin
Ab Hamid, Siti Hafizah
Sani, Asmiza Abdul
Daud, Nur Nasuha Mohd
Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
description Deep Q-Network (DQN) is a popular deep reinforcement learning algorithm that has demonstrated promising results across a variety of domains. DQN presents a promising solution to the challenge of lowering false positives in software defect prediction, thereby enhancing the reliability of the prediction performance. In software defect prediction, false positives occur when the prediction model incorrectly predicts code changes to be defective. Consequently, developers waste time and resources on non-existent defects. This paper advocates for employing DQN in software defect prediction, focusing on minimizing false positives and maximizing the prediction performance. Throughout the training phase, the model learns to predict defect-prone following a reward policy aimed at reducing false results. Experimental findings show that the proposed DQN outperforms baseline classifier, improving the prediction accuracy of true defects by up to 27% when using only 20% efforts. The results show that the effectiveness of DQN in tackling false positives, thereby emphasizing the significance of incorporating dynamic reward in predicting software defects.
format Article
author Ismail, Ahmad Muhaimin
Ab Hamid, Siti Hafizah
Sani, Asmiza Abdul
Daud, Nur Nasuha Mohd
author_facet Ismail, Ahmad Muhaimin
Ab Hamid, Siti Hafizah
Sani, Asmiza Abdul
Daud, Nur Nasuha Mohd
author_sort Ismail, Ahmad Muhaimin
title Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
title_short Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
title_full Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
title_fullStr Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
title_full_unstemmed Toward Reduction in False Positives Just-In-Time Software Defect Prediction Using Deep Reinforcement Learning
title_sort toward reduction in false positives just-in-time software defect prediction using deep reinforcement learning
publisher Institute of Electrical and Electronics Engineers
publishDate 2024
url http://eprints.um.edu.my/45862/
https://doi.org/10.1109/ACCESS.2024.3382991
_version_ 1816130468368613376
score 13.214268

Similar Items