{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T11:35:12Z","timestamp":1781264112650,"version":"3.54.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>Predicting bug fix times is a key objective for improving software maintenance and supporting planning in open source projects. In this study, we evaluate the effectiveness of different time series forecasting models applied to real-world data from multiple repositories, comparing local (one model per project) and global (a single model trained across multiple projects) approaches. We considered classical models (Naive, Linear Regression, Random Forest) and neural networks (MLP, LSTM, GRU), with global extensions including Random Forest and LSTM with project embeddings. The results highlight that, at the local level, Random Forest achieves lower errors and better classification metrics than deep learning models in several cases. However, global models show greater robustness and generalizability: in particular, the global Random Forest significantly reduces the mean error and maintains high performance in terms of accuracy and F1 score, while the global LSTM captures temporal dependencies and provides additional insights into cross-project dynamics. The explainable AI techniques adopted (permutation importance, saliency maps, and embedding analysis) allow us to interpret the main drivers of forecasts, confirming the role of process variables and temporal characteristics. Overall, the study demonstrates that an integrated approach, combining classical models and deep learning in a global perspective, offers more reliable and interpretable forecasts to support software maintenance.<\/jats:p>","DOI":"10.3389\/fdata.2025.1745751","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T05:18:06Z","timestamp":1766121486000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Time series forecasting for bug resolution using machine learning and deep learning models"],"prefix":"10.3389","volume":"8","author":[{"given":"Lerina","family":"Aversano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martina","family":"Iammarino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonella","family":"Madau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiano","family":"Pecorelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"112896","DOI":"10.1016\/j.eswa.2019.112896","article-title":"Forecasting across time series databases using recurrent neural networks on groups of similar series: a clustering approach","volume":"140","author":"Bandara","year":"2020","journal-title":"Expert Syst. Appl"},{"key":"B2","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1145\/1985441.1985472","article-title":"\u201cBug-fix time prediction models: can we do better?,\u201d","volume-title":"Proceedings of the 8th Working Conference on Mining Software Repositories (MSR)","author":"Bhattacharya","year":"2011"},{"key":"B3","doi-asserted-by":"publisher","first-page":"120597","DOI":"10.1016\/j.eswa.2023.120597","article-title":"A community detection approach based on network representation learning for repository mining","volume":"231","author":"De Luca","year":"2023","journal-title":"Expert Syst. Appl"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1210559","DOI":"10.3389\/fdata.2023.1210559","article-title":"Benchmarking open source and paid services for speech to text: an analysis of quality and input variety","volume":"6","author":"Ferraro","year":"2023","journal-title":"Front. Big Data"},{"key":"B5","first-page":"789","article-title":"\u201cRevisiting the impact of classification techniques on the performance of defect prediction models,\u201d","volume-title":"Proceedings of the 37th International Conference on Software Engineering (ICSE)","author":"Ghotra","year":"2015"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/a17050175","article-title":"Cross-project defect prediction using optimal transport for domain adaptation","volume":"31","author":"Javed","year":"2024","journal-title":"Autom. Softw. Eng"},{"key":"B8","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/s10462-025-11223-9","article-title":"A comprehensive survey of deep learning for time series","volume":"58","author":"Kim","year":"2025","journal-title":"Artif. Intell. Rev"},{"key":"B9","doi-asserted-by":"publisher","first-page":"20200209","DOI":"10.1098\/rsta.2020.0209","article-title":"Time-series forecasting with deep learning: a survey","volume":"379","author":"Lim","year":"2021","journal-title":"Philos. Trans. R. Soc. A"},{"key":"B10","doi-asserted-by":"publisher","first-page":"223","DOI":"10.3390\/math12101504","article-title":"Deep learning for time series forecasting: a survey","volume":"12","author":"Liu","year":"2024","journal-title":"Mathematics"},{"key":"B11","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.ijforecast.2019.04.014","article-title":"The m4 competition: 100,000 time series and 61 forecasting methods","volume":"36","author":"Makridakis","year":"2020","journal-title":"Int. J. Forecast"},{"key":"B12","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.ijforecast.2019.02.011","article-title":"Forecasting with model combinations and reconciled forecasts","volume":"36","author":"Montero-Manso","year":"2020","journal-title":"Int. J. Forecast"},{"key":"B13","doi-asserted-by":"publisher","first-page":"195","DOI":"10.48550\/arXiv.2505.01108","article-title":"Interpretable prediction of issue resolution time","volume":"36","author":"Nastos","year":"","journal-title":"Inf. Softw. Technol"},{"key":"B14","article-title":"Towards an interpretable analysis for estimating the time of resolution of software issues","author":"Nastos","year":"","journal-title":"arXiv [preprint]"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1032440","DOI":"10.3389\/fcomp.2023.1032440","article-title":"Deep learning and gradient-based extraction of bug report features","volume":"5","author":"Noyori","year":"2023","journal-title":"Front. Comput. Sci"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21241","article-title":"Bug analysis towards bug resolution time prediction","author":"Ozkan","year":"2024","journal-title":"arXiv [preprint]"},{"key":"B17","first-page":"654","article-title":"\u201cPredicting issue resolution time with machine learning: an industrial case study,\u201d","author":"Ozkan","year":"2024","journal-title":"Proceedings of the 30th International Conference on Software Analysis, Evolution and Reengineering (SANER)"},{"key":"B18","unstructured":"Patil\n              A.\n            \n          \n          GitBugs: Bug Reports From Some Popular Open Source Projects [Data set]"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.09651","article-title":"GitBugs: Bug reports for duplicate detection, retrieval augmented generation, triage, and more","author":"Patil","year":"","journal-title":"arXiv preprint"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.01234","article-title":"Gitbugs: a benchmark dataset for bug report analysis","author":"Patil","year":"2025","journal-title":"arXiv [preprint]"},{"key":"B21","author":"Pressman","year":"2010","journal-title":"Software Engineering: A Practitioner's Approach"},{"key":"B22","doi-asserted-by":"publisher","first-page":"341","DOI":"10.62527\/joiv.8.2.2305","article-title":"Performance evaluation on resolution time prediction using machine learning","volume":"6","author":"Raharja","year":"2023","journal-title":"J. Inf. Vocat. Educ"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.00950","article-title":"Explainable artificial intelligence (XAI) on time series data: a survey","author":"Rojat","year":"2021","journal-title":"arXiv [preprint]"},{"key":"B24","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/s10664-008-9103-7","article-title":"On the relative value of cross-company and within-company data for defect prediction","volume":"14","author":"Turhan","year":"2009","journal-title":"Empir. Softw. Eng"},{"key":"B25","first-page":"1","article-title":"Feddpi: federated cross-project defect prediction with knowledge transfer","volume":"29","author":"Wang","year":"2024","journal-title":"Empir. Softw. Eng"},{"key":"B26","first-page":"181","article-title":"\u201cOn the use of machine learning for predicting defect fix time,\u201d","volume-title":"Proceedings of the 14th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE)","author":"Weiss","year":"2022"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1109\/ICSE.2013.6606654","author":"Zhang","year":"2013"},{"key":"B28","first-page":"91","article-title":"\u201cCross-project defect prediction: a large scale experiment on data vs. domain vs. process,\u201d","volume-title":"Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering (ESEC\/FSE)","author":"Zimmermann","year":"2009"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1745751\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T05:18:09Z","timestamp":1766121489000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1745751\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":28,"alternative-id":["10.3389\/fdata.2025.1745751"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2025.1745751","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"article-number":"1745751"}}