{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T01:18:08Z","timestamp":1776647888331,"version":"3.51.2"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"11-12","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00500-025-10751-4","type":"journal-article","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T03:39:28Z","timestamp":1753501168000},"page":"4685-4709","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable-AI-assisted feature selection for software change-proneness prediction"],"prefix":"10.1007","volume":"29","author":[{"given":"Ankit","family":"Rajpal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4379-1837","authenticated-orcid":false,"given":"Megha","family":"Khanna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naman","family":"Singhal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"10751_CR1","doi-asserted-by":"crossref","unstructured":"Abbas R, Albalooshi FA, Hammad M. (2020). Software change proneness prediction using machine learning. In 2020 international conference on innovation and intelligence for informatics, computing and technologies (3ICT), pages 1\u20137. IEEE","DOI":"10.1109\/3ICT51146.2020.9311978"},{"key":"10751_CR2","unstructured":"Ali M. (2020). PyCaret: An open source, low-code machine learning library in Python. PyCaret version 1.0"},{"issue":"3","key":"10751_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2023.05.011","volume":"24","author":"Y Al-Smadi","year":"2023","unstructured":"Al-Smadi Y, Eshtay M, Al-Qerem A, Nashwan S, Ouda O, Abd El-Aziz A (2023) Reliable prediction of software defects using Shapley interpretable machine learning models. Egyptian Informatics Journal 24(3):100386","journal-title":"Egyptian Informatics Journal"},{"issue":"10","key":"10751_CR4","doi-asserted-by":"publisher","first-page":"5234","DOI":"10.3390\/app12105234","volume":"12","author":"H Alsolai","year":"2022","unstructured":"Alsolai H, Roper M (2022) The impact of ensemble techniques on software maintenance change prediction: an empirical study. Appl Sci 12(10):5234","journal-title":"Appl Sci"},{"key":"10751_CR5","doi-asserted-by":"crossref","unstructured":"Barbieri MC, Grisci BI, Dorn M. (2024) Analysis and comparison of feature selection methods towards performance and stability. Expert Systems with Applications, page 123667","DOI":"10.1016\/j.eswa.2024.123667"},{"key":"10751_CR6","doi-asserted-by":"publisher","first-page":"132750","DOI":"10.1109\/ACCESS.2023.3329051","volume":"11","author":"M Begum","year":"2023","unstructured":"Begum M, Shuvo MH, Ashraf I, Al Mamun A, Uddin J, Samad MA (2023) Software defects identification: Results using machine learning and explainable artificial intelligence techniques. IEEE Access 11:132750\u2013132765","journal-title":"IEEE Access"},{"key":"10751_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests Machine learning 45:5\u201332","journal-title":"Random forests Machine learning"},{"key":"10751_CR8","doi-asserted-by":"crossref","unstructured":"Cabello-Solorzano K, Ortigosa\u00a0de Araujo I, Pe\u00f1a M, Correia L, J.\u00a0Tall\u00f3n-Ballesteros A. (2023) The impact of data normalization on the accuracy of machine learning algorithms: a comparative analysis. In International Conference on Soft Computing Models in Industrial and Environmental Applications, pages 344\u2013353. Springer","DOI":"10.1007\/978-3-031-42536-3_33"},{"key":"10751_CR9","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neucom.2017.11.077","volume":"300","author":"J Cai","year":"2018","unstructured":"Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: A new perspective. Neurocomputing 300:70\u201379","journal-title":"Neurocomputing"},{"issue":"9","key":"10751_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2156","volume":"31","author":"G Catolino","year":"2019","unstructured":"Catolino G, Ferrucci F (2019) An extensive evaluation of ensemble techniques for software change prediction. Journal of Software Evolution and Process 31(9):e2156","journal-title":"Journal of Software Evolution and Process"},{"key":"10751_CR11","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"10751_CR12","doi-asserted-by":"crossref","unstructured":"Cohen J (2013) Statistical power analysis for the behavioral sciences. routledge","DOI":"10.4324\/9780203771587"},{"key":"10751_CR13","unstructured":"Conover WJ (1999) Practical nonparametric statistics, volume 350. john wiley & sons"},{"key":"10751_CR14","unstructured":"Crabb\u00e9, AH, Cahy T, Somers B, Verbeke LP, Coillie FV (2020) Neural Network MLPClassifier (Version 1.5). Software"},{"issue":"6","key":"10751_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3459665","volume":"54","author":"P Cunningham","year":"2021","unstructured":"Cunningham P, Delany SJ (2021) K-nearest neighbour classifiers-a tutorial. ACM computing surveys (CSUR) 54(6):1\u201325","journal-title":"ACM computing surveys (CSUR)"},{"issue":"5","key":"10751_CR16","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.jss.2007.07.040","volume":"81","author":"KO Elish","year":"2008","unstructured":"Elish KO, Elish MO (2008) Predicting defect-prone software modules using support vector machines. J Syst Softw 81(5):649\u2013660","journal-title":"J Syst Softw"},{"issue":"1","key":"10751_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3\u201342","journal-title":"Mach Learn"},{"key":"10751_CR18","doi-asserted-by":"crossref","unstructured":"Gezici B, Tarhan AK (2022) Explainable ai for software defect prediction with gradient boosting classifier. In 2022 7th International Conference on Computer Science and Engineering (UBMK), pages 1\u20136. IEEE","DOI":"10.1109\/UBMK55850.2022.9919490"},{"issue":"2","key":"10751_CR19","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/computers13020052","volume":"13","author":"S Haldar","year":"2024","unstructured":"Haldar S, Capretz LF (2024) Interpretable software defect prediction from project effort and static code metrics. Computers 13(2):52","journal-title":"Computers"},{"issue":"4","key":"10751_CR20","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1108\/10650740610704135","volume":"23","author":"A Hanemann","year":"2006","unstructured":"Hanemann A, Liakopoulos A, Molina M, Swany DM (2006) A study on network performance metrics and their composition. Campus-Wide Information Systems 23(4):268\u2013282","journal-title":"Campus-Wide Information Systems"},{"issue":"1","key":"10751_CR21","volume":"16","author":"M Khanna","year":"2022","unstructured":"Khanna M (2022) A systematic review of ensemble techniques for software defect and change prediction. E-Inform Softw Eng J 16(1):220105","journal-title":"E-Inform Softw Eng J"},{"key":"10751_CR22","unstructured":"Kumar L, Sureka A. (2017) A comparative study of different source code metrics and machine learning algorithms for predicting change proneness of object oriented systems. arXiv preprint arXiv:1712.07944"},{"key":"10751_CR23","doi-asserted-by":"crossref","unstructured":"Kumar L, Lal S, Goyal A, Murthy NLB (2019) Change-proneness of object-oriented software using combination of feature selection techniques and ensemble learning techniques. In Proceedings of the 12th Innovations in Software Engineering Conference (Formerly Known as India Software Engineering Conference), ISEC \u201919. Association for Computing Machinery","DOI":"10.1145\/3299771.3299778"},{"key":"10751_CR24","doi-asserted-by":"crossref","unstructured":"Kumar L, Rath SK, Sureka A. (2017) Using source code metrics to predict change-prone web services: A case-study on ebay services. In 2017 IEEE workshop on machine learning techniques for software quality evaluation (MaLTeSQuE), pages 1\u20137. IEEE","DOI":"10.1109\/MALTESQUE.2017.7882009"},{"issue":"2","key":"10751_CR25","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.3390\/make6020050","volume":"6","author":"D Li","year":"2024","unstructured":"Li D, Liu Y, Huang J (2024) Assessment of software vulnerability contributing factors by model-agnostic explainable ai. Machine Learning and Knowledge Extraction 6(2):1087\u20131113","journal-title":"Machine Learning and Knowledge Extraction"},{"issue":"1","key":"10751_CR26","first-page":"5346498","volume":"2020","author":"H Li","year":"2020","unstructured":"Li H, Wang T, Xu X, Jiang B, Wei J, Wang J (2020) Modeling software systems as complex networks: Analysis and their applications. Math Probl Eng 2020(1):5346498","journal-title":"Math Probl Eng"},{"issue":"4","key":"10751_CR27","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1504\/IJCAT.2016.080487","volume":"54","author":"R Malhotra","year":"2016","unstructured":"Malhotra R, Bansal AJ (2016) Software change prediction: A literature review. Int J Comput Appl Technol 54(4):240\u2013256","journal-title":"Int J Comput Appl Technol"},{"key":"10751_CR28","doi-asserted-by":"publisher","first-page":"2806","DOI":"10.1007\/s10664-016-9488-7","volume":"22","author":"R Malhotra","year":"2017","unstructured":"Malhotra R, Khanna M (2017a) An empirical study for software change prediction using imbalanced data. Empir Softw Eng 22:2806\u20132851","journal-title":"Empir Softw Eng"},{"issue":"3","key":"10751_CR29","first-page":"1755","volume":"34","author":"R Malhotra","year":"2018","unstructured":"Malhotra R, Khanna M (2018) Prediction of change prone classes using evolution-based and object-oriented metrics. Journal of Intelligent & Fuzzy Systems 34(3):1755\u20131766","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10751_CR30","doi-asserted-by":"crossref","unstructured":"Malhotra R, Kapoor R, Aggarwal D, Garg P. (2021) Comparative study of feature reduction techniques in software change prediction. In 2021 IEEE\/ACM 18th International Conference on Mining Software Repositories (MSR), pages 18\u201328. IEEE","DOI":"10.1109\/MSR52588.2021.00015"},{"key":"10751_CR31","doi-asserted-by":"crossref","unstructured":"Malhotra R, Khanna M. (2017b) Software change prediction using voting particle swarm optimization based ensemble classifier. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, pages 311\u2013312","DOI":"10.1145\/3067695.3076007"},{"key":"10751_CR32","unstructured":"Malhotra R, Khanna M (2019) Software change prediction: A systematic review and future guidelines. e-Informatica Software Engineering Journal, 13(1)"},{"key":"10751_CR33","unstructured":"Molnar C (2022) Interpretable Machine Learning. Lulu.com, 2 edition"},{"key":"10751_CR34","unstructured":"Mohammadkhani AH, Bommi NS, Daboussi M, Sabnis O, Tantithamthavorn C, Hemmati H. (2023) A systematic literature review of explainable ai for software engineering. arXiv preprint arXiv:2302.06065"},{"key":"10751_CR35","doi-asserted-by":"crossref","unstructured":"Melo CS, da\u00a0Cruz MML, Martins ADF, Matos T, da\u00a0Silva Monteiro\u00a0Filho JM, de\u00a0Castro\u00a0Machado J. (2019) A practical guide to support change-proneness prediction. In International Conference on Enterprise Information Systems, pages 269\u2013276","DOI":"10.5220\/0007727702690276"},{"key":"10751_CR36","unstructured":"Pallant J (2013) Spss survival manual mcgraw-hill education (uk)"},{"key":"10751_CR37","unstructured":"Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A (2018) Catboost: unbiased boosting with categorical features. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS\u201918, page 6639\u20136649"},{"key":"10751_CR38","doi-asserted-by":"crossref","unstructured":"Raskutti B, Ferr\u00e1 H, Kowalczyk A. (2001) Second order features for maximising text classification performance. In European Conference on Machine Learning, pages 419\u2013430. Springer","DOI":"10.1007\/3-540-44795-4_36"},{"key":"10751_CR39","doi-asserted-by":"crossref","unstructured":"Santos G, Figueiredo E, Veloso A, Viggiato M, Ziviani N. (2021) Predicting software defects with explainable machine learning. In Proceedings of the XIX Brazilian Symposium on Software Quality, SBQS \u201920. Association for Computing Machinery","DOI":"10.1145\/3439961.3439979"},{"key":"10751_CR40","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.procs.2020.08.043","volume":"176","author":"T Sasada","year":"2020","unstructured":"Sasada T, Liu Z, Baba T, Hatano K, Kimura Y (2020) A resampling method for imbalanced datasets considering noise and overlap. Procedia Computer Science 176:420\u2013429","journal-title":"Procedia Computer Science"},{"issue":"1","key":"10751_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/smr.404","volume":"22","author":"R Shatnawi","year":"2010","unstructured":"Shatnawi R, Li W, Swain J, Newman T (2010) Finding software metrics threshold values using roc curves. J Softw Maint Evol Res Pract 22(1):1\u201316","journal-title":"J Softw Maint Evol Res Pract"},{"key":"10751_CR42","doi-asserted-by":"crossref","unstructured":"Shin J, Aleithan R, Nam J, Wang J, Wang S. (2021) Explainable software defect prediction: Are we there yet? arXiv preprint arXiv:2111.10901","DOI":"10.1109\/ICSE-Companion52605.2021.00056"},{"key":"10751_CR43","doi-asserted-by":"crossref","unstructured":"Tantithamthavorn CK, Jiarpakdee J. (2021) Explainable ai for software engineering. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pages 1\u20132. IEEE","DOI":"10.1109\/ASE51524.2021.9678580"},{"key":"10751_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.infsof.2017.07.003","volume":"92","author":"M Yan","year":"2017","unstructured":"Yan M, Zhang X, Liu C, Xu L, Yang M, Yang D (2017) Automated change-prone class prediction on unlabeled dataset using unsupervised method. Inf Softw Technol 92:1\u201316","journal-title":"Inf Softw Technol"},{"issue":"12","key":"10751_CR45","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2111","volume":"30","author":"X Zhu","year":"2018","unstructured":"Zhu X, He Y, Cheng L, Jia X, Zhu L (2018) Software change-proneness prediction through combination of bagging and resampling methods. Journal of Software Evolution and Process 30(12):e2111","journal-title":"Journal of Software Evolution and Process"},{"issue":"4","key":"10751_CR46","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2434","volume":"34","author":"X Zhu","year":"2022","unstructured":"Zhu X, Li N, Wang Y (2022) Software change-proneness prediction based on deep learning. Journal of Software Evolution and Process 34(4):e2434","journal-title":"Journal of Software Evolution and Process"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10751-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-025-10751-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10751-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T03:54:10Z","timestamp":1757130850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-025-10751-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":46,"journal-issue":{"issue":"11-12","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10751"],"URL":"https:\/\/doi.org\/10.1007\/s00500-025-10751-4","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"1 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent was obtained from all participants in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}