{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:51:41Z","timestamp":1775638301090,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Predictive maintenance plays a key role in digitalization initiatives; however, in real settings, issues related to failure prediction occur when failure instances are rare compared to normal instances, leading to class imbalance. In this study, we systematically compare five machine learning (ML) models\u2014random forest, XGBoost, support vector machine, k-nearest neighbors, and multinomial logistic regression (MLR)\u2014to detect multiclass rare failures using four imbalance-handling approaches (i.e., no handling, manual oversampling, selective manual oversampling, and class weighting), forming 20 configurations. Using the AI4I 2020 predictive maintenance dataset, which contains five failure types, we determined that XGBoost with no handling achieved the highest macro-averaged F1 (macro-F1) score (0.842) but obtained 0% recall for tool wear failure (TWF). MLR with selective manual oversampling achieved approximately 50% TWF recall with lower overall performance (0.636 macro-F1) than top-performing models such as XGBoost. We also found that very rare classes remain difficult to detect. Even high-performing models fail to consistently detect all five failure types. Overall, no single strategy can achieve a high detection rate across all performance measures.<\/jats:p>","DOI":"10.3390\/computation14040088","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:25:12Z","timestamp":1775633112000},"page":"88","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Comparative Study of Imbalance-Handling Methods in Multiclass Predictive Maintenance"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2602-3123","authenticated-orcid":false,"given":"Mohammed","family":"Alnahhal","sequence":"first","affiliation":[{"name":"Mechanical Engineering Department, American University of Ras Al Khaimah, Ras Al Khaimah P.O. Box 10021, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3688-7224","authenticated-orcid":false,"given":"Mosab I.","family":"Tabash","sequence":"additional","affiliation":[{"name":"Department of Business Administration, College of Business, Al Ain University, Al Ain P.O. Box 64141, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4385-6047","authenticated-orcid":false,"given":"Samir K.","family":"Safi","sequence":"additional","affiliation":[{"name":"Department of Statistics and Business Analytics, College of Business and Economics, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7831-2886","authenticated-orcid":false,"given":"Mujeeb Saif Mohsen","family":"Al-Absy","sequence":"additional","affiliation":[{"name":"Accounting and Financial Science Department, College of Administrative and Financial Science, Gulf University, Sanad 26489, Bahrain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1508-488X","authenticated-orcid":false,"given":"Zokir","family":"Mamadiyarov","sequence":"additional","affiliation":[{"name":"Department of Economics, Mamun University, Khiva P.O. Box 220900, Uzbekistan"},{"name":"Department of Finance and Tourism, Termez University of Economics and Service, Termez P.O. Box 190100, Uzbekistan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"ref_1","first-page":"18","article-title":"A cyber-physical systems architecture for Industry 4.0-based manufacturing systems","volume":"3","author":"Lee","year":"2015","journal-title":"Manuf. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sipos, R., Fradkin, D., Moerchen, F., and Wang, Z. (2014). Log-based predictive maintenance. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/2623330.2623340"},{"key":"ref_3","first-page":"1","article-title":"Hybrid deep learning approach for predictive maintenance of industrial machinery using convolutional LSTM networks","volume":"12","author":"Stow","year":"2024","journal-title":"Int. J. Comput. Sci. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Matzka, S. (2020). Explainable artificial intelligence for predictive maintenance applications. 2020 Third International Conference on Artificial Intelligence for Industries (AI4I), IEEE.","DOI":"10.1109\/AI4I49448.2020.00023"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Torcianti, A., and Matzka, S. (2021). Explainable artificial intelligence for predictive maintenance applications using a local surrogate model. 2021 4th International Conference on Artificial Intelligence for Industries (AI4I), IEEE.","DOI":"10.1109\/AI4I51902.2021.00029"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/j.procs.2024.09.546","article-title":"AI4I-PMDI: Predictive maintenance datasets with complex industrial settings\u2019 irregularities","volume":"246","author":"Autran","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., and Adda, M. (2022). On predictive maintenance in Industry 4.0: Overview, models, and challenges. Appl. Sci., 12.","DOI":"10.3390\/app12168081"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103298","DOI":"10.1016\/j.compind.2020.103298","article-title":"Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges","volume":"123","author":"Dalzochio","year":"2020","journal-title":"Comput. Ind."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/j.procs.2025.03.115","article-title":"Predictive maintenance in Industry 4.0: A review of data processing methods","volume":"257","author":"Hassan","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Farooq, U., Ademola, M., and Shaalan, A. (2024). Comparative analysis of machine learning models for predictive maintenance of ball bearing systems. Electronics, 13.","DOI":"10.3390\/electronics13020438"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2560","DOI":"10.1016\/j.ymssp.2006.12.007","article-title":"Support vector machine in machine condition monitoring and fault diagnosis","volume":"21","author":"Widodo","year":"2007","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.isatra.2014.08.007","article-title":"Application of higher order spectral features and support vector machines for bearing faults classification","volume":"54","author":"Saidi","year":"2015","journal-title":"ISA Trans."},{"key":"ref_16","first-page":"1179","article-title":"A predictive maintenance approach in manufacturing systems via AI-based early failure detection","volume":"35","author":"Hosseinzadeh","year":"2023","journal-title":"Manuf. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"31","DOI":"10.59511\/riestech.v1i01.6","article-title":"Machine predictive maintenance by using support vector machines","volume":"1","author":"Assagaf","year":"2023","journal-title":"Recent Eng. Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"26","DOI":"10.59511\/riestech.v1i03.21","article-title":"Machine failure detection using deep learning","volume":"1","author":"Assagaf","year":"2023","journal-title":"Recent Eng. Sci. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"534","DOI":"10.55730\/1300-0632.4086","article-title":"Ordinal predictive maintenance with ensemble binary decomposition (OPMEB)","volume":"32","author":"Birant","year":"2024","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"key":"ref_20","first-page":"785","article-title":"Failure prediction using ensemble learning: A comparative study with synthetic and real world datasets","volume":"25","author":"Kanar","year":"2025","journal-title":"Afyon Kocatepe Univ. Fen Ve M\u00fchendis. Bilim. Derg."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ucar, A., Karakose, M., and K\u0131r\u0131m\u00e7a, N. (2024). Artificial intelligence for predictive maintenance applications: Key components, trustworthiness, and future trends. Appl. Sci., 14.","DOI":"10.3390\/app14020898"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Atere, A., and Kivrak, H. (2025, January 19\u201320). A comparative evaluation of interpolation and generative oversampling techniques for predictive maintenance. Proceedings of the International Symposium on AI-Driven Engineering Systems (ISADES), Tokat, T\u00fcrkiye. SETSCI Conference Proceedings.","DOI":"10.36287\/setsci.22.21.001"},{"key":"ref_24","unstructured":"Bektasoglu, N., Narin, A., and \u0130leri, U. (2025). Performance analysis of the cheetah optimization algorithm in predictive maintenance forecasting. Proceedings of the 5th International Artificial Intelligence and Data Science Congress (ICADA 2025), Necmettin Erbakan University Press."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ghasemkhani, B., Kut, R.A., Birant, D., and Yilmaz, R. (2025). Balanced Hoeffding Tree Forest (BHTF): A novel multi-label classification with oversampling and undersampling techniques for failure mode diagnosis in predictive maintenance. Mathematics, 13.","DOI":"10.3390\/math13183019"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1007\/s10462-023-10652-8","article-title":"Cost-sensitive learning for imbalanced medical data: A review","volume":"57","author":"Araf","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Saito, T., and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, J., Chen, K., He, R., Huang, T., Tian, J., Wu, S., Yan, P., and Cheng, Y. (2026). Remaining Useful Life Prediction Based on Interpretable Serialized Variational Autoencoder: A Drift-Diffusion Stochastic Equation Perspective. IEEE Trans. Ind. Inform., early access.","DOI":"10.1109\/TII.2026.3657827"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"112271","DOI":"10.1016\/j.ress.2026.112271","article-title":"Source-Free Domain Adaptation for Cross-Domain Remaining Useful Life Prediction: A Distributed Federated Learning Perspective","volume":"271","author":"Zhang","year":"2026","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chow, C.W.K., Rahman, M.M., Rameezdeen, R., and Law, Y.W. (2025). Remaining Useful Life Prediction for Bearings Across Domains via a Subdomain Adaptation Network Driven by Spectral Clustering. Sensors, 25.","DOI":"10.3390\/s25226919"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6076","DOI":"10.1016\/j.procs.2025.10.077","article-title":"Optimizing predictive maintenance in Industrial IoT using enhanced Genghis Khan Shark Optimizer","volume":"270","author":"Khedr","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: Deep learning is not all you need","volume":"81","author":"Armon","year":"2022","journal-title":"Inf. Fusion"}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/4\/88\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:01:50Z","timestamp":1775635310000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/4\/88"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":32,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["computation14040088"],"URL":"https:\/\/doi.org\/10.3390\/computation14040088","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]}}}