Труды КНЦ. Технические науки. – 2026. - № 2

12. Atlas of isothermal transformation diagrams. United States Steel Corporation. 1951. Available at: https://dn720705.ca.archive.org/0/items/atlas_of_isothermal_transformation_diagrams/atlas_of_isothermal_transf ormation_diagrams_big_text.pdf (accessed 03.07.2025). 13. Florek P., Zagdanski A. Benchmarking state-of-the-art gradient boosting algorithms for classification. arXiv:2305.17094. Available at: https://arxiv.org/abs/2305.17094 (accessed 07.03.2025). 14. Zhang Y., Liu J., Shen W. A Review o f Ensemble Learning Algorithms Used in Remote Sensing Applications. Applied Sciences, 2022, 12 (17), рр. 8654. https://doi.org/10.3390/app12178654 15. Zhi-Hua Zhou. Ensemble Methods. New York, Chapman and Hall/CRC, 2012, 236 р. https://doi.org/10.1201/b12207 16. Lai J-P, Lin Y-L, Lin H-C, Shih C-Y, Wang Y-P, Pai P-F. Tree-Based Machine Learning Models with Optuna in Predicting Impedance Values for Circuit Analysis. Micromachines, 2023, Vоl. 14 (2), рр. 265. https://doi.org/10.3390/mi14020265 17. Sedukhin O. CatBoost, XGBoost and the expressive power of decision trees. habr.com. Available at: https://habr.com/ru/companies/ods/articles/645887 (accessed 07.03.2025). 18. Teaching mathematical models using the Decision Trees algorithm using regression and classification methods. AQT (Advanced Quality Tools) Center for Advanced Quality Management Tools. Available at: https://advanced- quality-tools.ru/python-machine_learning_decision_trees.html (accessed 05.04.2025). 19. Shakhomirov M. Modern data engineering. Tools and best practices for specific platforms. Towards Data Science. Available at: https://towardsdatascience.com/modern-data-engineering-e202776fb9a9 (accessed 05.04.2025). 20. Zheng A., Kazari A. Designing features for machine learning. O'Reilly Media, Inc. 2018, April, 215 р. Available at: https://www.oreilly.com/library/view/featureengineering-for/9781491953235 (accessed 05.07.2025). 21. Kuhn M., Johnson K. Design and selection of features: a practical approach to predictive models. Kuhn & Johnson, 2020. Available at: https://bookdown.org/max/FES (accessed 05.12.2025). 22. He H., Bai Y., Garcia E. A., Li Sh. ADASYN: an adaptive approach to synthetic sampling for Unbalanced learning. 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). Hong Kong, 2008, pp. 1322-1328. doi:10.1109/IJCNN.2008.4633969 23. Loffredo E., Pastore M., Cocco S., Monasson R. Restoring balance: principled under/oversampling of data for optimal classification. arXiv:2405.09535v2 [cond-mat.dis-nn], 2025, 31 Jan. Available at: https://arxiv.org/pdf/2405.09535 (accessed 07.03.2025). 24. Akiba T., Sano Sh., Yanase T., OhtaT., KoyamaM. Optuna: A Next-generationHyperparameterOptimizationFramework. arXiv:1907.10902. Available at: https://arxiv.org/abs/1907.10902 (accessed 07.03.2025). 25. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. J. Machine Learning Research, 2012, No. 13, pp. 281-305. 26. Gebreyesus Y., Dalton D., De Chiara D., Chinnici M., Chinnici A. AI for Automating Data Center Operations: Model Explainability in the Data Centre Context Using Shapley Additive Explanations (SHAP). Electronics, 2024, ^ l . 13 (9), рр. 1628. https://doi.org/10.3390/electronics13091628 27. Lundberg S. M., Lee Su-In. A Unified Approach to Interpreting Model Predictions. arXiv:1705.07874v2 [cs.AI ], 2017, 25 Nov. URL: https://arxiv.org/pdf/1705.07874 (accessed 07.03.2025). Информация об авторах О. А. Бутов — ведущий инженер / младший научный сотрудник; В. С. Солод — кандидат технических наук, научный сотрудник. Information about the authors O. A. Butov — Senior Engineer / Junior Researcher; V. S. Solod — PhD (Engineering), research fellow. Статья поступила в редакцию 09.02.2026; одобрена после рецензирования 28.05.2026; принята к публикации 28.05.2026. The article was submitted 09.02.2026; approved after reviewing 28.05.2026; accepted for publication 28.05.2026.