<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">msi</journal-id><journal-title-group><journal-title xml:lang="ru">Современная наука и инновации</journal-title><trans-title-group xml:lang="en"><trans-title>Modern Science and Innovations</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2307-910X</issn><publisher><publisher-name>North-Caucasus Federal University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.37493/2307-910X.2025.2.2</article-id><article-id custom-type="elpub" pub-id-type="custom">msi-1741</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ТЕХНИЧЕСКИЕ НАУКИ. ИНФОРМАТИКА, ВЫЧИСЛИТЕЛЬНАЯ ТЕХНИКА И УПРАВЛЕНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>TECHNICAL SCIENCES. INFORMATION, COMPUTING AND MANAGEMENT</subject></subj-group></article-categories><title-group><article-title>Исследование механизмов детектирования кибератак с помощью технологий машинного обучения</article-title><trans-title-group xml:lang="en"><trans-title>Investigation of cyberattack detection mechanisms using machine learning technologies</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Андрусенко</surname><given-names>Ю. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Andrusenko</surname><given-names>Yu. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Юлия Алексеевна Андрусенко – старший преподаватель</p><p>д. 1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Yulia A. Andrusenko – Senior Lecturer</p><p>1, Pushkin St., Stavropol, 355017</p></bio><email xlink:type="simple">iuandrusenko@ncfu.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шавло</surname><given-names>Д. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Shavlo</surname><given-names>D. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Дмитрий Сергеевич Шавло – студент</p><p>д. 1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Dmitry S. Shavlo – Student</p><p>1, Pushkin St., Stavropol, 355017</p></bio><email xlink:type="simple">ds357@ro.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Плетухин</surname><given-names>А. П.</given-names></name><name name-style="western" xml:lang="en"><surname>Pletukhin</surname><given-names>A. P.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Алексей Павлович Плетухин – студент</p><p>д. 1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Alexey P. Pletukhin – Student</p><p>1, Pushkin St., Stavropol, 355017</p></bio><email xlink:type="simple">mrster03@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Семиколеннова</surname><given-names>Е. Р.</given-names></name><name name-style="western" xml:lang="en"><surname>Semikolennova</surname><given-names>E. R.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Елена Романовна Семиколеннова – студент</p><p>д. 1, ул. Пушкина, Ставрополь, 355017</p></bio><bio xml:lang="en"><p>Elena R. Semikolennova – Student</p><p>1, Pushkin St., Stavropol, 355017</p></bio><email xlink:type="simple">elena291204@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кондрашов</surname><given-names>М. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Kondrashov</surname><given-names>M. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Михаил Ильич Кондрашов – студент</p><p>д. 78, пр. Вернадского, Москва, 119454</p></bio><bio xml:lang="en"><p>Mikhail I. Kondrashov – Student</p><p>78, Vernadsky Ave., Moscow, 119454</p></bio><email xlink:type="simple">kondr-mih@mail.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Северо-Кавказский федеральный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>North-Caucasus Federal University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>МИРЭА – Российский технологический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>MIREA - Russian Technological University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>20</day><month>01</month><year>2026</year></pub-date><volume>0</volume><issue>2</issue><fpage>19</fpage><lpage>31</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Андрусенко Ю.А., Шавло Д.С., Плетухин А.П., Семиколеннова Е.Р., Кондрашов М.И., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Андрусенко Ю.А., Шавло Д.С., Плетухин А.П., Семиколеннова Е.Р., Кондрашов М.И.</copyright-holder><copyright-holder xml:lang="en">Andrusenko Y.A., Shavlo D.S., Pletukhin A.P., Semikolennova E.R., Kondrashov M.I.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://msi.elpub.ru/jour/article/view/1741">https://msi.elpub.ru/jour/article/view/1741</self-uri><abstract><p>В условиях растущей сложности киберугроз и увеличения частоты кибератак актуальность разработки эффективных инструментов для автоматического обнаружения вторжений в информационные системы неуклонно возрастает. Традиционные методы защиты, основанные на сигнатурном анализе, часто не справляются с новыми, неизвестными атаками, что стимулирует исследование альтернативных подходов, в том числе методов машинного обучения (ML). В статье рассматривается применение ML для решения задачи бинарной классификации сетевой активности на нормальную и аномальную (кибератаку) с использованием программной платформы KNIME, ориентированной на визуальное проектирование аналитических пайплайнов.Исследование проводилось на общедоступном датасете Cybersecurity Intrusion Detection, включающем 11 признаков, характеризующих сетевой трафик и пользовательское поведение (время активности, протокол передачи данных, размер пакетов, количество подключений, частота запросов и т.д.). Целью работы стало сравнительное изучение эффективности пяти алгоритмов ML: Decision Trees (деревья решений), Naive Bayes (наивный байесовский классификатор), Random Forest (случайный лес), Gradient Boosted Trees (градиентный бустинг на деревьях) и Simple Regression Tree (простое регрессионное дерево). Выбор моделей обусловлен их распространенностью в задачах обнаружения аномалий и различиями в принципах работы: от простых решающих правил (Decision Trees) до ансамблевых методов (Random Forest, Gradient Boosted Trees), объединяющих несколько "слабых" моделей для повышения точности.Для подготовки данных к обучению применялся метод главных компонент (PCA), позволивший сократить размерность признакового пространства с 11 до 3 компонент без существенной потери информации. Это важный шаг, так как избыточность или коррелированность признаков может негативно влиять на качество моделей. Настройка гиперпараметров (например, глубины деревьев, количества деревьев в Random Forest, скорости обучения в Gradient Boosted Trees) и борьба с переобучением осуществлялись через кроссвалидацию, что обеспечило стабильность результатов на новых данных. Эксперименты показали, что наибольшую точность (83.055%) и площадь под ROC-кривой (AUC = 0.811) продемонстрировали алгоритмы Random Forest и Gradient Boosted Trees. Эти результаты объясняются способностью ансамблевых методов учитывать нелинейные зависимости в данных и  устойчивостью  к  шуму,  что   критично   для   задач   кибербезопасности,  где   атаки   могут маскироваться под нормальную активность. Модели Decision Trees и Simple Regression Tree показали более низкие метрики (точность ~75-78%), что связано с их склонностью к переобучению на небольших датасетах. Naive Bayes, предполагающий независимость признаков, также уступил ансамблевым методам, что подтверждает ограниченность предположения о независимости в контексте сетевых данных. Особое внимание уделено этапам работы: от загрузки и визуализации данных (анализ распределения классов, корреляций между признаками) до обучения моделей и интерпретации результатов. Использование KNIME упростило реализацию пайплайна: платформа предоставляет визуальные инструменты для предобработки данных, настройки моделей и оценки их качества, что делает подход доступным для специалистов в области кибербезопасности без глубоких знаний программирования.Результаты исследования вносят вклад в развитие практических приложений ML для защиты информационных систем. Они демонстрируют, что ансамблевые методы, такие как Random Forest и Gradient Boosted Trees, могут эффективно применяться для обнаружения кибератак в режиме реального времени, особенно в условиях ограниченного набора данных. Перспективными направлениями дальнейших работ являются расширение датасета за счет включения новых типов атак (например, Advanced Persistent Threats, IoT-атак, атак на криптографические протоколы), а также интеграция методов глубокого обучения (например, рекуррентных нейронных сетей для анализа последовательностей сетевых событий) для повышения точности и адаптивности систем обнаружения вторжений.</p></abstract><trans-abstract xml:lang="en"><p>In the context of the growing complexity of cyber threats and the increasing frequency of cyberattacks, the relevance of developing effective tools for automatic detection of intrusions into information systems is steadily increasing. Traditional protection methods based on signature analysis often fail to cope with new, unknown attacks, which stimulates the study of alternative approaches, including machine learning (ML) methods. The article discusses the use of ML to solve the problem of binary classification of network activity into normal and abnormal (cyberattack) using the KNIME software platform, which is focused on the visual design of analytical pipelines. The study was conducted on the publicly available Cybersecurity Intrusion Detection dataset, which includes 11 features characterizing network traffic and user behavior (activity time, data transfer protocol, packet size, number of connections, request frequency, etc.). The aim of the work was a comparative study of the efficiency of five ML algorithms: Decision Trees, Naive Bayes, Random Forest, Gradient Boosted Trees, and Simple Regression Tree. The choice of models is due to their prevalence in anomaly detection problems and differences in operating principles: from simple decision rules (Decision Trees) to ensemble methods (Random Forest, Gradient Boosted Trees) that combine several "weak" models to improve accuracy. To prepare the data for training, the principal component analysis (PCA) was used, which allowed us to reduce the dimensionality of the feature space from 11 to 3 components without significant loss of information. This is an important step, since redundancy or correlation of features can negatively affect the quality of the models. Tuning hyperparameters (e.g. tree depth, number of trees in Random Forest, learning rate in Gradient Boosted Trees) and combating overfitting were performed through cross-validation, which ensured the stability of the results on new data. Experiments showed that the highest accuracy (83.055%) and area under the ROC curve (AUC = 0.811) were demonstrated by the Random Forest and Gradient Boosted Trees algorithms. These results are explained by the ability of ensemble methods to take into account nonlinear dependencies in data and their resistance to noise, which is critical for cybersecurity tasks, where attacks can be disguised as normal activity. Decision Trees and Simple Regression Tree models showed lower metrics (accuracy ~75-78%), which is due to their tendency to overfitting on small datasets. Naive Bayes, which assumes independence of features, also gave way to ensemble methods, which confirms the limitations of the independence assumption in the context of network data. Particular attention is paid to the stages of work: from loading and visualizing data (analysis of class distribution, correlations between features) to training models and interpreting the results. The use of KNIME simplified the implementation of the pipeline: the platform provides visual tools for data preprocessing, model tuning and assessing their quality, which makes the approach accessible to cybersecurity specialists without deep programming knowledge. The results of the study contribute to the development of practical applications of ML for protecting information systems. They demonstrate that ensemble methods such as Random Forest and Gradient Boosted Trees can be effectively used to detect cyberattacks in real time, especially in conditions of a limited data set. Promising areas for further work include expanding the dataset to include new types of attacks (e.g. Advanced Persistent Threats, IoT attacks, attacks on cryptographic protocols), as well as integrating deep learning methods (e.g. recurrent neural networks for analyzing network event sequences) to improve the accuracy and adaptability of intrusion detection systems. </p></trans-abstract><kwd-group xml:lang="ru"><kwd>KNIME</kwd><kwd>машинное обучение</kwd><kwd>датасет</kwd><kwd>кибератака</kwd><kwd>сетевая активность</kwd></kwd-group><kwd-group xml:lang="en"><kwd>KNIME</kwd><kwd>Machine Learning</kwd><kwd>Dataset</kwd><kwd>Cyber Attack</kwd><kwd>Network Activity</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Kemmerer R. A. Cybersecurity // 25th International Conference on Software Engineering, 2003. Proceedings. IEEE, 2003. P. 705–715.</mixed-citation><mixed-citation xml:lang="en">Kemmerer RA. Cybersecurity. 25th International Conference on Software Engineering, 2003. Proceedings. IEEE, 2003. P. 705-715.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Biju J. M., Gopal N., Prakash A. J. Cyberattacks and its different types // International Research Journal of Engineering and Technology. 2019. Vol. 6. No. 3. P. 4849–4852.</mixed-citation><mixed-citation xml:lang="en">Biju JM., Gopal N, Prakash AJ. Cyberattacks and its different types. International Research Journal of Engineering and Technology. 2019;6(3):4849-4852.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Sabillon R., Cano M. J. J., Serra-Ruiz J., Cavaller V. Cybercrime and cybercriminals: A comprehensive study // International Journal of Computer Networks and Communications Security. 2016. Vol. 4. No. 6. P. 165–176.</mixed-citation><mixed-citation xml:lang="en">Sabillon R, Cano MJJ, Serra-Ruiz J, Cavaller V. Cybercrime and cybercriminals: A comprehensive study. International Journal of Computer Networks and Communications Security. 2016;4(6):165176.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Najafabadi M. M., Khoshgoftaar T. M., Kemp C., Seliya N., Zuech R. Machine learning for detecting brute force attacks at the network level // 2014 IEEE International Conference on Bioinformatics and Bioengineering. Boca Raton: IEEE, 2014. P. 379–385.</mixed-citation><mixed-citation xml:lang="en">Najafabadi MM., Khoshgoftaar TM, Kemp C, Seliya N, Zuech R. Machine learning for detecting brute force attacks at the network level. 2014 IEEE International Conference on Bioinformatics and Bioengineering. Boca Raton: IEEE, 2014. P. 379-385.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Kim J., Song M., Seo M., Jin Y., Shin S. PassREfinder: Credential stuffing risk prediction by representing password reuse between websites on a graph // 2024 IEEE Symposium on Security and Privacy (SP). San Francisco: IEEE, 2024. P. 1385–1404.</mixed-citation><mixed-citation xml:lang="en">Kim J, Song M, Seo M, Jin Y, Shin S. PassREfinder: Credential stuffing risk prediction by representing password reuse between websites on a graph. 2024 IEEE Symposium on Security and Privacy (SP). San Francisco: IEEE, 2024. P. 1385-1404.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Doshi R., Apthorpe N., Feamster N. Machine learning ddos detection for consumer internet of things devices // 2018 IEEE Security and Privacy Workshops (SPW). IEEE, 2018. P. 29–35.</mixed-citation><mixed-citation xml:lang="en">Doshi R, Apthorpe N, Feamster N. Machine learning ddos detection for consumer internet of things devices. 2018 IEEE Security and Privacy Workshops (SPW). IEEE, 2018. P. 29-35.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Jonas M. A., Hossain M. S., Islam R., Narman H. S., Atiquzzaman M. An intelligent system for preventing ssl stripping-based session hijacking attacks // MILCOM 2019-2019 IEEE Military Communications Conference (MILCOM). Norfolk: IEEE, 2019. P. 1–6.</mixed-citation><mixed-citation xml:lang="en">Jonas MA, Hossain MS, Islam R, Narman HS, Atiquzzaman M. An intelligent system for preventing ssl stripping-based session hijacking attacks. MILCOM 2019-2019 IEEE Military Communications Conference (MILCOM). Norfolk: IEEE, 2019. P. 1-6.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Al-Juboori S. A. M., Hazzaa F., Jabbar Z. S., Salih S., Gheni H. M. Man-in-the-middle and denial of service attacks detection using machine learning algorithms // Bulletin of Electrical Engineering and Informatics. 2023. Vol. 12. No. 1. P. 418–426.</mixed-citation><mixed-citation xml:lang="en">Al-Juboori SAM, Hazzaa F, Jabbar ZS, Salih S, Gheni HM. Man-in-the-middle and denial of service attacks detection using machine learning algorithms. Bulletin of Electrical Engineering and Informatics. 2023;12(1):418-426.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Stone G., Talbert D., Eberle W. Using Using AI/Machine Learning for Reconnaissance Activities During Network Penetration Testing // International Conference on Cyber Warfare and Security. Academic Conferences International Limited, 2021. P. 541–XIV.</mixed-citation><mixed-citation xml:lang="en">Stone G., Talbert D., Eberle W. Using AI/Machine Learning for Reconnaissance Activities During Network Penetration Testing. International Conference on Cyber Warfare and Security. Academic Conferences International Limited, 2021. P. 541-XIV.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Santoso R., Gunawan A. A. S. Detecting Account Takeover (ATO) in Fintech Companies Using Machine Learning // 2024 6th International Conference on Cybernetics and Intelligent System (ICORIS). Surakarta: IEEE, 2024. P. 1–6.</mixed-citation><mixed-citation xml:lang="en">Santoso R, Gunawan AAS. Detecting Account Takeover (ATO) in Fintech Companies Using Machine Learning // 2024 6th International Conference on Cybernetics and Intelligent System (ICORIS). Surakarta: IEEE, 2024. P. 1-6.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Ghafir I., Hammoudeh M., Prenosil V., Han L., Hegarty R., Rabie K., Aparicio-Navarro F. J. Detection of advanced persistent threat using machine-learning correlation analysis // Future Generation Computer Systems. 2018. Vol. 89. P. 349–359.</mixed-citation><mixed-citation xml:lang="en">Ghafir I, Hammoudeh M, Prenosil V, Han L, Hegarty R, Rabie K, Aparicio-Navarro  FJ. Detection of advanced persistent threat using machine-learning correlation analysis. Future Generation Computer Systems. 2018;89:349-359.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Nath H. V., Mehtre B. M. Static malware analysis using machine learning methods // International Conference on Security in Computer Networks and Distributed Systems. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014. P. 440–450.</mixed-citation><mixed-citation xml:lang="en">Nath HV, Mehtre BM. Static malware analysis using machine learning methods. International Conference on Security in Computer Networks and Distributed Systems. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014. P. 440-450.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Zahra F., Jhanjhi N. Z., Khan N. A., Brohi S. N., Masud M., Aljahdali S. Protocol-specific and sensor network-inherited attack detection in IoT using machine learning // Applied Sciences. 2022. Vol. 12. No. 22. P. 11598.</mixed-citation><mixed-citation xml:lang="en">Zahra F, Jhanjhi NZ, Khan NA, Brohi SN, Masud M, Aljahdali S. Protocol-specific and sensor network-inherited attack detection in IoT using machine learning. Applied Sciences. 2022;12(22):11598.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Samudrala D. N. K. Cybersecurity Intrusion Detection Dataset // Kaggle. [Electronic resource]. URL: https://www.kaggle.com/datasets/dnkumars/cybersecurity-intrusion-detection-dataset (accessed: 15.03.2025).</mixed-citation><mixed-citation xml:lang="en">Samudrala 	DNK. 	Cybersecurity 	Intrusion 	Detection 	Dataset. 	Kaggle. 	Available 	from: https://www.kaggle.com/datasets/dnkumars/cybersecurity-intrusion-detection-dataset [Accessed 15 March 2025].</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Mackiewicz A., Ratajczak W. Principal components analysis (PCA) // Computers and Geosciences. 1993. Vol. 19. No. 3. P. 303–342.</mixed-citation><mixed-citation xml:lang="en">Mackiewicz A, Ratajczak W. Principal components analysis (PCA). Computers and Geosciences. 1993;19(3):303-342.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Nahm F. S. Receiver operating characteristic curve: overview and practical use for clinicians // Korean journal of anesthesiology. 2022. Vol. 75. No. 1. P. 25–36.</mixed-citation><mixed-citation xml:lang="en">Nahm FS. Receiver operating characteristic curve: overview and practical use for clinicians. Korean journal of anesthesiology. 2022;75(1):25-36.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Charbuty B., Abdulazeez A. Classification based on decision tree algorithm for machine learning // Journal of applied science and technology trends. 2021. Vol. 2. No. 1. P. 20–28.</mixed-citation><mixed-citation xml:lang="en">Charbuty B, Abdulazeez A. Classification based on decision tree algorithm for machine learning. Journal of applied science and technology trends. 2021;2(1):20-28.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Rigatti S. J. Random forest // Journal of Insurance Medicine. 2017. Vol. 47. No. 1. P. 31–39.</mixed-citation><mixed-citation xml:lang="en">Rigatti SJ. Random forest. Journal of Insurance Medicine. 2017;47(1):31-39.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Loh W. Y. Classification and regression trees // Wiley interdisciplinary reviews: data mining and knowledge discovery. 2011. Vol. 1. No. 1. P. 14–23.</mixed-citation><mixed-citation xml:lang="en">Loh WY. Classification and regression trees. Wiley interdisciplinary reviews: data mining and knowledge discovery. 2011;1(1):14-23.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Ye J., Chow J. H., Chen J., Zheng Z. Stochastic gradient boosted distributed decision trees // Proceedings of the 18th ACM conference on Information and knowledge management. 2009. P. 2061–2064.</mixed-citation><mixed-citation xml:lang="en">Ye J, Chow JH, Chen J, Zheng Z. Stochastic gradient boosted distributed decision trees. Proceedings of the 18th ACM conference on Information and knowledge management. 2009. P. 2061-2064.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Webb G. I., Keogh E., Miikkulainen R. Naïve Bayes // Encyclopedia of machine learning. 2010. Vol. 15. No. 1. P. 713–714.</mixed-citation><mixed-citation xml:lang="en">Webb GI, Keogh E, Miikkulainen R. Naive Bayes. Encyclopedia of machine learning. 2010;15(1):713-714.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Berrar D. Cross-validation. Encyclopedia of Bioinformatics and Computational Biology. 2019. Vol. 1. P. 542–545.</mixed-citation><mixed-citation xml:lang="en">Berrar D. Cross-validation. Encyclopedia of Bioinformatics and Computational Biology. 2019;1:542-545.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
