moitvivt Моделирование, оптимизация и информационные технологии Modeling, Optimization and Information Technology 2310-6018 Издательство 10.26102/2310-6018/2026.53.2.018 2196 Онтологический подход к прогнозированию покупательского поведения пользователей в электронной коммерции Ontology-based approach to predicting consumer purchasing behavior in e-commerce 0009-0009-0322-1443 Святов Роман Сергеевич Svyatov Roman Sergeevich romasvyatov@yandex.ru aff-1 Российский университет дружбы народов RUDN University 01 01 2026 1 1 10.26102/2310-6018/2026.53.2.018 Copyright © Авторы, 2026 2026 This work is licensed under a Creative Commons Attribution 4.0 International License

Актуальность исследования обусловлена необходимостью повышения точности и интерпретируемости моделей прогнозирования покупательского поведения пользователей интернет-магазинов. Существующие методы машинного обучения демонстрируют высокие показатели качества, однако их эффективность существенно зависит от состава и структуры признакового пространства, которое, как правило, формируется эмпирически и не отражает причинно-следственных связей между пользовательскими действиями. В связи с этим данная работа направлена на разработку метода прогнозирования покупательского поведения, основанного на онтологическом анализе предметной области электронной коммерции. Предложен формализованный подход к описанию сущностей и их взаимосвязей, обеспечивающий системное построение признакового пространства и возможность его масштабирования для различных интернет-магазинов. В качестве инструмента машинного обучения использован алгоритм градиентного бустинга CatBoost, реализованный на данных системы веб-аналитики Яндекс.Метрика. Проведено тестирование на пяти интернет-магазинах различной тематической направленности. Экспериментальные результаты показали устойчивые значения метрик качества (F-мера в 65–83 %), что подтверждает применимость и воспроизводимость предложенного метода. Материалы статьи представляют практическую ценность для разработки интеллектуальных систем поддержки принятия решений в электронной коммерции и могут быть использованы при проектировании масштабируемых аналитических платформ для прогнозирования пользовательской активности и конверсии.

The relevance of this study is determined by the need to improve the accuracy and interpretability of models for predicting consumer purchasing behavior in online stores. Existing machine learning methods demonstrate high performance; however, their effectiveness largely depends on the composition and structure of the feature space, which is typically formed empirically and does not reflect the causal relationships between user actions. This study aims to develop a purchasing behavior prediction method based on an ontological analysis of the e-commerce domain. A formalized approach is proposed for describing entities and their interrelations, providing a systematic construction of the feature space and enabling its scalability across various online stores. The gradient boosting algorithm CatBoost was employed as the machine learning tool, trained on data obtained from the Yandex.Metrica web analytics system. The proposed method was tested on five online stores with different thematic focuses. Experimental results demonstrated stable quality metrics, with F-scores ranging from 65 % to 83 %, confirming the applicability and reproducibility of the developed approach. The findings have practical significance for the development of intelligent decision support systems in e-commerce and can be utilized in designing scalable analytical platforms for predicting user activity and purchase conversion.

 машинное обучение онтологический анализ анализ поведения пользователей электронная коммерция прогнозирование покупательского поведения интернет-магазины machine learning ontology analysis user behavior analysis e-commerce consumer behavior prediction online stores Исследование выполнено без спонсорской поддержки. The study was performed without external funding. References Sikelis K., Tsekouras G.E., Kotis K.I. Ontology-Based Feature Selection: A Survey. arXiv. URL: https://doi.org/10.48550/arXiv.2104.07720 [Accessed 18th January 2026]. Vicient C., Sánchez D., Moreno A. An Automatic Approach for Ontology-Based Feature Extraction from Heterogeneous Textual Resources. Engineering Applications of Artificial Intelligence. 2013;26(3):1092–1106. https://doi.org/10.1016/j.engappai.2012.08.002 Di Noia T., Magarelli C., Maurino A., Palmonari M., Rula A. Using ontology-based data summarization to develop semantics-aware recommender systems. In: The Semantic Web: 15th International Conference, ESWC 2018, 03–07 June 2018, Heraklion, Crete, Greece. Cham: Springer; 2018. P. 128–144. https://doi.org/10.1007/978-3-319-93417-4_9 Lu S., Ye Y., Tsui R., et al. Domain Ontology-based Feature Reduction for High Dimensional Drug Data and its Application to 30-Day Heart Failure Readmission Prediction. In: 9th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing, 20–23 October 2013, Austin, TX, USA. IEEE; 2013. P. 478–484. https://doi.org/10.4108/icst.collaboratecom.2013.254124 Abdollahi M., Gao X., Mei Y., Ghosh Sh., Li J. An Ontology-based Two-Stage Approach to Medical Text Classification with Feature Selection by Particle Swarm Optimisation. In: 2019 IEEE Congress on Evolutionary Computation, 10–13 June 2019, Wellington, New Zealand. IEEE; 2019. P. 119–126. https://doi.org/10.1109/CEC.2019.8790259 Kühl N., Mühlthaler M., Goutier M. Supporting customer-oriented marketing with artificial intelligence: automatically quantifying customer needs from social media. Electronic Markets. 2020;30(2):351–367. https://doi.org/10.1007/s12525-019-00351-0 Heilman C.M., Kaefer F., Ramenofsky S.D. Determining the appropriate amount of data for classifying consumers for direct marketing purposes. Journal of Interactive Marketing. 2003;17(3):5–28. https://doi.org/10.1002/dir.10057 Kotis K.I., Vouros G.A., Spiliotopoulos D. Ontology engineering methodologies for the evolution of living and reused ontologies: status, trends, findings and recommendations. The Knowledge Engineering Review. 2020;35. https://doi.org/10.1017/S0269888920000065 Wen Zh., Lin W., Liu H. Machine-Learning-Based Approach for Anonymous Online Customer Purchase Intentions Using Clickstream Data. Systems. 2023;11(5). https://doi.org/10.3390/systems11050255 Hesvindrati N., Aminuddin A., Mahadhni J., Pambudi A., Sudaryatno B. Behavior-Based Purchase Intent Prediction in E-Commerce: A Machine Learning Approach. International Journal of Current Science Research and Review. 2025;8(8):3970–3980. https://doi.org/10.47191/ijcsrr/V8-i8-03 Liu D., Huang H., Zhang H., Luo X., Fan Zh. Enhancing customer behavior prediction in e-commerce: A comparative analysis of machine learning and deep learning models. Applied and Computational Engineering. 2024;55(1):181–195. https://doi.org/10.54254/2755-2721/55/20241475 Abhichandani D., Vadrevu N.R.T., Doshi P., Shrivastava Sh. Predicting Online Purchases Using Six Machine Learning Models Based on Customer Demographics. In: 2025 6th International Conference on Data Intelligence and Cognitive Informatics (ICDICI), 09–11 July 2025, Tirunelveli, India. IEEE; 2025. P. 1787–1792. https://doi.org/10.1109/icdici66477.2025.11135228 Ayyadapu A.K.R., Saini P., Gupta P., et al. Fuzzy Logic and Machine Learning Hybrid Model for Influencing Consumer Purchasing Behavior in E-Commerce. In: 2025 International Conference on Computing Technologies & Data Communication, 04–05 July 2025, HASSAN, India. IEEE; 2025. P. 1–6. https://doi.org/10.1109/icctdc64446.2025.11158906 Li H. Research on Consumer Behavior Prediction Based on E-commerce Data Analysis. BCP Business & Management. 2023;49:106–110. https://doi.org/10.54691/bcpbm.v49i.5411 Htar T.T., Zaw M.M. Predicting Consumer Purchasing Behavior Using SVM and Random Forest Classification Methods. International Journal of Scientific Research in Engineering and Management. 2025;9(8). https://doi.org/10.55041/ijsrem51727 Huang W. Analysis of Promotional Online Shopping Behavior Based on Machine Learning. Highlights in Science, Engineering and Technology. 2023;56:65–72. https://doi.org/10.54097/hset.v56i.9817 Usha U.M., Swamy K.P.N. Anticipatory Modeling of Product Purchases. International Journal of Advanced Research in Science, Communication and Technology. 2024;4(1):137–143. https://doi.org/10.48175/ijarsct-19117 Chaudhuri N., Gupta G., Vamsi V., Bose I. On the platform but will they buy? Predicting customers' purchase behavior using deep learning. Decision Support Systems. 2021;149. https://doi.org/10.1016/j.dss.2021.113622 Bhutani P., Baranwal Sh.K., Jain S. Semantic Framework for Facilitating Product Discovery. In: ACI'21: Workshop on Advances in Computational Intelligence at ISIC 2021, 25–27 February 2021, Delhi, India. 2021. P. 30–36. García M. del M.R., García-Nieto J., Aldana-Montes J.F. An ontology-based data integration approach for web analytics in e-commerce. Expert Systems with Applications. 2016;63:20–34. https://doi.org/10.1016/j.eswa.2016.06.034 Kim H. Developing a Product Knowledge Graph of Consumer Electronics to Manage Sustainable Product Information. Sustainability. 2021;13(4). https://doi.org/10.3390/su13041722 Preece Ch., Rojas Gaviria P. An ontology of consumers as distributed networks: a question of cause and effect. Journal of Marketing Management. 2024;40(7-8):628–634. https://doi.org/10.1080/0267257X.2024.2346010 Esmeli R., Bader-El-Den M., Abdullahi H. Towards early purchase intention prediction in online session based retailing systems. Electronic Markets. 2020;31:697–715. https://doi.org/10.1007/s12525-020-00448-x Liu Zh., Zhang Y., Abedin M.Z., et al. Profit-driven fusion framework based on bagging and boosting classifiers for potential purchaser prediction. Journal of Retailing and Consumer Services. 2024;79. https://doi.org/10.1016/j.jretconser.2024.103854 Zhang W., Wang M. An improved deep forest model for prediction of e-commerce consumers' repurchase behavior. PLoS ONE. 2021;16(9). https://doi.org/10.1371/journal.pone.0255906 Zhou Sh., Hudin N.S. Advancing e-commerce user purchase prediction: Integration of time-series attention with event-based timestamp encoding and Graph Neural Network-Enhanced user profiling. PLoS ONE. 2024;19(4). https://doi.org/10.1371/journal.pone.0299087 Chauleva B., Capeska Bogatinoska D., Karadimce A. Optimizing Customer Journey through Advanced Analytics Techniques over Google Analytics 4 Data in Google BigQuery. WSEAS Transactions On Computers. 2024;23:336–346. https://doi.org/10.37394/23205.2024.23.33 Святов Р.С. Прогнозирование покупательского поведения пользователей интернет-магазинов на основе событийных данных. Моделирование, оптимизация и информационные технологии. 2025;13(4). https://doi.org/10.26102/2310-6018/2025.51.4.064

The authors declare that there are no conflicts of interest present.