<?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="en"><front><journal-meta><journal-id journal-id-type="publisher-id">donstu</journal-id><journal-title-group><journal-title xml:lang="en">Advanced Engineering Research (Rostov-on-Don)</journal-title><trans-title-group xml:lang="ru"><trans-title>Advanced Engineering Research (Rostov-on-Don)</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2687-1653</issn><publisher><publisher-name>Don State Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.23947/2687-1653-2026-26-1-2211</article-id><article-id custom-type="edn" pub-id-type="custom">FDZUZD</article-id><article-id custom-type="elpub" pub-id-type="custom">donstu-2591</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="en"><subject>INFORMATION TECHNOLOGY, COMPUTER SCIENCE AND MANAGEMENT</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАТИКА, ВЫЧИСЛИТЕЛЬНАЯ ТЕХНИКА И УПРАВЛЕНИЕ</subject></subj-group></article-categories><title-group><article-title>A Customer Lifetime Value-aware Framework for Strategic Churn Prediction Using Deep Learning</article-title><trans-title-group xml:lang="ru"><trans-title>Методология прогнозирования стратегического оттока клиентов с учётом их пожизненной ценности на основе глубокого обучения</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2042-2708</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ума Махешвари</surname><given-names>Гурусами</given-names></name><name name-style="western" xml:lang="en"><surname>Uma Maheswari</surname><given-names>Gurusamy</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ума Махешвари Гурусами, PhD, доцент, факультет компьютерных наук и инженерии</p><p>625701, штат Тамилнад, г. Вирудунагар</p><p>ResearcherID: X-1451-2019</p><p>Scopus Author ID: 57199165617</p></bio><bio xml:lang="en"><p>Uma Maheswari Gurusamy, PhD, Assistant Professor, Department of Computer Science and Engineering</p><p>Virudhunagar, Tamil Nadu, 625701</p><p>ResearcherID: X-1451-2019</p><p>Scopus Author ID: 57199165617</p></bio><email xlink:type="simple">uma.optimist@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3780-1472</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Минакши</surname><given-names>Анантараман</given-names></name><name name-style="western" xml:lang="en"><surname>Meenakshi</surname><given-names>Anantharaman</given-names></name></name-alternatives><bio xml:lang="ru"><p>Минакши Анантараман, магистр технических наук, PhD, профессор и заведующая факультетом компьютерных наук и инженерии</p><p>625701, штат Тамилнад, г. Вирудунагар</p><p>Scopus Author ID: 58546951800</p></bio><bio xml:lang="en"><p>Meenakshi Anantharaman, M.E., PhD, Professor, Head of the Department of Computer Science and Engineering</p><p>Virudhunagar, Tamil Nadu, 625701</p><p>Scopus Author ID: 58546951800</p></bio><email xlink:type="simple">meenakshirajesh11@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0009-0980-7699</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Рам Прасат</surname><given-names>Сельвамани</given-names></name><name name-style="western" xml:lang="en"><surname>Ram Prasath</surname><given-names>Selvamani</given-names></name></name-alternatives><bio xml:lang="ru"><p>Рам Прасат Сельвамани, доцент, факультет компьютерных наук и инженерии</p><p>625701, штат Тамилнад, г. Вирудунагар</p></bio><bio xml:lang="en"><p>Ram Prasath Selvamani, M.E., Assistant Professor, Department of Computer Science and Engineering</p><p>Virudhunagar, Tamil Nadu, 625701</p></bio><email xlink:type="simple">srpfxec@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-2529-6025</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Санджита</surname><given-names>Виджаяраджан</given-names></name><name name-style="western" xml:lang="en"><surname>Sangeetha</surname><given-names>Vijayarajan</given-names></name></name-alternatives><bio xml:lang="ru"><p>Санджита Виджаяраджан, магистр технических наук, доцент, факультет искусственного интеллекта и науки о данных</p><p>600089, штат Тамилнад, г. Ченнаи</p></bio><bio xml:lang="en"><p>Sangeetha Vijayarajan, M.E., Assistant Professor, Department of Artificial Intelligence and Data Science</p><p>Ramapuram, Chennai, Tamil Nadu, 600089</p></bio><email xlink:type="simple">vsangeethacse@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Инженерно-технологический колледж имени Камараджа</institution><country>Индия</country></aff><aff xml:lang="en"><institution>Kamaraj College of Engineering and Technology</institution><country>India</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Инженерный колледж имени Ишвари при Университете SRM</institution><country>Индия</country></aff><aff xml:lang="en"><institution>SRM Easwari Engineering College</institution><country>India</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>06</day><month>03</month><year>2026</year></pub-date><volume>26</volume><issue>1</issue><fpage>2211</fpage><lpage>2211</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Uma Maheswari G., Meenakshi A., Ram Prasath S., Sangeetha V., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Ума Махешвари Г., Минакши А., Рам Прасат С., Санджита В.</copyright-holder><copyright-holder xml:lang="en">Uma Maheswari G., Meenakshi A., Ram Prasath S., Sangeetha V.</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://www.vestnik-donstu.ru/jour/article/view/2591">https://www.vestnik-donstu.ru/jour/article/view/2591</self-uri><abstract><sec><title>Introduction</title><p>Introduction. Customer churn prediction represents a challenge in the current era of rapid digital transformation, hyper-competition, and data-driven marketing. In sectors such as telecommunications and banking, even marginal reductions in churn translate to significant revenue protection. Numerous companies employ uniform approaches, leading to the inefficient allocation of marketing resources and loss of loyal customers. Recent research has advanced along two largely separate domains. The first focuses on improving predictive accuracy through machine learning and deep learning techniques. Another stream, rooted in marketing science, emphasizes the economic dimension of churn, introducing Customer Lifetime Value (CLV) as a key metric. Existing solutions either maximize accuracy at high computational cost or discuss value-based strategy without providing a technical, implementable system. To bridge this gap, this paper aims to create, test, and present a comprehensive churn control system integrating customer lifetime value framework (CVLV). To achieve this, the following tasks are addressed: segmenting customers based on dynamic CLV and churn risk scores; evaluating the efficiency of various neural network configurations; and building a decision model that assigns optimal deep learning architectures for targeted retention, seamlessly integrating data analytics with corporate strategy.</p></sec><sec><title>Materials and Methods</title><p>Materials and Methods.The study was performed on two datasets: IBM Telco Customer Churn (7,043 customers, 21 features, binary churn) and Santander Customer Transaction Prediction (200,000 records, 200 numerical features, binary target variable). The data were preprocessed to address class imbalance and split 70-15-15 (train-validation-test) using 5-fold cross-validation. ANN (3–6 layers) and RNN/LSTM models were compared within the CVLV framework. The training utilized Adam optimizer, L2 regularization, dropout, early stopping, gradient clipping, and uniform batch size and epoch settings. The performance was evaluated based on accuracy, loss, and the Pareto frontier. Subsequently, customers were segmented by CLV/risk level, and retention strategies were assigned to the respective optimal models.</p></sec><sec><title>Results</title><p>Results. The comprehensive assessment of artificial neural networks (ANN) and recurrent neural networks (RNN) shows that RNN with 2 layers achieved marginally higher accuracy of 0.90, while the 3-layer ANN produced the best robustness with a loss of 0.25 with relatively similar predictive performance. With the CVLV framework, RNN 2L is assigned for high value, high risk relationships that need the most precision, ANN 3L is assigned for stable, high value relationships, and general RNN for low value customers.</p></sec><sec><title>Discussion</title><p>Discussion. This work has shown that the CVLV framework strategically optimizes churn prediction by aligning deep learning models with customer value-risk profiles. The data obtained confirm that ANN 3L provides optimal robustness while RNN 2L achieves superior accuracy for temporal patterns, together enabling more efficient and targeted retention interventions across industries. This approach can be deployed across the telecommunications, banking and retail sectors and facilitate a meaningful connection between technical model performance and strategic decision-making, enabling organizations to deploy retention efforts effectively by aligning model capability with the customer's value and probability of churn. The findings indicates that strategic model assignments based on CLV-risk profiles led to improved efficiencies associated with retention without compromising predictive reliability.</p></sec><sec><title>Conclusion</title><p>Conclusion. The main results are that the ANN 3L model provides the optimal balance of accuracy (0.875) and robustness (loss: 0.25) for churn prediction, while the RNN 2L achieves peak accuracy (0.90) for high-risk segments. The practical significance lies in the proposed CVLV framework, which enables businesses to strategically align deep learning model selection with customer lifetime value, improving retention efficiency. Further research will focus on integrating real-time CLV updates and validating the framework across additional industry domains. </p></sec></abstract><trans-abstract xml:lang="ru"><sec><title>Введение</title><p>Введение. Прогнозирование оттока клиентов приобретает особую актуальность в эпоху цифровой трансформации и обострения конкуренции. В таких секторах, как телекоммуникации и банковское дело, даже минимальное сокращение этого показателя способно заметно укрепить финансовые позиции. Многие компании применяют унифицированные подходы к удержанию клиентов, что приводит к нерациональному использованию ресурсов и утрате лояльных пользователей. Современные исследования фокусируются на двух ключевых направлениях. Первое из них посвящено совершенствованию точности прогнозирования посредством алгоритмов машинного обучения. Второе подчеркивает экономическую составляющую, включая пожизненную ценность клиента (CLV). Существующие подходы либо достигают максимальной точности за счет значительных вычислительных затрат, либо предлагают концепции, основанные на факторе ценности, но не имеющие практической технической реализации. Для преодоления этого разрыва в настоящей работе предлагается создать, испытать и представить комплексную систему контроля оттока клиентов с интеграцией жизненной ценности клиента (CVLV). Цель исследования заключается в разработке и верификации методологии контроля оттока с учетом жизненной ценности клиента (CVLV). Для ее достижения решаются следующие задачи: сегментация аудитории по динамическим метрикам CLV и вероятности ухода; оценка эффективности разнообразных конфигураций нейронных сетей; построение модели, которая выявляет наилучшие архитектуры глубокого обучения для целенаправленного удержания клиентов, гармонично сочетая аналитику данных с корпоративной стратегией.</p></sec><sec><title>Материалы и методы</title><p>Материалы и методы. Исследование проводилось на двух наборах данных: IBM Telco Customer Churn (7 043 клиента, 21 признак, бинарный отток) и Santander Customer Transaction Prediction (200 000 записей, 200 числовых признаков, бинарный целевой признак). Данные обрабатывались с учётом дисбаланса классов и делились в пропорции 70–15–15 с 5‑кратной кросс‑проверкой. Сравнивались ANN (3–6 слоёв) и RNN/LSTM в CVLV‑фреймворке. При обучении использовались Adam, L2-регуляризация, dropout, ранняя остановка, обрезка градиентов, единые настройки батча и эпох. Эффективность оценивалась по точности, функции потерь и Парето‑фронту. Затем клиенты сегментировались по уровню пожизненной ценности (CLV) и риску оттока. Затем моделям назначались стратегии.</p></sec><sec><title>Результаты исследования</title><p>Результаты исследования. Всесторонняя оценка искусственных (ANN) и рекуррентных (RNN) нейронных сетей показала, что двухслойная RNN обеспечивает незначительно более высокую точность (0,90), в то время как трёхслойная ANN демонстрирует наилучшую устойчивость с минимальными потерями (0,25) при сопоставимой прогностической эффективности. В рамках CVLV-фреймворка это определяет назначение моделей: RNN 2L используется для высокоценных клиентов с высоким риском оттока, где критически важна максимальная точность прогноза; ANN 3L — для стабильных высокоценных отношений; а базовая RNN — для клиентов с низкой ценностью.</p></sec><sec><title>Обсуждение</title><p>Обсуждение. Проведённое исследование продемонстрировало, что CVLV-фреймворк стратегически оптимизирует прогнозирование оттока клиентов за счёт согласования моделей глубокого обучения с ценностно-рисковыми профилями клиентов. Полученные данные подтверждают, что модель ANN 3L обеспечивает оптимальную устойчивость, а RNN 2L достигает максимальной точности при работе с временными закономерностями. Совместное их применение позволяет реализовывать более эффективные и целенаправленные мероприятия по удержанию клиентов в различных отраслях. Данный подход может быть внедрён в телекоммуникационном, банковском секторах, в сфере розничных продаж. Он устанавливает содержательную связь между техническими характеристиками модели и стратегическим принятием решений, позволяя организациям эффективно распределять усилия по удержанию, соотнеся возможности модели с ценностью клиентов и вероятностью их оттока. Результаты указывают на то, что стратегическое назначение моделей на основе CLV-рисковых профилей приводит к повышению эффективности мероприятий по удержанию без ущерба для надёжности прогнозов.</p></sec><sec><title>Заключение</title><p>Заключение. Основные результаты заключаются в том, что модель ANN 3L обеспечивает оптимальный баланс между точностью (0,875) и устойчивостью (потери: 0,25) в прогнозировании оттока, в то время как модель RNN 2L достигает максимальной точности (0,90) для сегментов с высоким риском. Практическая значимость исследования состоит в предложенном CVLV-фреймворке, который позволяет бизнесу стратегически соотносить выбор модели глубокого обучения с пожизненной ценностью клиента, повышая эффективность мероприятий по удержанию. Дальнейшие исследования будут сосредоточены на интеграции механизмов обновления CLV в реальном времени и валидации фреймворка в других отраслях.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>учёт пожизненной ценности клиента</kwd><kwd>прогнозирование оттока клиентов</kwd><kwd>ANN</kwd><kwd>RNN</kwd><kwd>точность</kwd><kwd>функция потерь</kwd><kwd>оптимальная модель</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Customer Lifetime Value-aware</kwd><kwd>churn prediction</kwd><kwd>ANN</kwd><kwd>RNN</kwd><kwd>accuracy</kwd><kwd>loss</kwd><kwd>optimum model</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Авторы выражают искреннюю благодарность кураторам и разработчикам наборов данных IBM Telco Customer Churn и Santander Customer Transaction Prediction за предоставление открытого доступа к данным, которые послужили основой для эмпирической валидации, проведенной в данном исследовании, а также признательны за вычислительные ресурсы, предоставленные учреждениями.</funding-statement><funding-statement xml:lang="en">The authors would like to express their sincere gratitude to the curators and maintainers of the IBM Telco Customer Churn and Santander Customer Transaction Prediction datasets for making their data publicly available, which was fundamental to the empirical validation conducted in this study. The computational resources provided by respective institutions are gratefully acknowledged.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Ascarza E. Retention Futility: Targeting High-Risk Customers Might Be Ineffective. Journal of Marketing Research. 2018;55(1):80–98. https://doi.org/10.1509/jmr.16.0163</mixed-citation><mixed-citation xml:lang="en">Ascarza E. Retention Futility: Targeting High-Risk Customers Might Be Ineffective. Journal of Marketing Research. 2018;55(1):80–98. https://doi.org/10.1509/jmr.16.0163</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Glady N, Baesens B, Croux C. Modeling Churn Using Customer Lifetime Value. European Journal of Operational Research. 2009;197(1):402–411. https://doi.org/10.1016/j.ejor.2008.06.027</mixed-citation><mixed-citation xml:lang="en">Glady N, Baesens B, Croux C. Modeling Churn Using Customer Lifetime Value. European Journal of Operational Research. 2009;197(1):402–411. https://doi.org/10.1016/j.ejor.2008.06.027</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Burez J, Van den Poel D. Handling Class Imbalance in Customer Churn Prediction. Expert Systems with Applications. 2009;36(3):4626–4636. https://doi.org/10.1016/j.eswa.2008.05.027</mixed-citation><mixed-citation xml:lang="en">Burez J, Van den Poel D. Handling Class Imbalance in Customer Churn Prediction. Expert Systems with Applications. 2009;36(3):4626–4636. https://doi.org/10.1016/j.eswa.2008.05.027</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Keramati A, Ghaneei H, Mirmohammadi SM. Developing a Prediction Model for Customer Churn from Electronic Banking Services Using Data Mining. Financial Innovation. 2016;2(1):10. https://doi.org/10.1186/s40854-016-0029-6</mixed-citation><mixed-citation xml:lang="en">Keramati A, Ghaneei H, Mirmohammadi SM. Developing a Prediction Model for Customer Churn from Electronic Banking Services Using Data Mining. Financial Innovation. 2016;2(1):10. https://doi.org/10.1186/s40854-016-0029-6</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Yiquing Huang, Fangzhou Zhu, Mingxuan Yuan, Ke Deng, Yanhua Li, Bing Ni, et al. Telco Churn Prediction with Big Data. In: Proc. ACM SIGMOD International Conference on Management of Data. New York, NY: Association for Computing Machinery; 2015. P. 607–618. https://doi.org/10.1145/2723372.2742794</mixed-citation><mixed-citation xml:lang="en">Yiquing Huang, Fangzhou Zhu, Mingxuan Yuan, Ke Deng, Yanhua Li, Bing Ni, et al. Telco Churn Prediction with Big Data. In: Proc. ACM SIGMOD International Conference on Management of Data. New York, NY: Association for Computing Machinery; 2015. P. 607–618. https://doi.org/10.1145/2723372.2742794</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Idris A, Khan A, Yeon Soo Lee. Intelligent Churn Prediction in Telecom: Employing mRMR Feature Selection and RotBoost Based Ensemble Classification. Applied Intelligence. 2013;39(3):659–672. https://doi.org/10.1007/s10489-013-0440-x</mixed-citation><mixed-citation xml:lang="en">Idris A, Khan A, Yeon Soo Lee. Intelligent Churn Prediction in Telecom: Employing mRMR Feature Selection and RotBoost Based Ensemble Classification. Applied Intelligence. 2013;39(3):659–672. https://doi.org/10.1007/s10489-013-0440-x</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kumar A, Sharma A. Predicting Customer Churn in Telecom Industry Using Machine Learning Techniques. Journal of Information and Optimization Sciences. 2020;41(2):479–488. https://doi.org/10.1080/02522667.2020.1761234</mixed-citation><mixed-citation xml:lang="en">Kumar A, Sharma A. Predicting Customer Churn in Telecom Industry Using Machine Learning Techniques. Journal of Information and Optimization Sciences. 2020;41(2):479–488. https://doi.org/10.1080/02522667.2020.1761234</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">López V, del Río S, Benítez JM, Herrera F. Cost-Sensitive Linguistic Fuzzy Rule-Based Classification Systems under the MapReduce Framework for Imbalanced Big Data. Fuzzy Sets and Systems. 2015;258:5–38. https://doi.org/10.1016/j.fss.2014.01.015</mixed-citation><mixed-citation xml:lang="en">López V, del Río S, Benítez JM, Herrera F. Cost-Sensitive Linguistic Fuzzy Rule-Based Classification Systems under the MapReduce Framework for Imbalanced Big Data. Fuzzy Sets and Systems. 2015;258:5–38. https://doi.org/10.1016/j.fss.2014.01.015</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Óskarsdóttir M, Bravo C, Sarraute C, Vanthienen J, Baesens B. The Value of Big Data for Credit Scoring: Enhancing Financial Inclusion Using Mobile Phone Data and Social Network Analytics. Applied Soft Computing. 2019;74:26–39. https://doi.org/10.1016/j.asoc.2018.10.004</mixed-citation><mixed-citation xml:lang="en">Óskarsdóttir M, Bravo C, Sarraute C, Vanthienen J, Baesens B. The Value of Big Data for Credit Scoring: Enhancing Financial Inclusion Using Mobile Phone Data and Social Network Analytics. Applied Soft Computing. 2019;74:26–39. https://doi.org/10.1016/j.asoc.2018.10.004</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Amin A, Shehzad S, Khan C, Ali I, Anwar S. Churn Prediction in Telecommunication Industry Using Rough Set Approach. In book: New Trends in Computational Collective Intelligence. Cham: Springer; 2015. P. 83–95.</mixed-citation><mixed-citation xml:lang="en">Amin A, Shehzad S, Khan C, Ali I, Anwar S. Churn Prediction in Telecommunication Industry Using Rough Set Approach. In book: New Trends in Computational Collective Intelligence. Cham: Springer; 2015. P. 83–95.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Zengyuan Wu, Lizheng Jing, Bei Wu, Lingmin Jin. A PCA-AdaBoost Model for E-commerce Customer Churn Prediction. Annals of Operations Research. 2025;350:537–554. https://doi.org/10.1007/s10479-022-04526-5</mixed-citation><mixed-citation xml:lang="en">Zengyuan Wu, Lizheng Jing, Bei Wu, Lingmin Jin. A PCA-AdaBoost Model for E-commerce Customer Churn Prediction. Annals of Operations Research. 2025;350:537–554. https://doi.org/10.1007/s10479-022-04526-5</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Bhargava M, Singh S, Sharma J, Vinod DF. Telecom Customer Churn Prediction. In book: Proceedings of the International Conference on Innovative Computing and Communication (ICICC). Singapore; Springer; 2021. P. 325–333. https://doi.org/10.1007/978-981-16-6601-8_30</mixed-citation><mixed-citation xml:lang="en">Bhargava M, Singh S, Sharma J, Vinod DF. Telecom Customer Churn Prediction. In book: Proceedings of the International Conference on Innovative Computing and Communication (ICICC). Singapore; Springer; 2021. P. 325–333. https://doi.org/10.1007/978-981-16-6601-8_30</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Achari KMT, Binu S, Thomas KT. A Neural Network-based Customer Churn Prediction Algorithm for the Telecom Sector. In book: IOT and Smart Systems. Singapore; Springer; 2022. P. 215–227. https://doi.org/10.1007/978-981-16-3945-6_22</mixed-citation><mixed-citation xml:lang="en">Achari KMT, Binu S, Thomas KT. A Neural Network-based Customer Churn Prediction Algorithm for the Telecom Sector. In book: IOT and Smart Systems. Singapore; Springer; 2022. P. 215–227. https://doi.org/10.1007/978-981-16-3945-6_22</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Saanchay PM, Thomas KT. An Approach for Credit Card Churn Prediction Using Gradient Descent. In book: IOT and Smart Systems. Singapore; Springer; 2022. P. 689–697. https://doi.org/10.1007/978-981-16-3945-6_68</mixed-citation><mixed-citation xml:lang="en">Saanchay PM, Thomas KT. An Approach for Credit Card Churn Prediction Using Gradient Descent. In book: IOT and Smart Systems. Singapore; Springer; 2022. P. 689–697. https://doi.org/10.1007/978-981-16-3945-6_68</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Zhijie Zhao, Wanting Zhou, Zeguo Qiu, Ang Li, Jiaying Wang. Research on Ctrip Customer Churn Prediction Model Based on Random Forest. In book: Business Intelligence and Information Technology. Cham; Springer; 2021. P. 511–523. https://doi.org/10.1007/978-3-030-92632-8_48</mixed-citation><mixed-citation xml:lang="en">Zhijie Zhao, Wanting Zhou, Zeguo Qiu, Ang Li, Jiaying Wang. Research on Ctrip Customer Churn Prediction Model Based on Random Forest. In book: Business Intelligence and Information Technology. Cham; Springer; 2021. P. 511–523. https://doi.org/10.1007/978-3-030-92632-8_48</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Garimella B, Prasad GVSNRV, Krishna Prasad MHM. Adaptive Optimization-enabled Neural Networks to Handle the Imbalance Churn Data in Churn Prediction. International Journal of Computational Intelligence and Applications. 2021;20(4):2150025. https://doi.org/10.1142/S1469026821500255</mixed-citation><mixed-citation xml:lang="en">Garimella B, Prasad GVSNRV, Krishna Prasad MHM. Adaptive Optimization-enabled Neural Networks to Handle the Imbalance Churn Data in Churn Prediction. International Journal of Computational Intelligence and Applications. 2021;20(4):2150025. https://doi.org/10.1142/S1469026821500255</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Li X, Zhang Y. Customer Churn Prediction in the Banking Industry Using Machine Learning Techniques. Journal of Banking and Financial Technology. 2020;4:125–138. https://doi.org/10.1007/s42786-020-00018-7</mixed-citation><mixed-citation xml:lang="en">Li X, Zhang Y. Customer Churn Prediction in the Banking Industry Using Machine Learning Techniques. Journal of Banking and Financial Technology. 2020;4:125–138. https://doi.org/10.1007/s42786-020-00018-7</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Singh R, Kaur H. A Comparative Study of Machine Learning Algorithms for Customer Churn Prediction in Telecom Industry. International Journal of Advanced Computer Science and Applications. 2019;10(6):348–355.</mixed-citation><mixed-citation xml:lang="en">Singh R, Kaur H. A Comparative Study of Machine Learning Algorithms for Customer Churn Prediction in Telecom Industry. International Journal of Advanced Computer Science and Applications. 2019;10(6):348–355.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Kim D, Lee J. Hybrid Deep Learning Framework for CLV-aware Churn Segmentation. IEEE Access. 2022;10:112340–112352. https://doi.org/10.1109/ACCESS.2022.3210056</mixed-citation><mixed-citation xml:lang="en">Kim D, Lee J. Hybrid Deep Learning Framework for CLV-aware Churn Segmentation. IEEE Access. 2022;10:112340–112352. https://doi.org/10.1109/ACCESS.2022.3210056</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang T, Xu H, Wang Q. CLV-driven Customer Churn Prediction via Explainable Deep Learning. Decision Support Systems. 2023;168:113923. https://doi.org/10.1016/j.dss.2023.113923</mixed-citation><mixed-citation xml:lang="en">Zhang T, Xu H, Wang Q. CLV-driven Customer Churn Prediction via Explainable Deep Learning. Decision Support Systems. 2023;168:113923. https://doi.org/10.1016/j.dss.2023.113923</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Gupta A, Das S. Explainable AI for Churn Prediction in Telecom Using SHAP and LIME. Knowledge-Based Systems. 2021;228:107302. https://doi.org/10.1016/j.knosys.2021.107302</mixed-citation><mixed-citation xml:lang="en">Gupta A, Das S. Explainable AI for Churn Prediction in Telecom Using SHAP and LIME. Knowledge-Based Systems. 2021;228:107302. https://doi.org/10.1016/j.knosys.2021.107302</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Raj A, Srinivas R. Comparative Analysis of RNN and LSTM in Telecom Churn Prediction. International Journal of Data Science and Analytics. 2023;15(3):251–266.</mixed-citation><mixed-citation xml:lang="en">Raj A, Srinivas R. Comparative Analysis of RNN and LSTM in Telecom Churn Prediction. International Journal of Data Science and Analytics. 2023;15(3):251–266.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou L, Chen Y. Cross-Sectoral Deep Transfer Learning for Churn Prediction. Information Sciences. 2022;601:32–45. https://doi.org/10.1016/j.ins.2022.03.015</mixed-citation><mixed-citation xml:lang="en">Zhou L, Chen Y. Cross-Sectoral Deep Transfer Learning for Churn Prediction. Information Sciences. 2022;601:32–45. https://doi.org/10.1016/j.ins.2022.03.015</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Martinez P, Alvarez R. Cost-aware Neural Architecture Optimization for Churn Management. Expert Systems with Applications. 2023;222:119918. https://doi.org/10.1016/j.eswa.2023.119918</mixed-citation><mixed-citation xml:lang="en">Martinez P, Alvarez R. Cost-aware Neural Architecture Optimization for Churn Management. Expert Systems with Applications. 2023;222:119918. https://doi.org/10.1016/j.eswa.2023.119918</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Kim S, Park J, Lee Y. A Multi-Objective Deep Reinforcement Learning Approach to Churn Prevention. Applied Intelligence. 2023;53(1):215–230. https://doi.org/10.1007/s10489-022-03719-2</mixed-citation><mixed-citation xml:lang="en">Kim S, Park J, Lee Y. A Multi-Objective Deep Reinforcement Learning Approach to Churn Prevention. Applied Intelligence. 2023;53(1):215–230. https://doi.org/10.1007/s10489-022-03719-2</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Anderson M, Clark S. Resource Optimization in Customer Retention Using AI-based Cost Modeling. Journal of Business Analytics. 2022;5(2):145–160. https://doi.org/10.1080/2573234X.2022.2035643</mixed-citation><mixed-citation xml:lang="en">Anderson M, Clark S. Resource Optimization in Customer Retention Using AI-based Cost Modeling. Journal of Business Analytics. 2022;5(2):145–160. https://doi.org/10.1080/2573234X.2022.2035643</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Mehta R, Patel D. Dynamic CLV Estimation in Real-Time Churn Prediction Pipelines. Neural Networks. 2024;174:250–267. https://doi.org/10.1016/j.neunet.2024.03.007</mixed-citation><mixed-citation xml:lang="en">Mehta R, Patel D. Dynamic CLV Estimation in Real-Time Churn Prediction Pipelines. Neural Networks. 2024;174:250–267. https://doi.org/10.1016/j.neunet.2024.03.007</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Wang J, Liu F, Zhao L. Federated Deep Learning for Privacy-Preserving Churn Analysis. ACM Transactions on Privacy and Security. 2024;27(2):1–20. https://doi.org/10.1145/3601198</mixed-citation><mixed-citation xml:lang="en">Wang J, Liu F, Zhao L. Federated Deep Learning for Privacy-Preserving Churn Analysis. ACM Transactions on Privacy and Security. 2024;27(2):1–20. https://doi.org/10.1145/3601198</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Coussement K, Van den Poel D. Improving Customer Attrition Prediction by Integrating Emotions from Client/Company Interaction Emails and Evaluating Multiple Classifiers. Expert Systems with Applications. 2008;36(3):6127–6134. https://doi.org/10.1016/j.eswa.2008.07.021</mixed-citation><mixed-citation xml:lang="en">Coussement K, Van den Poel D. Improving Customer Attrition Prediction by Integrating Emotions from Client/Company Interaction Emails and Evaluating Multiple Classifiers. Expert Systems with Applications. 2008;36(3):6127–6134. https://doi.org/10.1016/j.eswa.2008.07.021</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">Hewamalage H, Bergmeir C, Bandara K. Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions. International Journal of Forecasting. 2021;37(1):388–427. https://doi.org/10.1016/j.ijforecast.2020.06.008</mixed-citation><mixed-citation xml:lang="en">Hewamalage H, Bergmeir C, Bandara K. Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions. International Journal of Forecasting. 2021;37(1):388–427. https://doi.org/10.1016/j.ijforecast.2020.06.008</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Khan MA, Saqib S, Alyas T, Anees Ur Rehman, Saeed Y, Zeb A. Effective Demand Forecasting Model Using Business Intelligence Empowered with Machine Learning. IEEE Access. 2020;8(1):16013–116023. https://doi.org/10.1109/ACCESS.2020.3004209</mixed-citation><mixed-citation xml:lang="en">Khan MA, Saqib S, Alyas T, Anees Ur Rehman, Saeed Y, Zeb A. Effective Demand Forecasting Model Using Business Intelligence Empowered with Machine Learning. IEEE Access. 2020;8(1):16013–116023. https://doi.org/10.1109/ACCESS.2020.3004209</mixed-citation></citation-alternatives></ref><ref id="cit32"><label>32</label><citation-alternatives><mixed-citation xml:lang="ru">Rezvanov VK, Romakina OM, Zaytseva EV. Forecasting Delivery Time of Goods in Supply Chains Using Machine Learning Methods. Advanced Engineering Research (Rostov-on-Don). 2025;25(2):120–128. https://doi.org/10.23947/2687-1653-2025-25-2-120-128</mixed-citation><mixed-citation xml:lang="en">Rezvanov VK, Romakina OM, Zaytseva EV. Forecasting Delivery Time of Goods in Supply Chains Using Machine Learning Methods. Advanced Engineering Research (Rostov-on-Don). 2025;25(2):120–128. https://doi.org/10.23947/2687-1653-2025-25-2-120-128</mixed-citation></citation-alternatives></ref><ref id="cit33"><label>33</label><citation-alternatives><mixed-citation xml:lang="ru">Topilin IV, Han M, Feofilova AA, Beskopylny NA. Comparative Analysis of Neural Network and Machine Learning Models for Short-Term Traffic Flow Prediction on Shenzhen Expressway. Advanced Engineering Research (Rostov-on-Don). 2025;25(4):2215. https://doi.org/10.23947/2687-1653-2025-25-4-2215</mixed-citation><mixed-citation xml:lang="en">Topilin IV, Han M, Feofilova AA, Beskopylny NA. Comparative Analysis of Neural Network and Machine Learning Models for Short-Term Traffic Flow Prediction on Shenzhen Expressway. Advanced Engineering Research (Rostov-on-Don). 2025;25(4):2215. https://doi.org/10.23947/2687-1653-2025-25-4-2215</mixed-citation></citation-alternatives></ref><ref id="cit34"><label>34</label><citation-alternatives><mixed-citation xml:lang="ru">Samoylenko VV. Concept of a Multilevel Network Infrastructure for Monitoring Agricultural Facilities Based on Wireless Sensor Networks. Advanced Engineering Research (Rostov-on-Don). 2025;25(4):2238. https://doi.org/10.23947/2687-1653-2025-25-4-2238</mixed-citation><mixed-citation xml:lang="en">Samoylenko VV. Concept of a Multilevel Network Infrastructure for Monitoring Agricultural Facilities Based on Wireless Sensor Networks. Advanced Engineering Research (Rostov-on-Don). 2025;25(4):2238. https://doi.org/10.23947/2687-1653-2025-25-4-2238</mixed-citation></citation-alternatives></ref><ref id="cit35"><label>35</label><citation-alternatives><mixed-citation xml:lang="ru">Martinez P, Alvarez R. Economic-aware Deep Learning for ROI-focused Model Selection. Expert Systems with Applications. 2023;222:119918. https://doi.org/10.1016/j.eswa.2023.119918</mixed-citation><mixed-citation xml:lang="en">Martinez P, Alvarez R. Economic-aware Deep Learning for ROI-focused Model Selection. Expert Systems with Applications. 2023;222:119918. https://doi.org/10.1016/j.eswa.2023.119918</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>
