caerCentral Asian Economic ReviewCentral Asian Economic Review2789-43982789-4401Университет Нархоз10.52821/2789-4401-2025-5-212-226caer-1599Research ArticleЦИФРОВАЯ ЭКОНОМИКАDIGITAL ECONOMYМодели искусственного интеллекта для персонализации сервисов и оптимизации маркетинга АО «Air Astana»Artificial intelligence models for service personalization and marketing optimization: the case of Air Astana (JSC)https://orcid.org/0000-0002-7926-6877ДуйсебаеваА. М.DuisebayevaA. М.

Алматы 

Aizhan Duisebayeva – PhD, Associate Professor, School of Economics and Management 

Almaty 

aizhan.duisebaeva@narxoz.kzhttps://orcid.org/0009-0003-3685-2141ӘділбекқызыА.AdilbekkyzyA.

Алматы 

Aidana Adilbekkyzy – Student of "Marketing" 

Almaty 

aidana.adilbekkyzy@narxoz.kzhttps://orcid.org/0009-0000-0095-1939ТоқталыГ.ToktalyG.

Алматы 

Gulnur Toktaly – Student of "Marketing" 

Almaty 

gulnur.toktaly@narxoz.kzНАО «Университет Нархоз»КазахстанNarxoz UniversityKazakhstan20250512202505212226Copyright © Дуйсебаева А.М., Әділбекқызы А., Тоқталы Г., 20252025Дуйсебаева А.М., Әділбекқызы А., Тоқталы Г.Duisebayeva A.М., Adilbekkyzy A., Toktaly G.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://caer.narxoz.kz/jour/article/view/1599Цель исследования

Цель исследования: Исследование направлено на разработку персонализированных цифровых предложений для Air Astana с использованием искусственного интеллекта и методов машинного обучения с целью усиления уникальных конкурентных преимуществ – высокого качества сервиса и транзитной сети – и оценки их влияния на маркетинговую эффективность в 2010–2024 годах.

Методология

Методология: Применены системный и сравнительный анализ, экономико-математическое моделирование и социологическое интервьюирование. Использованы алгоритмы AI – collaborative filtering, content-based filtering, uplift modeling и reinforcement learning – для прогнозирования поведения потребителей и оптимизации персонализации.

Оригинальность/Научная новизна: Работа представляет собой первое комплексное исследование в авиационной отрасли Казахстана, демонстрирующее, что использование AI в персонализации способствует повышению конкурентоспособности Air Astana и эффективности маркетинговых инвестиций.

Результаты

Результаты: Разработанные модели повысили отклик цифровых кампаний на 15% и сократили маркетинговые расходы на 20%. Проверка показала высокую статистическую значимость (R² = 0,902).

Purpose

Purpose: The study aims to develop personalized digital offers for Air Astana through artificial intelligence (AI) and machine learning (ML) to strengthen its unique selling propositions (USPs) – high service quality and transit connectivity – and to measure their quantitative impact on marketing performance during 2010–2024.

Methodology

Methodology: A mixed approach combining system-based and comparative analysis, economic-mathematical modeling, and interview–survey techniques was applied. AI algorithms such as collaborative filtering, content-based filtering, uplift modeling, and reinforcement learning were used to predict consumer behavior and optimize personalization strategies.

Findings

Findings: The developed AI-driven personalization models improved digital campaign response rates by +15% and reduced marketing expenditures by –20%. Statistical validation showed a strong model fit (R² = 0.902), confirming that offer relevance significantly increases customer engagement and conversion probability.

Originality / Value

Originality / Value: This is the first comprehensive empirical study in Kazakhstan’s aviation sector integrating real airline data with AI-based personalization. The findings demonstrate that data-driven marketing decisions can enhance Air Astana’s competitiveness as a Eurasian transit hub and ensure more efficient budget allocation.

искусственный интеллектмаркетингперсонализациямашинное обучениеAir Astanaartificial intelligencemarketing personalizationuplift modelingAir Astanamachine learningReferencesChatterjee S., Rana N. P., Tamilmani K., Sharma A. The future of artificial intelligence in marketing: A systematic review // Journal of Business Research. – 2021. – Vol. 124. – P. 336–352. – DOI: 10.1016/j.jbusres.2020.11.041.Chatterjee, S., Rana, N. P., Tamilmani, K., & Sharma, A. (2021). The future of artificial intelligence in marketing: A systematic review. Journal of Business Research, 124, 336–352. https://doi.org/10.1016/j.jbusres.2020.11.041Bughin J., Seong J., Manyika J., Chui M., Joshi R. Notes from the AI frontier: Modeling the impact of AI on the world economy. – McKinsey Global Institute, 2018.Bughin, J., Seong, J., Manyika, J., Chui, M., & Joshi, R. (2018). Notes from the AI frontier: Modeling the impact of AI on the world economy. McKinsey Global Institute. Retrieved from https://www.mckinsey.com/featured-insights/artificial-intelligence/notes-from-the-ai-frontier-modeling-the-impact-of-ai-on-the-worldeconomyMcKinsey&Company+2McKinsey&Company+2Guerrini A., Ferri G., Rocchi S., Cirelli M., Piña V., Grieszmann A. Personalization @ scale in airlines: Combining the power of rich customer data, experiential learning, and revenue management // Journal of Revenue and Pricing Management. – 2023. – Vol. 22, № 2. – P. 171–180. – DOI: 10.1057/s41272-022-00404-8.Guerrini, A., Ferri, G., Rocchi, S., Cirelli, M., Piña, V., & Grieszmann, A. (2023). Personalization @ scale in airlines: Combining the power of rich customer data, experiential learning, and revenue management. Journal of Revenue and Pricing Management, 22(2), 171–180. https://doi.org/10.1057/s41272-022-00404-8Devriendt F., Van Belle J., Guns T., Verbeke W. Learning to rank for uplift modeling // IEEE Transactions on Knowledge and Data Engineering. – 2022. – Vol. 34, № 10. – P. 4888–4904. – DOI: 10.1109/TKDE.2022.3153950.Devriendt, F., Van Belle, J., Guns, T., & Verbeke, W. (2022). Learning to rank for uplift modeling. IEEE Transactions on Knowledge and Data Engineering, 34(10), 4888–4904. https://doi.org/10.1109/TKDE.2022.3153950Pazzani M. J., Billsus D. Content-based recommendation systems // In: The Adaptive Web. – Berlin: Springer, 2007. – P. 325–341. – DOI: 10.1007/978-3-540-72079-9_10.Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In The Adaptive Web (pp. 325–341). Springer. https://doi.org/10.1007/978-3-540-72079-9_10Bobadilla J., Ortega F., Hernando A., Gutierrez A. Recommender systems survey // Knowledge-Based Systems. – 2013. – Vol. 46. – P. 109–132. – DOI: 10.1016/j.knosys.2013.03.012.Bobadilla, J., Ortega, F., Hernando, A., & Gutierrez, A. (2013). Recommender systems survey. Knowledge-Based Systems, 46, 109–132. https://doi.org/10.1016/j.knosys.2013.03.012Jo H., Moon I., Rhee B. Dynamic pricing in airline revenue management using reinforcement learning // Expert Systems with Applications. – 2024. – Vol. 233. – Art. 120857. – DOI: 10.1016/j.eswa.2023.120857.Jo, H., Moon, I., & Rhee, B. (2024). Dynamic pricing in airline revenue management using reinforcement learning. Expert Systems with Applications, 233, Article 120857. https://doi.org/10.1016/j.eswa.2023.120857Olaya-Contreras D., Suárez-Andrés J., & García-Núñez J. A survey and benchmarking study of multitreatment uplift modelling // Data Mining and Knowledge Discovery. – 2020. – Vol. 34, No 5. – P. 1303–1336. – DOI: 10.1007/s10618-020-00702-yOlaya-Contreras, D., Suárez-Andrés, J., & García-Núñez, J. (2020). A survey and benchmarking study of multitreatment uplift modelling. Data Mining and Knowledge Discovery, 34(5), 1303–1336. https://doi.org/10.1007/s10618-020-00702-yRadcliffe N. J., Surry P. D. Uplift Modelling: Literature Survey and Experimental Evaluation // Big Data. – 2017. – Vol. 5, No 4. – P. 273–290. – DOI: 10.1089/big.2016.0074Radcliffe, N. J., & Surry, P. D. (2017). Uplift modelling: Literature survey and experimental evaluation. Big Data, 5(4), 273–290. https://doi.org/10.1089/big.2016.0074Chandra S., Verma S., Lim W. M., Kumar S., Donthu N. Personalization in personalized marketing: Trends and ways forward // Psychology & Marketing. – 2022. –Vol. 39, No 8. – P. 1529-1562. – DOI: 10.1002/mar.21670.Chandra, S., Verma, S., Lim, W. M., Kumar, S., & Donthu, N. (2022). Personalization in personalized marketing: Trends and ways forward. Psychology & Marketing, 39(8), 1529–1562. https://doi.org/10.1002/mar.21670Kapoor A., Dwivedi Y. K., Piercy N. Artificial intelligence in marketing: Evolution, challenges, and opportunities // European Journal of Marketing. – 2022. – Vol. 56, № 3. – P. 853–880. – DOI: 10.1108/EJM-12-2021-1009.Kapoor, A., Dwivedi, Y. K., & Piercy, N. (2022). Artificial intelligence in marketing: Evolution, challenges, and opportunities. European Journal of Marketing, 56(3), 853–880. https://doi.org/10.1108/EJM-12-2021-1009Alfaifi Y.H., Hasanain F., Ramayah T. Recommender Systems Applications: Data Sources, Features, Challenges and Future Trends // Information. – 2024. – Vol. 15, No. 10, Article 660. – DOI: 10.3390/info15100660.Alfaifi, Y. H., Hasanain, F., & Ramayah, T. (2024). Recommender systems applications: Data sources, features, challenges and future trends. Information, 15(10), Article 660. https://doi.org/10.3390/info15100660Aksoy N., Kabadayı E., Yılmaz C., Koçak Alan A. A Typology of Personalisation Practices in Marketing in the Digital Age // Journal of Marketing Management. – 2021. – Vol. 37, No. 11-12, – P. 1091-1122. – DOI: 10.1080/0267257X.2020.1866647Aksoy, N., Kabadayı, E., Yılmaz, C., & Koçak Alan, A. (2021). A typology of personalisation practices in marketing in the digital age. Journal of Marketing Management, 37(11–12), 1091–1122. https://doi.org/10.1080/0267257X.2020.1866647Jannach D., Jugovac M. Measuring the Business Value of Recommender Systems // ACM Transactions on Management Information Systems. – 2019. – Vol. 10, No. 4, Article 1. – DOI: 10.1145/3370082.Jannach, D., & Jugovac, M. (2019). Measuring the business value of recommender systems. ACM Transactions on Management Information Systems, 10(4), Article 1. https://doi.org/10.1145/3370082Zangerle E., Bauer C. Evaluating recommender systems: Survey and framework // ACM Computing Surveys. –2023. – Vol. 55, No 8: Article 170, 1-38 pp. – DOI: 10.1145/3556536.Zangerle, E., & Bauer, C. (2023). Evaluating recommender systems: Survey and framework. ACM Computing Surveys, 55(8), Article 170. https://doi.org/10.1145/3556536

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