An MLOps-centric Framework for Personalized Player Experience in Mobile Gaming Using MLflow

Abstract

The rapid growth of the mobile gaming industry has intensified competition, prompting developers to adopt advanced methods to improve engagement and retention. This paper presents an AI-driven platform for personalized mobile game development that applies Machine Learning Operations (MLOps) principles to tailor game content based on individual user behavior. Built on the MLflow (an open-source platform for managing the ML lifecycle) framework, the system ensures scalability, reproducibility, and efficient model lifecycle management. It integrates algorithms such as XGBoost, Random Forest, K-means, and DBSCAN for tasks including churn prediction, ad optimization, and adaptive difficulty adjustment. Multi-dimensional user data—covering session metrics, gameplay patterns, demographics, and monetization events—is processed through automated backend services. MLflow enables experiment tracking, model versioning, and artifact management across all development stages. Empirical results show strong predictive performance, with Random Forest achieving an F1-score of 0.8679 in churn prediction. The proposed MLOps-centric framework advances data-driven game development and establishes a replicable model for AI-powered personalization.

Keywords

• Artificial intelligence
• Machine learning operations
• Mobile gaming
• User behavior analysis

References

1. Z. Belyaeva, A. Petrosyan, and S. R. Shams, “Stakeholder data analysis in the video gaming industry: Implications for regional development,” EuroMed J. Bus., vol. 17, no. 3, pp. 333–349, 2022. doi: 10.1108/EMJB-10-2021-0150
2. S. Esiri, “A digital innovation model for enhancing competitive gaming engagement and user experience,” Int. J. Multidiscip. Res. Growth Eval., vol. 3, no. 1, pp. 752–760, 2022. doi: 10.54660/.IJMRGE.2022.3.1.752-760
3. P. D. Paraschos and D. E. Koulouriotis, “Game difficulty adaptation and experience personalization: A literature review,” Int. J. Hum.-Comput. Interact., vol. 39, no. 1, pp. 1–22, 2023. doi: 10.1080/10447318.2021.2020008
4. D. Ang and A. Mitchell, “Comparing effects of dynamic difficulty adjustment systems on video game experience,” in Proc. Annu. Symp. Comput.-Hum. Interact. Play, 2017, pp. 317–327. doi: 10.1145/3116595.3116623
5. D. Kreuzberger, N. Kühl, and S. Hirschl, “Machine learning operations (MLOps): Overview, definition, and architecture,” IEEE Access, vol. 11, pp. 31866–31879, 2023. doi: 10.1109/ACCESS.2023.3262138
6. K. Mustač, K. Bačić, L. Skorin-Kapov, and M. Sužnjević, “Predicting player churn of a free-to-play mobile video game using supervised machine learning,” Appl. Sci., vol. 12, no. 6, Art. no. 2795, 2022. doi: 10.3390/app12062795
7. A. Perišić and M. Pahor, “Clustering mixed-type player behavior data for churn prediction in mobile games,” Cent. Eur. J. Oper. Res., vol. 31, no. 1, pp. 165–190, 2023. doi: 10.1007/s10100-022-00802-8
8. F. A. Damastuti, K. Firmansyah, Y. M. Arif, T. Dutono, A. Barakbah, and M. Hariadi, “Dynamic level of difficulties using Q-learning and fuzzy logic,” IEEE Access, 2024. doi: 10.1109/ACCESS.2024.3457801

9. I. H. Sarker, M. M. Hoque, M. K. Uddin, and T. Alsanoosy, “Mobile data science and intelligent apps: Concepts, AI-based modeling and research directions,” Mob. Netw. Appl., vol. 26, no. 1, pp. 285–303, 2021. doi: 10.1007/s11036-020-01650-z
10. D. A. Tamburri, “Sustainable MLOps: Trends and challenges,” in Proc. 22nd Int. Symp. Symbolic Numer. Algorithms Sci. Comput. (SYNASC), 2020, pp. 17–23. doi: 10.1109/SYNASC51798.2020.00015
11. S. Mäkinen, H. Skogström, E. Laaksonen, and T. Mikkonen, “Who needs MLOps: What data scientists seek to accomplish and how can MLOps help?,” in Proc. IEEE/ACM 1st Workshop AI Eng.-Softw. Eng. AI (WAIN), 2021, pp. 109–112. doi: 10.1109/WAIN52551.2021.00024
12. R. Bozkır, M. Cicioğlu, A. Çalhan, and C. Toğay, “A new platform for machine-learning-based network traffic classification,” Comput. Commun., vol. 208, pp. 1–14, 2023. doi: 10.1016/j.comcom.2023.05.010
13. V. Spadari, F. Cerasuolo, G. Bovenzi, and A. Pescape, “An MLOps framework for explainable network intrusion detection with MLflow,” in Proc. IEEE Symp. Comput. Commun. (ISCC), 2024, pp. 1–6. doi: 10.1109/ISCC61673.2024.10733700
14. K. Kumar et al., “Game-changing intelligence: Unveiling the societal impact of artificial intelligence in game software,” Entertain. Comput., vol. 52, Art. no. 100862, 2025. doi: 10.1016/j.entcom.2024.100862
15. Y. Wang, L. Wang, and K. L. Siau, “Human-centered interaction in virtual worlds: A new era of generative artificial intelligence and metaverse,” Int. J. Hum.-Comput. Interact., vol. 41, no. 2, pp. 1459–1501, 2025. doi: 10.1080/10447318.2024.2316376
16. J. K. Ochab et al., “Mobile game evaluation method based on data mining of affective time series,” Sensors, vol. 25, no. 9, Art. no. 2756, 2025. doi: 10.3390/s25092756
17. M. M. Rezapour, A. Fatemi, and M. A. Nematbakhsh, “Learning experience assessment through players’ chat content in multiplayer online games,” Comput. Hum. Behav., vol. 151, Art. no. 108003, 2024. doi: 10.1016/j.chb.2023.108003
18. T. Wang et al., “Player2Vec: A language modeling approach to understand player behavior in games,” arXiv preprint arXiv:2404.04234, 2024. doi: 10.48550/arXiv.2404.0423