Prediction of Player Churn in Mobile Games Using Classification Algorithms

Abstract

This study aims to predict player churn in a mobile game using machine learning algorithms. A behavioural dataset from Kaggle was used, and five key features were extracted through feature engineering: success rate, average duration, help usage, number of levels played, and remaining step rate. These features were used as inputs for the three classification models. Random Forest (RF), XGBoost, and Logistic Regression (LR) algorithms were used for model development for the prediction. The model performances were evaluated based on the evaluation metrics. Among all the models, RF achieved the highest overall accuracy (0.70) and strong recall for churned users (0.84). XGBoost showed the highest recall for churn (0.90). LR offered a balanced performance. The most influential predic tors were avg_reststep, level_count, and avg_duration. The findings showed the usefulness of behavioural features and machine learning algorithms in early churn detection. These results can support game developers in designing targeted interventions to retain users and reduce churn.

Keywords

• Churn Rate
• Mobile Games
• Classification Mdels
• Machine Learning
• Player Churn

References

1. Alomari, K. M., Ncube, C., & Shaalan, K. (2018). Predicting success of a mobile game: A proposed data analytics-based prediction model. In Proceedings of the International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE 2018) (pp. 587–598). Springer. https://doi.org/10.1007/978-3-319-92058-0_12 google scholar
2. Alves, J., Lange, S., Lenz, M., & Riedmiller, M. (2014). Case study: Behavioral prediction of future revenues in freemium games. In Proceedings of the Workshop on New Challenges in Neural Computation 2014 (NCNC 2014) (pp. 26–33). google scholar
3. Arik, K., Gezer, M., & Tayali, S. T. (2022). The study of indicators affecting customer churn in MMORPG games with machine learning models. Upravlenets, 13(6), 70–85. https://doi.org/10.29141/2218-5003-2022-13-6-6 google scholar
4. Banerjee, T., Mukherjee, G., Dutta, S., & Ghosh, P. (2020). A large-scale constrained joint modeling approach for predicting user activity, engagement, and churn with application to freemium mobile games. Journal of the American Statistical Association, 115(531), 1277–1290. Retrieved from https://doi.org/10.1080/01621459.2019.1611584 google scholar
5. Burelli, P. (2019). Predicting customer lifetime value in free-to-play games. In D. S. Alexandrova & L. Calefato (Eds.), Data analytics applications in gaming and entertainment (pp. 129–146). CRC Press. https://www.taylorfrancis.com/chapters/edit/10.1201/9780429029023-9 google scholar
6. Chauhan, S., Mittal, M., Woźniak, M., Gupta, S., & Pérez de Prado, R. (2021). Predicting churn in mobile games using explainable machine learning. google scholar
7. Symmetry, 13(8), 1545. https://doi.org/10.3390/sym13081545 google scholar
8. David, D., & Zahra, A. (2024). Player Churn Prediction in Free to Play Game Using Ensemble Learning. Action Research Literate, 8(4), 543–549. https://doi.org/10.46799/arl.v8i4.280 google scholar

9. Hadiji, F., Sifa, R., Drachen, A., Thurau, C., Kersting, K., & Bauckhage, C. (2014). Predicting player churn in the wild. In 2014 IEEE Conference on Computational Intelligence and Games (CIG) (S. 1–8). IEEE. https://doi.org/10.1109/CIG.2014.6932876 google scholar
10. Jang, K., Kim, J., & Yu, B. (2021). On Analyzing Churn Prediction in Mobile Games. arXiv preprint. https://doi.org/10.48550/arXiv.2104.05554 google scholar
11. Kilimci, Z. H., Yörük, H., & Akyokuş, S. (2020). Sentiment analysis based churn prediction in mobile games using word embedding models and deep learning algorithms. In 2020 International Conference on Innovations in Intelligent Systems and Applications (INISTA) (pp. 1–6). IEEE. https://doi.org/10.1109/INISTA49547.2020.9194624 google scholar
12. Kim, S., Choi, D., Lee, E., & Rhee, W. (2017). Churn prediction of mobile and online casual games using play log data. PLOS ONE, 12(7), e0180735. https://doi.org/10.1371/journal.pone.0180735 google scholar
13. Liu, X., Xie, M., Wen, X., Chen, R., Ge, Y., Duffield, N., & Wang, N. (2020). Micro- and macro-level churn analysis of large-scale mobile games. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (CIKM ’20) (pp. 2617–2624). ACM. https://doi.org/10.1145/3340531.3412730 google scholar
14. Milošević, M., Živić, N., & Andjelković, I. (2017). Early churn prediction with personalized targeting in mobile social games. In 2017 IEEE 5th International Conference on Serious Games and Applications for Health (SeGAH) (pp. 1–8). IEEE. https://doi.org/10.1016/j.eswa.2017.04.056 google scholar
15. Mulla, R., et al. (2025). Predicting Player Churn in the Gaming Industry: A Machine Learning Framework for Enhanced Retention Strategies. Journal of Current Science and Technology, 15(2), Article 103. https://doi.org/10.59796/jcst.V15N2.2025.103 google scholar
16. Peng, L. (2024). Research on Machine Learning Models for Predicting Player Churn. MLSCM 2024. https://doi.org/10.5220/0013234700004558 google scholar
17. Perišić, A., & Pahor, M. (2021). RFM-LIR feature framework for churn prediction in the mobile games market. Expert Systems with Applications, 186, 115748. https://doi.org/10.1109/TG.2021.3067114 google scholar
18. Runge, J., Gao, P., Garcin, F., & Faltings, B. (2014, August). Churn prediction for high-value players in casual social games. In 2014 IEEE Conference on Computational Intelligence and Games (CIG) (pp. 1–8). IEEE. https://doi.org/10.1109/CIG.2014.6932875 google scholar
19. Sifa, R., Hadiji, F., Runge, J., Drachen, A., Kersting, K., & Bauckhage, C. (2015). Predicting purchase decisions in mobile free-to-play games. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 11(1), 79–85. https://ojs.aaai.org/index.php/AIIDE/article/view/12788 google scholar