A Data Imputation Strategy to Enhance Online Game Churn Prediction, Considering Non-Login Periods

JaeHong Lee, Pavinee Rerkjirattikal and SangGyu Nam ()
Additional contact information
JaeHong Lee: School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, Thailand
Pavinee Rerkjirattikal: Department of Technology and Operations Management, Faculty of Business Administration, Kasetsart University, Bangkok 10900, Thailand
SangGyu Nam: School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, Thailand

Data, 2025, vol. 10, issue 7, 1-20

Abstract: User churn in online games refers to players becoming inactive for an extended period. Even a small increase in churn can lead to significant revenue loss, making churn prediction crucial for sustaining long-term player engagement. Although user churn prediction has been extensively studied, most existing approaches either ignore non-login periods or treat all inactivity uniformly, overlooking key behavioral differences. This study addresses this gap by categorizing non-login periods into three types, as follows: inactivity due to new or dormant users, genuine loss of interest, and temporary inaccessibility caused by external factors. These periods are treated as either non-existent or missing data and imputed using techniques such as mean or mode substitution, linear interpolation, and multiple imputation by chained equations (MICE). MICE was selected due to its ability to impute missing values more robustly by considering multivariate relationships. A random forest (RF) classifier, chosen for its interpretability and robustness to incomplete data, serves as the primary prediction model. Additionally, classifier chains are used to capture label dependencies, and principal component analysis (PCA) is applied to reduce dimensionality and mitigate overfitting. Experiments on real-world MMORPG data show that our approach improves predictive accuracy, achieving a micro-averaged AUC of above 0.92 and a weighted F1 score exceeding 0.70. These findings suggest that our approach improves churn prediction and offers actionable insights for supporting personalized player retention strategies.

Keywords: user churn prediction; online games; multiple imputation; machine learning (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/10/7/96/pdf (application/pdf)
https://www.mdpi.com/2306-5729/10/7/96/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:10:y:2025:i:7:p:96-:d:1685465

Access Statistics for this article

Data is currently edited by Ms. Becky Zhang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().