Research on Machine Learning Models for Predicting Player Churn

Lilin Peng

2024

Abstract

In recent years, with the rapid development of the gaming industry, predicting player churn to improve game retention has become a key research area. This review summarizes the main research achievements and methods in the field of player churn prediction in recent years. By analyzing various machine learning algorithms such as random forest, decision tree, and logistic regression, the performance of these models in processing player behavior data and improving prediction accuracy is summarized. These studies demonstrate the effectiveness of data-driven methods in predicting player behavior, particularly when using long-term data frames, resulting in significantly improved prediction accuracy. In addition, it also indicates that incorporating personalized behavior and social relationships of players in the prediction model can enhance the accuracy of the model. In addition, this article explores the potential applications of cutting-edge methods such as multisource data fusion, real-time prediction and intervention, and long-term behavior analysis. The review concludes that future research should continue to focus on algorithm optimization and the application of emerging technologies to further improve the accuracy and adaptability of player churn prediction models, providing a scientific basis for game developers to develop more effective user retention strategies.

Paper Citation

in Harvard Style

Peng L. (2024). Research on Machine Learning Models for Predicting Player Churn. In Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM; ISBN 978-989-758-738-2, SciTePress, pages 112-121. DOI: 10.5220/0013234700004558

in Bibtex Style

@conference{mlscm24,
author={Lilin Peng},
title={Research on Machine Learning Models for Predicting Player Churn},
booktitle={Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM},
year={2024},
pages={112-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013234700004558},
isbn={978-989-758-738-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM
TI - Research on Machine Learning Models for Predicting Player Churn
SN - 978-989-758-738-2
AU - Peng L.
PY - 2024
SP - 112
EP - 121
DO - 10.5220/0013234700004558
PB - SciTePress