Abstract
Player churn is a prevalent challenge in the gaming industry. Most predictions of player churn utilize private datasets that are not easily accessible to the public. This study aims to investigate the performance of Logistic Regression, Random Forest, Support Vector Machines, and Ensemble Learning models using a dataset from a public API for predicting player churn, in comparison to other studies that typically rely on private game logs. In this research, the dataset consists of 418 unique player IDs, with a churn rate of 15%. After training the models, it was found that Logistic Regression and SVM achieved an accuracy of 95%, Random Forest achieved an accuracy of 96%, and Ensemble Learning, with Neural Network as the meta-learner, achieved an accuracy of 92%. These results underscore the validity of using public API data as an alternative data source for predicting player churn. n.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have