Utilizing Players’ Playtime Records for Churn Prediction: Mining Playtime Regularity

Churn prediction is an important topic in the free online game industry. Reducing the churn rate of a game significantly helps with the success of the game. Churn prediction helps a game operator identify possible churning players and keep them engaged in the game via appropriate operational strategies, marketing strategies, and/or incentives. Playtime-related features are some of the widely used universal features for most churn prediction models. In this article, we consider developing new universal features for churn predictions for long-term players based on playtime. In particular, we measure playtime regularity using the notion of entropy and cross-entropy from information theory. After computing playtime regularity of players from the datasets of six free online games of different types, we leverage information from the playtime regularity in the form of universal features for churn prediction. Experiments show that the proposed features are better at predicting churners compared to the baseline features, implying that the proposed features could utilize the information extracted from playtime more effectively than the related baseline playtime features.