Utilizing Players' In-game Time Spending Records for Churn Prediction: Mining In-game Time Spending Regularity
In the free online game industry, churn prediction is an important research topic. 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. Time spending related features are some of the widely used universal features for most churn prediction models. In this paper, we consider developing new universal features for churn predictions for long-term players based on player in-game time spending. In particular, we measure player time spending regularity using the notion of entropy and cross-entropy from information theory as the metric to characterize variance and change in the in-game time spent by a player, from data sets of six free online games of different types. We leverage information from players' in-game time spending regularity in the form of universal features for churn prediction. Experiments show that our developed features are better at predicting churners compared to baseline features. Thus, the experiment results imply that our proposed features could utilize the information extracted from players' in-game time spending more effectively than related baseline time spending features.
READ FULL TEXT