Predicting the monetization percentage with survival analysis in free-to-play games

Understanding and predicting player monetization is very important, because the free-to-play revenue model is so common. Many game developers now face a new challenge of getting users to buy in the game rather than getting users to buy the game. In this paper, we present a method to predict what percentage of all players will eventually monetize for a limited follow-up game data set. We assume that the data is described by a survival analysis based cure model, which can be applied to unlabeled data collected from any free-to-play game. The model has latent variables, so we solve the optimal parameters of the model with the Expectation Maximization algorithm. The result is a simple iterative algorithm, which returns the estimated monetization percentage and the estimated monetization rate in the data set.