To be or not to be... social: Incorporating simple social features in mobile game customer lifetime value predictions

Mobile games make up the largest segment of the games industry, in terms of revenue as well as players. Hundreds of thousands of games are available with most being free to download and play. In freemium games, revenue is predominantly generated by users making in-game purchases. As only a small fraction of users make purchases, predicting these users and their Customer Lifetime Value are key challenges in Game Analytics and currently barely explored in academic research. Furthermore, while social factors have been shown to be essential for retention in games in general, the impact on retention and monetization in mobile games is unexplored. In this paper, the problem of defining social features in freemium casual mobile games is addressed through a case study with over 200,000 players. The study evaluates the influence of specific types of social interactions typical of casual mobile games, on predictions of premium users and Customer Lifetime Value by applying classifiers and regression models respectively. Results indicate that social activity does not correlate with the tendency to become a premium user, but that social activity increases over time in a cohort