Delivered at Casual Connect Eastern Europe, November 2014
In the face of rising CPIs across the board, boosting ARPU and keeping players for longer is the key to survival. With this in mind, predicting when a player will leave a game creates a unique opportunity to increase a player’s lifetime and revenue contribution. Players can be incentivized to stay in the game, strategically cross-linked to other games in the company’s portfolio or, as a last resort, be passed on to competing companies. Using data from two big live freemium games – Diamond Dash and Monster World – this talk sheds light on the feasibility of churn prediction in freemium games using Machine Learning, and evaluates the effectiveness of incentivization to extend players’ lifetime value.
2