Understanding Player Engagement and In-Game Purchasing Behavior with Ensemble Learning

TL;DR

This paper analyzes player engagement and in-game purchasing behavior using ensemble learning, identifying different churn profiles and demonstrating how excluding certain sporadic or false churners improves prediction models.

Contribution

It introduces a detailed behavioral analysis of churn and purchase churn, and explores the impact of excluding specific player profiles on prediction accuracy.

Findings

Excluding certain sporadic players improves model performance.

Identified profiles of false churners and zombies.

Behavioral profiles help in better churn prediction.

Abstract

As video games attract more and more players, the major challenge for game studios is to retain them. We present a deep behavioral analysis of churn (game abandonment) and what we called "purchase churn" (the transition from paying to non-paying user). A series of churning behavior profiles are identified, which allows a classification of churners in terms of whether they eventually return to the game (false churners)--or start purchasing again (false purchase churners)--and their subsequent behavior. The impact of excluding some or all of these churners from the training sample is then explored in several churn and purchase churn prediction models. Our results suggest that discarding certain combinations of "zombies" (players whose activity is extremely sporadic) and false churners has a significant positive impact in all models considered.