Combining Sequential and Aggregated Data for Churn Prediction in Casual Freemium Games

TL;DR

This paper explores combining sequential and aggregated data with neural networks to enhance churn prediction accuracy in freemium games, aiming to better retain players and increase revenue.

Contribution

It introduces a novel approach that integrates sequential and aggregated data for churn prediction, demonstrating improved accuracy over existing methods.

Findings

Combined data types improve prediction accuracy

Neural network architectures effectively utilize both data forms

Enhanced churn detection can lead to better player retention

Abstract

In freemium games, the revenue from a player comes from the in-app purchases made and the advertisement to which that player is exposed. The longer a player is playing the game, the higher will be the chances that he or she will generate a revenue within the game. Within this scenario, it is extremely important to be able to detect promptly when a player is about to quit playing (churn) in order to react and attempt to retain the player within the game, thus prolonging his or her game lifetime. In this article we investigate how to improve the current state-of-the-art in churn prediction by combining sequential and aggregate data using different neural network architectures. The results of the comparative analysis show that the combination of the two data types grants an improvement in the prediction accuracy over predictors based on either purely sequential or purely aggregated data.