Churn Prediction in Mobile Social Games: Towards a Complete Assessment Using Survival Ensembles

Abstract

Reducing user attrition, i.e. churn, is a broad challenge faced by several industries. In mobile social games, decreasing churn is decisive to increase player retention and rise revenues. Churn prediction models allow to understand player loyalty and to anticipate when they will stop playing a game. Thanks to these predictions, several initiatives can be taken to retain those players who are more likely to churn. Survival analysis focuses on predicting the time of occurrence of a certain event, churn in our case. Classical methods, like regressions, could be applied only when all players have left the game. The challenge arises for datasets with incomplete churning information for all players, as most of them still connect to the game. This is called a censored data problem and is in the nature of churn. Censoring is commonly dealt with survival analysis techniques, but due to the inflexibility of the survival statistical algorithms, the accuracy achieved is often poor. In contrast, novel ensemble learning techniques, increasingly popular in a variety of scientific fields, provide high-class prediction results. In this work, we develop, for the first time in the social games domain, a survival ensemble model which provides a comprehensive analysis together with an accurate prediction of churn. For each player, we predict the probability of churning as function of time, which permits to distinguish various levels of loyalty profiles. Additionally, we assess the risk factors that explain the predicted player survival times. Our results show that churn prediction by survival ensembles significantly improves the accuracy and robustness of traditional analyses, like Cox regression.

References in corpus (2)

• Random survival forests
• Discovering Playing Patterns: Time Series Clustering of Free-To-Play Game Data

Cited by in corpus (17)

• Customer Lifetime Value in Video Games Using Deep Learning and Parametric Models
• A Machine-Learning Item Recommendation System for Video Games
• Games and Big Data: A Scalable Multi-Dimensional Churn Prediction Model
• The Arousal video Game AnnotatIoN (AGAIN) Dataset
• Game Data Mining Competition on Churn Prediction and Survival Analysis using Commercial Game Log Data
• Predicting Game Difficulty and Churn Without Players
• Discovering Playing Patterns: Time Series Clustering of Free-To-Play Game Data
• Combining Sequential and Aggregated Data for Churn Prediction in Casual Freemium Games
• The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition
• A Time Series Approach To Player Churn and Conversion in Videogames
• From Non-Paying to Premium: Predicting User Conversion in Video Games with Ensemble Learning
• User Engagement in Mobile Health Applications
• Profiling Players with Engagement Predictions
• Midwifery Learning and Forecasting: Predicting Content Demand with User-Generated Logs
• Forecasting Player Behavioral Data and Simulating in-Game Events
• From the Hands of an Early Adopter's Avatar to Virtual Junkyards: Analysis of Virtual Goods' Lifetime Survival
• Explainability, risk modeling, and segmentation based customer churn analytics for personalized retention in e-commerce