Churn prediction of mobile and online casual games using play log data.

Seungwook Kim,Eunjung Lee,Daeyoung Choi,Wonjong Rhee,Wei-Xing Zhou

doi:10.1371/journal.pone.0180735

Abstract

Internet-connected devices, especially mobile devices such as smartphones, have become widely accessible in the past decade. Interaction with such devices has evolved into frequent and short-duration usage, and this phenomenon has resulted in a pervasive popularity of casual games in the game sector. On the other hand, development of casual games has become easier than ever as a result of the advancement of development tools. With the resulting fierce competition, now both acquisition and retention of users are the prime concerns in the field. In this study, we focus on churn prediction of mobile and online casual games. While churn prediction and analysis can provide important insights and action cues on retention, its application using play log data has been primitive or very limited in the casual game area. Most of the existing methods cannot be applied to casual games because casual game players tend to churn very quickly and they do not pay periodic subscription fees. Therefore, we focus on the new players and formally define churn using observation period (OP) and churn prediction period (CP). Using the definition, we develop a standard churn analysis process for casual games. We cover essential topics such as pre-processing of raw data, feature engineering including feature analysis, churn prediction modeling using traditional machine learning algorithms (logistic regression, gradient boosting, and random forests) and two deep learning algorithms (CNN and LSTM), and sensitivity analysis for OP and CP. Play log data of three different casual games are considered by analyzing a total of 193,443 unique player records and 10,874,958 play log records. While the analysis results provide useful insights, the overall results indicate that a small number of well-chosen features used as performance metrics might be sufficient for making important action decisions and that OP and CP should be properly chosen depending on the analysis goal.

Highlights

The global game market continues to grow, and it is expected to grow 9.6 percent per year between 2013 and 2018 with a stable revenue stream [1]
If not impossible, to unambiguously define casual games in a concise way, obviously casual games have become very popular with a high growth rate since 2000 [5] and they are the primary subject of this study
The play log data of casual games is relatively simple, and our results indicate that the prediction performance has little dependency on the choice of machine learning algorithm

Summary

Introduction

The global game market continues to grow, and it is expected to grow 9.6 percent per year between 2013 and 2018 with a stable revenue stream [1]. Casual games are widely based on freemium models where players might not return to the game for a few months or even for good without notifying anyone or paying monthly charges For such dormant players, it becomes impossible to have one single golden definition of churn, and an adequate definition needs to be adopted in accordance to the main analysis purpose—one might be interested in if a player will return in 10 days in one case, and 1 month in another case. The player is not paying subscription fee, and there will be no special action such as a service termination notice To avoid this problem, we need to compromise, set CP at a reasonable value, and make it possible to identify churners by looking into CP days of future. We derive interesting insights on mobile and online casual games through the churn prediction analysis

Related works

Findings

Conclusions