User activity decay in mobile games determined by simple differential equations?

Decay of population level daily user activity in Tribeflame Ltd.'s mobile games is found to be determined by elementary differential equations. We describe practical methods for investigating laws underlying the decay of daily user activity in a given cohort, known as retention in the gaming industry. Simple decay patterns are found to accurately describe this evolution. In addition to being of academic interest in sharing parallels to population growth and decay dynamics, this finding has immediate applications in the mobile games industry. Utilizing this finding allows using smaller cohorts of users in intermittent paid acquisition tests and enables game performance forecasting over long timespans.

[1]  Christian Bauckhage,et al.  How players lose interest in playing a game: An empirical study based on distributions of total playing times , 2012, 2012 IEEE Conference on Computational Intelligence and Games (CIG).

[2]  Jukka Heikkonen,et al.  Modelling user retention in mobile games , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[3]  Christian Bauckhage,et al.  The Playtime Principle: Large-scale cross-games interest modeling , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[4]  G. M. Laslett,et al.  GENERALIZATIONS OF POWER-LAW DISTRIBUTIONS APPLICABLE TO SAMPLED FAULT-TRACE LENGTHS : MODEL CHOICE, PARAMETER ESTIMATION AND CAVEATS , 1999 .

[5]  Christian Bauckhage,et al.  Mathematical Models of Fads Explain the Temporal Dynamics of Internet Memes , 2013, ICWSM.

[6]  Debanjan Saha,et al.  A long-term study of a popular MMORPG , 2007, NetGames '07.

[7]  Gordon Johnston,et al.  Statistical Models and Methods for Lifetime Data , 2003, Technometrics.

[8]  Pasquale Cirillo,et al.  Are your data really Pareto distributed , 2013, 1306.0100.

[9]  Brent E. Harrison,et al.  An Analytic and Psychometric Evaluation of Dynamic Game Adaption for Increasing Session-Level Retention in Casual Games , 2015, IEEE Transactions on Computational Intelligence and AI in Games.

[10]  Arnav Jhala,et al.  Modeling Player Retention in Madden NFL 11 , 2011, IAAI.

[11]  Cristina V. Lopes,et al.  Retention and progression: Seven months in World of Warcraft , 2014, FDG.

[12]  Kuan-Ta Chen,et al.  Effect of Network Quality on Player Departure Behavior in Online Games , 2009, IEEE Transactions on Parallel and Distributed Systems.

[13]  M. Newman.  Power laws, Pareto distributions and Zipf's law , 2005 .

[14]  Saleem N. Bhatti,et al.  Modelling user behaviour in networked games , 2001, MULTIMEDIA '01.

[15]  Chris GauthierDickey,et al.  Characterizing Virtual Populations in Massively Multiplayer Online Role-Playing Games , 2010, MMM.

[16]  D. Kleinbaum,et al.  Survival Analysis: A Self-Learning Text. , 1996 .

[17]  Kuan-Ta Chen,et al.  On prophesying online gamer departure , 2009, 2009 8th Annual Workshop on Network and Systems Support for Games (NetGames).

[18]  J. Whitehead,et al.  Why players start and stop playing a Chinese social network game , 2013 .

[19]  Sam Devlin,et al.  Predicting player disengagement and first purchase with event-frequency based data representation , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[20]  Boi Faltings,et al.  Hidden Markov models for churn prediction , 2015, 2015 SAI Intelligent Systems Conference (IntelliSys).

[21]  A. Ghasemi,et al.  Normality Tests for Statistical Analysis: A Guide for Non-Statisticians , 2012, International journal of endocrinology and metabolism.

[22]  Debanjan Saha,et al.  Measurement-based characterization of a collection of on-line games , 2005, IMC '05.

[23]  Christian Bauckhage,et al.  Predicting Purchase Decisions in Mobile Free-to-Play Games , 2015, AIIDE.

[24]  Christian Bauckhage,et al.  Predicting player churn in the wild , 2014, 2014 IEEE Conference on Computational Intelligence and Games.