A comparison of methods for player clustering via behavioral telemetry

The analysis of user behavior in digital games has been aided by the introduction of user telemetry in game development, which provides unprecedented access to quantitative data on user behavior from the installed game clients of the entire population of players. Player behavior telemetry datasets can be exceptionally complex, with features recorded for a varying population of users over a temporal segment that can reach years in duration. Categorization of behaviors, whether through descriptive methods (e.g. segmention) or unsupervised/supervised learning techniques, is valuable for finding patterns in the behavioral data, and developing profiles that are actionable to game developers. There are numerous methods for unsupervised clustering of user behavior, e.g. k-means/c-means, Non-negative Matrix Factorization, or Principal Component Analysis. Although all yield behavior categorizations, interpretation of the resulting categories in terms of actual play behavior can be difficult if not impossible. In this paper, a range of unsupervised techniques are applied together with Archetypal Analysis to develop behavioral clusters from playtime data of 70,014 World of Warcraft players, covering a five year interval. The techniques are evaluated with respect to their ability to develop actionable behavioral profiles from the dataset.

[1]  Bruce Phillips,et al.  Tracking real-time user experience (TRUE): a comprehensive instrumentation solution for complex systems , 2008, CHI.

[2]  Christian Bauckhage,et al.  Making Archetypal Analysis Practical , 2009, DAGM-Symposium.

[3]  Magy Seif El-Nasr,et al.  Understanding and evaluating cooperative games , 2010, CHI.

[4]  Robert J. Moore,et al.  The social side of gaming: a study of interaction patterns in a massively multiplayer online game , 2004, CSCW.

[5]  Georgios N. Yannakakis,et al.  Player modeling using self-organization in Tomb Raider: Underworld , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[6]  Alessandro Canossa,et al.  Evaluating motion: spatial user behaviour in virtual environments , 2011, Int. J. Arts Technol..

[7]  Christian Bauckhage,et al.  Analyzing the Evolution of Social Groups in World of Warcraft® , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[8]  Bernard J. Jansen,et al.  Understanding User-Web Interactions via Web Analytics , 2009, Understanding User-Web Interactions via Web Analytics.

[9]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[10]  Georgios N. Yannakakis.  Game AI revisited , 2012, CF '12.

[11]  Jaideep Srivastava,et al.  Behavioral profiles of character types in EverQuest II , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[12]  Chin-Laung Lei,et al.  World of warcraft avatar history dataset , 2011, MMSys.

[13]  Ruck Thawonmas,et al.  Analysis of revisitations in online games , 2011, Entertain. Comput..

[14]  Ben Medler.  Play with data---an exploration of play analytics and its effect on player experiences , 2012 .

[15]  Ruck Thawonmas,et al.  Visualization of Online-Game Players Based on Their Action Behaviors , 2008, Int. J. Comput. Games Technol..

[16]  Julian Togelius,et al.  Predicting player behavior in Tomb Raider: Underworld , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[17]  Thomas Gärtner,et al.  Player Modeling for Intelligent Difficulty Adjustment , 2009, LWA.

[18]  Christian Bauckhage,et al.  Convex Non-negative Matrix Factorization in the Wild , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[19]  I. Jolliffe.  Principal Component Analysis , 2002 .

[20]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[21]  P. Paatero,et al.  Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values† , 1994 .

[22]  Michael Mateas,et al.  A data mining approach to strategy prediction , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[23]  Christian Bauckhage,et al.  Guns, swords and data: Clustering of player behavior in computer games in the wild , 2012, 2012 IEEE Conference on Computational Intelligence and Games (CIG).

[24]  Randy J. Pagulayan,et al.  User-centered design in games , 2012 .

[25]  John Bohannon,et al.  IEEE International Conference on Computational Intelligence and Games. Game-miners grapple with massive data. , 2010, Science.

[26]  C. Ji.  An Archetypal Analysis on , 2005 .

[27]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[28]  Christian Bauckhage,et al.  Descriptive matrix factorization for sustainability Adopting the principle of opposites , 2011, Data Mining and Knowledge Discovery.

[29]  Tim Fields,et al.  Social Game Design: Monetization Methods and Mechanics , 2011 .

[30]  L. Finesso,et al.  Approximate nonnegative matrix factorization via alternating minimization , 2004, math/0402229.

[31]  Georgios N. Yannakakis,et al.  Real-Time Game Adaptation for Optimizing Player Satisfaction , 2009, IEEE Transactions on Computational Intelligence and AI in Games.