Predicting unexpected influxes of players in EVE online

EVE Online is a massively multiplayer online role-playing game (MMORPG) taking place in a large galaxy consisting of about 7 500 star systems. In comparison to many other online role-playing games, the users interact in the same instance of a persistent player-driven universe. Given the number of simultaneous pilots online at the same time - a number which at times reaches up to more than 50 000 concurrent accounts logged on to the same server - the EVE Online universe can present atypically difficult load-balancing challenges when the users decide to operate in a coordinated fashion, for example, to launch an attack on a particular system. We will present an scalable, automated statistical method for predicting such unexpected user gatherings by considering the evolving shortest-path distances from each user to each system. Here we present a case study analyzing nearly 300 million user movements in the EVE Online universe from over 700 thousand user accounts over a period of three months. We demonstrate an ability to predict sudden spikes in user presence (corresponding to actual events) before they happen, suggesting our techniques could be useful for automated load-balancing in such massive online games.

[1]  Thad Starner,et al.  Learning Significant Locations and Predicting User Movement with GPS , 2002, Proceedings. Sixth International Symposium on Wearable Computers,.

[2]  Christian Bauckhage,et al.  Learning Human-Like Opponent Behavior for Interactive Computer Games , 2003, DAGM-Symposium.

[3]  Christian Bauckhage,et al.  Synthesizing Movements for Computer Game Characters , 2004, DAGM-Symposium.

[4]  Panos Kalnis,et al.  On Discovering Moving Clusters in Spatio-temporal Data , 2005, SSTD.

[5]  Ravi Jain,et al.  Evaluating Next-Cell Predictors with Extensive Wi-Fi Mobility Data , 2006, IEEE Transactions on Mobile Computing.

[6]  Dino Pedreschi,et al.  Trajectory pattern mining , 2007, KDD '07.

[7]  Bettina Speckmann,et al.  Efficient Detection of Patterns in 2D Trajectories of Moving Points , 2007, GeoInformatica.

[8]  John Krumm,et al.  Route Prediction from Trip Observations , 2008 .

[9]  Anna Monreale,et al.  WhereNext: a location predictor on trajectory pattern mining , 2009, KDD.

[10]  H. Pao,et al.  Game Bot Detection via Avatar Trajectory Analysis , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[11]  Marc-Olivier Killijian,et al.  Next place prediction using mobility Markov chains , 2012, MPM '12.

[12]  Bruno Martins,et al.  Predicting future locations with hidden Markov models , 2012, UbiComp.

[13]  Jiliang Tang,et al.  Mobile Location Prediction in Spatio-Temporal Context , 2012 .

[14]  Elio Masciari,et al.  Sequential pattern mining from trajectory data , 2013, IDEAS '13.