Controlling the crucible: a novel PvP recommender systems framework for destiny

Compared to conventional retail games, today's Massively Multiplayer Online Games (MMOGs) have become progressively more complex and volatile, living in a highly competitive market. Consumable resources in such games are nearly unlimited, making decisions to improve levels of engagement more challenging. Intelligent information filtering methods here can help players make smarter decisions, thereby improving performance, increasing level of engagement, and reducing the likelihood of early departure. In this paper, a novel approach towards building a hybrid multi-profile based recommender system for player-versus-player (PvP) content in the MMOG Destiny is presented. The framework groups the players based on three distinct traced behavioral aspects: base stats, cooldown stats, and weapon playstyle. Different combinations of these profiles are considered to make behavioral recommendations. An online evaluation was performed to investigate the usefulness of the proposed recommender framework to players of Destiny.

[1]  Diego Klabjan,et al.  Guns and guardians: Comparative cluster analysis and behavioral profiling in destiny , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[2]  Guy Shani,et al.  A Survey of Accuracy Evaluation Metrics of Recommendation Tasks , 2009, J. Mach. Learn. Res..

[3]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

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

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

[6]  Christian Bauckhage,et al.  Behavior evolution in Tomb Raider Underworld , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).

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

[8]  Sam Devlin,et al.  Exploration and Skill Acquisition in a Major Online Game , 2017, CogSci.

[9]  Syed Muhammad Anwar,et al.  A game recommender system using collaborative filtering (GAMBIT) , 2017, 2017 14th International Bhurban Conference on Applied Sciences and Technology (IBCAST).

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

[11]  Magy Seif El-Nasr,et al.  Game Analytics , 2013, Springer London.

[12]  Sifa Rafet,et al.  Predicting Retention in Sandbox Games with Tensor Factorization-based Representation Learning , 2016 .

[13]  Diego Klabjan,et al.  Rapid Prediction of Player Retention in Free-to-Play Mobile Games , 2016, AIIDE.

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

[15]  Lior Rokach,et al.  Recommender Systems Handbook , 2010 .

[16]  Christian Bauckhage,et al.  User Churn Migration Analysis with DEDICOM , 2015, RecSys.

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

[18]  Bracha Shapira,et al.  Recommender Systems Handbook , 2015, Springer US.

[19]  Christian Bauckhage,et al.  Clustering Game Behavior Data , 2015, IEEE Transactions on Computational Intelligence and AI in Games.

[20]  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).

[21]  Christian Bauckhage,et al.  Predicting Retention in Sandbox Games with Tensor Factorization-based Representation Learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[22]  Christian Bauckhage,et al.  Archetypal Game Recommender Systems , 2014, LWA.