Team Performance Prediction in Massively Multiplayer Online Role-Playing Games (MMORPGs)

• Main Authors: SHIM, Kyong Jin, SRIVASTAVA, Jaideep
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2010
• Subjects: Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/1510; https://ink.library.smu.edu.sg/context/sis_research/article/2509/viewcontent/Team_perf_MMORPG_pv_2010.pdf
• Institution: Singapore Management University

In this study, we propose a comprehensive performance management tool for measuring and reporting operational activities of teams. This study uses performance data of game players and teams in EverQuest II, a popular MMORPG developed by Sony Online Entertainment, to build performance prediction models for task performing teams. The prediction models provide a projection of task performing team's future performance based on the past performance patterns of participating players on the team as well as team characteristics. While the existing game system lacks the ability to predict team-level performance, the prediction models proposed in this study are expected to be a useful addition with potential applications in player and team recommendations. First, we present player and team performance metrics that can be generalized to all types of games with the concept of point gain, leveling up, and session or completion time. Second, we show that larger or more advanced teams do not necessarily achieve higher team performance than smaller or less advanced teams. Third, we present novel team performance prediction methods based on the past performance patterns of participating players and team characteristics.