Skip to main content
eScholarship
Open Access Publications from the University of California

Beyond Skill: Predictive Modeling with Individual and Team Attributes in Leagueof Legends

Abstract

The goal of this study is to explore the predictive capability ofseveral psychosocial variables, such as personality and groupcohesion, towards determining multiplayer online battle arenagame outcomes - namely diversity, cohesion, and resilience, oncollective performance. Our study finds that measures ofindividual and team perceptions of qualities provided a usefulprecursor for match victory. Using individual-level attributes,our cohesion survey questions provided the highest predictivevalue, and higher levels of perceived cohesion were associatedwith higher victory odds. In light of our results, we discuss theimplications of using behavioral data derived from onlinegames and opportunities for future large-scale game datacollection.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View