The sum of its parts : a three part framework for developing models of individual performance in the context of a team

Sangster, Matthew-Donald D.
Thumbnail Image
Other Contributors
Gray, Wayne D., 1950-
Mendonça, David
Kalsher, Michael J.
Sims, Chris
Issue Date
Cognitive science
Terms of Use
Attribution-NonCommercial-NoDerivs 3.0 United States
This electronic version is a licensed copy owned by Rensselaer Polytechnic Institute, Troy, NY. Copyright of original work retained by author.
Full Citation
Theories of learning and memory often rely on individual measures of performance for tasks in a given domain. However, when expanding these works to individuals in a team, many difficulties arise. The very nature of team tasks assume that individuals collaborate for a common goal. Thereby, it is complicated to try to differentiate between contributions of one team member and another. This work presents a framework for understanding individual performance in a team setting by building a three part ''snapshot'' performance metric of ''how well a particular team member performed in a particular match.'' Using Role Performance, Goal Performance and Individual-in-Team Performance, it becomes possible to find the ''I'' in ''Team'' by determining whether an individual played well even though her team lost. Our paradigms are the widely popular competitive team game League of Legends and NBA Basketball. Our League of Legends dataset consists of 1.9 million records from 539 thousand matches, while the NBA Basketball dataset consists of over 500 thousand records from 21 NBA seasons. In this report, we use these data to develop and test the GRIT (Goal, Role, and Individual-in-Team) behavior-based Framework for developing performance metrics in these tasks that include components of both individual (specific to the position being played) and team (general to all members of a team).
August 2019
School of Humanities, Arts, and Social Sciences
Dept. of Cognitive Science
Rensselaer Polytechnic Institute, Troy, NY
Rensselaer Theses and Dissertations Online Collection
CC BY-NC-ND. Users may download and share copies with attribution in accordance with a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License. No commercial use or derivatives are permitted without the explicit approval of the author.