Esports Analytics Through Encounter Detection
(2016) MIT Sloan Sports Analytics Conference- Abstract
- Esports is computer games played in a competitive environment, and analytics in this domain is focused on player and team behavior. Multiplayer Online Battle Arena (MOBA) games are among the most played digital games in the world. In these es, teams of players fight against each other in enclosed arena environs, with a complex gameplay focused on tactical combat. Here we present a technique for segmenting matches into spatio‐temporally defined components referred to as encounters, enabling performance analysis. We apply encounter‐based analysis to match data from the popular esport game DOTA, and present win probability predictions based on encounters. Finally,metrics for evaluating team performance during match runtime are proposed.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/8569749
- author
- Schubert, Matthias ; Drachen, Anders and Mahlmann, Tobias LU
- organization
- publishing date
- 2016
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- esports, dota2, machine learning, team encounter
- host publication
- Proceedings of the MIT Sloan Sports Analytics Conference 2016
- pages
- 18 pages
- publisher
- MIT Sloan
- conference name
- MIT Sloan Sports Analytics Conference
- conference dates
- 2016-03-11
- language
- English
- LU publication?
- yes
- id
- 37670941-2b22-4b72-84fc-7022700057df (old id 8569749)
- alternative location
- http://www.sloansportsconference.com/?p=17536
- date added to LUP
- 2016-04-04 10:28:55
- date last changed
- 2018-11-21 20:59:00
@inproceedings{37670941-2b22-4b72-84fc-7022700057df, abstract = {{Esports is computer games played in a competitive environment, and analytics in this domain is focused on player and team behavior. Multiplayer Online Battle Arena (MOBA) games are among the most played digital games in the world. In these es, teams of players fight against each other in enclosed arena environs, with a complex gameplay focused on tactical combat. Here we present a technique for segmenting matches into spatio‐temporally defined components referred to as encounters, enabling performance analysis. We apply encounter‐based analysis to match data from the popular esport game DOTA, and present win probability predictions based on encounters. Finally,metrics for evaluating team performance during match runtime are proposed.}}, author = {{Schubert, Matthias and Drachen, Anders and Mahlmann, Tobias}}, booktitle = {{Proceedings of the MIT Sloan Sports Analytics Conference 2016}}, keywords = {{esports; dota2; machine learning; team encounter}}, language = {{eng}}, publisher = {{MIT Sloan}}, title = {{Esports Analytics Through Encounter Detection}}, url = {{https://lup.lub.lu.se/search/files/5549290/8773291.pdf}}, year = {{2016}}, }