|
Title:
|
TOPOLOGICAL CLUES FOR PREDICTING OUTCOMES OF MULTIPLAYER ONLINE BATTLE ARENA GAMES |
|
Author(s):
|
Dominik Deja, Mateusz My?lak |
|
ISBN:
|
978-989-8533-38-8 |
|
Editors:
|
Katherine Blashki and Yingcai Xiao |
|
Year:
|
2015 |
|
Edition:
|
Single |
|
Keywords:
|
Esports, MOBA, Predictive Analytics, Data Mining |
|
Type:
|
Full Paper |
|
First Page:
|
116 |
|
Last Page:
|
122 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
With 27 million people playing League of Legends every day, e-sports became more and more important part of our everyday life. Rise of its popularity builds a demand for better understanding e-sports mechanics on a deeper level. In the article, we test a hypothesis that it is possible to predict an outcome of Multiplayer Online Battle Arena game based on topological clues only (such as area of polygon where vertices are players positions, and their dispersion). With accuracy, precision, and recall around 80%, we show that it is possible to construct a model which will be both: generic for MOBA games genre, and based on simple assumptions, which are hard to be perceived by the naked eye. Results can be used for better understanding how MOBA games works, as well as for developing more player-friendly games in terms of difficulty, and time one needs to learn how to play. |
|
|
|
|
|
|
