Predicting Win-Loss of League of Legends at the Start of the Game Using Machine Learning Techniques  
Author Cheolgi Kim


Co-Author(s) Soowon Lee


Abstract E-sports is not only a simple game that individuals enjoy but also a world-class sport that is adopted as a demonstration sport in the 2018 Asian Games. The League of Legends is one of the e-sports games. In this paper, we propose a win-loss prediction model of League of Legends at the start of the game using machine learning techniques. The prediction accuracy of 60.25% was obtained experimentally with the artificial neural network model. By using the prediction model proposed in this paper, it is expected that the team-based strategy can be established in choosing a champion at the start of the game.


Keywords Machine Learning, Data Mining, Neural Network, League of Legends, E-sports, win-loss prediction
    Article #:  DSBFI19-28
Proceedings of ISSAT International Conference on Data Science in Business, Finance and Industry
July 3-5, 2019 - Da Nang, Vietnam