Using Machine Learning to Predict Game Outcomes Based on Player-Champion Experience in League of Legends

TL;DR

This paper presents a deep learning approach to predict League of Legends game outcomes based on players' champion experience, revealing the importance of champion mastery and its impact on match results.

Contribution

It introduces a neural network model that predicts game outcomes using champion experience data, highlighting the significance of individual champion skill in match results.

Findings

Game outcomes can be predicted with 75.1% accuracy before gameplay.

Champion mastery significantly influences match results.

There is considerable variance in team skill even after matchmaking.

Abstract

League of Legends (LoL) is the most widely played multiplayer online battle arena (MOBA) game in the world. An important aspect of LoL is competitive ranked play, which utilizes a skill-based matchmaking system to form fair teams. However, players' skill levels vary widely depending on which champion, or hero, that they choose to play as. In this paper, we propose a method for predicting game outcomes in ranked LoL games based on players' experience with their selected champion. Using a deep neural network, we found that game outcomes can be predicted with 75.1% accuracy after all players have selected champions, which occurs before gameplay begins. Our results have important implications for playing LoL and matchmaking. Firstly, individual champion skill plays a significant role in the outcome of a match, regardless of team composition. Secondly, even after the skill-based matchmaking, there is still a wide variance in team skill before gameplay begins. Finally, players should only play champions that they have mastered, if they want to win games.