e-Coach: um sistema de recomendação de equipes e personagens de league of legends utilizando redes neurais multicamadas

Abstract

The mode of electronic sports has been increasingly present in society, crowding stadiums in different parts of the world and conquering more and more supporters by where their events take place. Between investment and millionaire awards, a career as a cyber athlete has become a goal of young people in the gamer community, as well as encouraging other companies in the area. In this sense, this study demonstrates the implementation of an algorithm applying Multi Layer Perceptron networks, using as a database the results of ranked matches of League of Legends. In addition, it explains the execution of experiments with players in real matches using the algorithm and comparing them to matches without using the algorithm. Thus, making possible the realization of the prediction of which team and characters that best fit for the match in obtaining victory.