Research on Prediction of the Game Winner Based on Artificial Intelligence Methods

Author:
Open Access
Publisher website
Google Scholar
Abstract
For a strategic game, players need to predict the next step or the next few steps of the maximum probability of action. Then players decide how to deal with so that they have the greatest chance to win. But artificial intelligence is very good at analyzing and predicting. Our goal is to predict the winner of League of legends and analyze the potential mechanism. The data set of this paper comes from kaggle website that provides a desirable base for the procedure of machine learning to analyze the relationship among data and game results. It contains 9879 samples in total, including 38 features. Based on machine learning method, the game player's winning situation can be predicted. The results show that the Support vector machine model with linear kernel function has a greater advantage in predicting the game, about 73%. This study has practical significance for the development of the game industry and the improvement of the skills of players.

This publication has 8 references indexed in Scilit: