Positional analysis of Brazilian soccer players using GPS data

Abstract

The professional soccer is always changing and is constantly searching tools and data to help the decision-making,
providing tactics and techniques to the team. In Brazil, this sport goes to same way and the investments are
considerable. The One Sports is a company that capture GPS data from professional soccer players of some
Brazilian teams. This set of data has a lot of features and the One Sports asked if was possible to predict the ideal
position of a player. Then, was firmed a cooperation between a academic study and a commercial company. This
work find to understand a propose methods and techniques to predict the ideal position of the soccer player, using
machine learning algorithms. The database has more of one million of tuples. It was submitted to preprocessing
step, what is fundamental, because generated new features, removed incomplete and noisy data, generated a
new balanced dataset and delete outliers, preparing the data to execution of the algorithms k-NN, decision trees,
logistic regression, SVM and neural networks. With the purpose to understand the performance and accuracy,
some scenarios were tested. There was poor results when executed multiclass problems. The best results come
from binary problems. The models k-NN and SVM, specifically to this study, had the best accuracy. It is important
to note that SVM spent more than six hours to finish your execution, and k-NN used less than one and half
minute to end.