Visual Analysis of Forecasts of Football Match Scores

Abstract

The present work describes the application of information visualization techniques to better understand the behaviour of a forecasting model designed to predict football match scores based on past confrontations. We have run the forecasts during the 2019 season of Brazilian National Championship and, once it was over, we gathered data to observe the performance of the forecasts, based on a set of evaluators we propose. The main contribution of this paper is the introduction of visual devices, each attached to one of these evaluators, designed to enhance interpretation of the performance of forecasting models in general and sports forecasts in particular. We also present other visualizations that help taking notice of particular features of the championship and the forecasts.