Link di Team
Titolo: An Introduction to Football Data and some Statistical Tools for Football Analytics 

Abstract: Machine learning and digitization tools are exponentially increasing in these last years and their applicationsare reflected in different areas of our life: in particular, this webinar aims to focus on football (i.e. soccer for Americans), the most practised sport in the world. Due to needing of professional teams, analytics tools in football are becoming a crucial point, in order to help technical staff, scouting and clubs management in policy evaluation and to optimize strategic decisions; in this seminar will be presented an overview about the football data world and the related literature and some tools and applications. In particular, this application aims to improve the expected goal (xG) model; with this final goal, it has been merged data from different sources: tracking data, match event data and some players' performance composite indicators obtained using a Partial Least Squares - Structural Equation Model (PLS-SEM). Using a sample of match data relying the season 19/20 of the Italian Serie A, composed by 1 outcome variable (i.e. the GOAL) and a set of features, a logistic regression model was applied on different scenarios for sample balanced techniques. Results seem to be interesting for different classification metrics, compared with a benchmark. In addition, some original performance composites and news tracking variables introduced are significant for the classification model.