Capturing football-teams behavior with a stochastic model

Barbone M. Relatori: Paolo Ferragina, Luca Pappalardo, Paolo Cintia

data science  stochastic models  sports analytics  soccer analytics 

This thesis aims to capture soccer teams behavior using a stochastic approach on a graph built on top of the Wyscout dataset, a market-leading company in data scouting for soccer. The main contributions of the thesis are twofold: first, it proposes a stochastic representation of a soccer game via a weighted graph properly derived from the Wyscout dataset. Secondly, it analyses every game through a stochastic model to detect the way teams move the ball together with the way they move onto the field and the performance that they achieve.