Pappalardo, Cintia, Gianotti and Pedreschi


Luca Pappalardo, PhD

PostDoc researcher in Big Data Analytics at University of Pisa and National Research Council of Italy. I work on Sports Analytics, Social Network Analysis and the application of data science for the analysis of the patterns of Human Mobility. Currently I am working on the definition of data-driven performance indicators for football players and football teams. Website:

Paolo Cintia, PhD candidate

PhD candidate at University of Pisa and research associate at National Research Council of Italy. I am an expert of Sports Data Mining, Mobility Data Mining and location prediction. Currently I am working on developing a network-based algorithm to rank quality and performances of football players. Website:

Fosca Giannotti, professor

Senior researcher at the Information Science and Technology Institute of the National Research Council of Pisa where I lead the KDD Lab, one of the earliest European research groups specifically targeted at data mining and knowledge discovery. My current research includes data mining, knowledge discovery support environment, web mining and spatio-temporal data mining.

Dino Pedreschi, professor

Professor of Computer Science at the University of Pisa and a pioneering scientist in mobility data mining, social network mining and privacy-preserving data mining. My research focus on big data analytics and mining and their impact on society.



The harsh rule of the goals: data-driven performance indicators for football teams

Football analytics has evolved in recent years in an amazing way, thanks to sensing technologies that provide high-fidelity data streams extracted from every game. We propose a data-driven approach and show that there is a large potential to boost the understanding of football team performance. From observational data of football games we extract a set of pass-based performance indicators and summarize them in the H indicator. We observe a strong correlation between the H indicator and the success of a team, and therefore perform a large-scale analysis on the four major European championships (78 teams, almost 1500 games). We observe that the team with the highest value of H indicator is more likely to win a game, while the game results in a draw when the H indicator of the two teams are very similar. The strongest European teams (Barcelona, Real Madrid, Bayern Munich) show the highest value of our H indicator. Moreover, they are at the top of the ranking of a simulated championship, where we replace the outcome of each game by a synthetic outcome (win, loss or draw) based on the H indicator computed for each team. We found that the final rankings in the simulated championships are very close to the actual rankings in the real championships, and show that teams with high ranking error show extreme values of a defence/attack efficiency measure, the Pezzali score. The H indicator and the Pezzali score allow us to define a "success zone", that is the behaviour of the most successful teams in Europe.