The Soccer Data Cup is an innovative initiative, unique of its kind, organized by the National Research Council of Italy (CNR) and University of Pisa, two partners of the SoBigData consortium, in collaboration with the Italian Ministry of Education (MIUR). The second edition was organized at L’Aquila (Italy) on 5-7 May 2019 and was totally dedicated to women.
In a first selection phase, six high schools were selected to represent six Italian regions: Abruzzo, Campania, Emilia-Romagna, Molise, Puglia, Umbria. Each high school then selected two teams: a team of seven female soccer players and a team of two female “wannabe” data scientists. Then, the competition was articulated in two parallel, but connected, competitions.
In the sports competition, the six teams of players faced each other in a futsal tournament: two Italian-style groups of three teams, semifinals and finals. During all matches, the players wore a device, produced by company Tracking4Fun, which monitored in great detail the movements on the field. At the same time, matches were filmed so as to allow company Wyscout to detect, with the usage of its proprietary software, all the main spatiotemporal events that have occurred during the matches (passes, tackles, shots, fouls, etc.).
In parallel, the teams of data scientists analyzed the data produced during the matches, with the purpose of creating a critical analysis of the tournament. With the help of data scientists of the SoBigData infrastructure, the data scientists coded in Python for three days, finally presenting their analyses in the last day to a committee of sports and science experts. The outcome of both the sports competition and the analytical one were used to decide the three finalists (Emilia-Romagna, Puglia and Umbria) that presented their analyses at the municipal theater. The audience at the theater used an online app to vote for the best presentation, finally decreeing Puglia as the winner of the Soccer Data Cup.
The second edition of the Soccer Data Cup was a big success, suggesting a bright future for women both in soccer and the STEM disciplines. The young data scientists showed an enormous enthusiasm for data science and sports analytics as well as a great talent for science communication. This motivated SoBigData to organize a third edition where both men and women will attend in mixed teams, with the purpose of promoting the sound values of sports, STEM disciplines, and gender equality.