The game is too fluid, they said. The movement is too chaotic, they said. There are simply too many moving parts in football to apply data in a way which provides value. Twenty years ago, this was the consensus among pundits, players, and managers alike. However, technological advancements have crushed this outdated belief. With analytics transforming the football pitch, it is time to look at how it has influenced the most celebrated game of all times.
Data’s disruption: How have Analytics transformed the football field?
Undeniably, the pool of football talent is large. For scouts, it is all about finding the diamond in the rough. While players like Messi and Ronaldo can’t be missed, a player in Cyprus can easily go undiscovered. Lucky for Lorenzo Ebecilio, he was discovered in 2018 with a little help from data analytics. When a London-based analyst sitting at his desk was impressed with what he saw, he recommended Ebecilio to the Serbian Red Stars. Soon, Ebecilio rose to stardom as the midfielder of the Red Star Belgrade before moving to Jubilo Iwata in the J1 League.
Numbers are not alien to the sport. For decades on end, commentators have compiled statistics on everything right from winning streaks to the most crosses delivered in one match. Over the past decade however, the approach to the game has become a lot more scientific, giving it a whole new dimension, especially in terms of scouting and identifying talent.
Clubs can now be selective about their players by simply looking at whether they match the profile of their ideal target signing or not. For instance, 21st Club assigns each player a rating after looking at their individual moves vis-à-vis the team’s overall performance in the game. They have also created PIRLO, an analytics engine named after the Italian midfielder Andrea Pirlo. With analytical information on over 150,000 players, it uses similar algorithms to Netflix and Amazon to recommend hidden talents like Ebecilio.
Data is also being used to assess the capabilities of stellar players across the globe. Professor Luis Amaral created an algorithm which objectively ranks professional players. After closely studying the game, he built a grid for each team, displaying how the ball was passed all over the field. Following an application of complex coding techniques and tools, Amaral came up with what was termed “Average Footballer Rating” (AFR) for each player, indicating how significant their role is in the game. The ‘Amaral Lab 2018 World Cup Dream Team’ comprises of Messi, Neymar and Ronaldo in the top positions with each of them scoring an AFR of 73.
So, a question that a lot of football fans may have is this: can analytics help us predict who wins the game? While that may be too far-fetched (at least for the time being!), it is worth acknowledging the impact data has had on a sport which was initially considered too complex and fluid for it to reap any results.