Minor League English Soccer Club Experiments With AI Coach


As major soccer teams around the world experiment with video and data analytics to improve their performances on the field, an eighth-tier team in London has taken a step even further, deploying an artificially intelligent coach to set lineups and provide insights.

The non-league club Wingate & Finchley began deploying the sport’s first AI coach earlier this month as part of an effort to inspire kids and teens to pursue careers in science, technology, engineering, and math. Developed by Greenshoot Labs, the voice-led coach collects in-depth knowledge of the team and each player’s attributes, then uses that information to make lineup and formation suggestions, and to offer match strategies and substitutions.

The AI coach may not have helped much in the way of dramatically improving Wingate & Finchley’s standing yet. The first game that it was deployed, on Feb. 9 against Isthmian Premier League opponent Whitehawk FC, ended in a tie. Of Wingate’s four games since then, two have ended in draws, and two in losses.

But Wingate’s use of an AI coach to assist its human coaches nevertheless represents an interesting experiment in how AI insights might further affect the game as technologies continue to improve.

A number of first-tier teams, including the Premier League’s Manchester City, use real-time analytics in an effort to improve performances on the pitch. With machine learning incorporated into many of those platforms, the insights should grow more prescriptive over time.

Sports business, tech, analytics

“Technology once confined to the Championship Manager video game series has now entered the real-world coaching fold—a digital outsider here to shake things up in the muddy, analogue environment of non-league football,” said JJ Shaw, an associate in Lewis Silkin’s commercial practice group with a specialization in sports, in a recent blogpost.

“This particular breakthrough should be seen only as the next step in a sporting revolution that is both well underway, and only in its infancy. AI has permeated many parts of the sports industry already and will continue to do so—raising interesting questions around the need for AI-specific regulations and ultimate ‘ownership’ of the vast swathes of data these technologies collect.”

In 2018, soccer was given a major AI assist when FIFA approved of the use of tablets that fed coaches real-time analytics during the World Cup. Now, seeing AI deployed alongside traditional data analytics across leagues and sports, from minor to professional, has become common. The NFL, NBA and NHL all now have league-wide systems in place to support this type of performance measurement.

The difference with modern technologies compared to the Moneyball era is that artificial intelligence can learn and tweak strategies based on the data it is fed, which will make insights more valuable over time. The information computers are being fed is also growing more granular, thanks to RFID chips that track player movements, wearables that track health, and advancements in video technology that mean statistics can be automatically captured from moving images.

“Since [Moneyball], we’ve witnessed a quantum leap in machine learning, AI and data science,” Shaw said. “As the technology behind AI has grown, so has its wider use in professional sport.”

That technology feeds sophisticated algorithms, which can crunch more data than ever before. As teams leverage smarter robot coaches, they’ll be able to develop a deeper understanding of the factors that determine their successes and failures on the field. In some cases, this has led to the emergence of entirely new metrics that teams can use to analyze team and opponent performance, such as Opta’s “xG” (expected goals), a quantitative measurement of scoring opportunities in soccer.

“By analysing the historical data from over 300,000 shots and factoring in the variations that determine chance quality (who was taking the shot, proximity and angle to goal, time and space to shoot etc.), xG calculates how likely it is that a particular shot will be scored,” Shaw wrote. “An xG model, made possible by big data, goes beyond simply looking at ‘number of shots/shots on target’ and is even a more a consistent measure of overall performance than actual goals scored.”

However, data and privacy regulations may provide a major obstacle to an AI sports future. Many leagues and players’ associations have started to look into ways to protect athletes, whose data is essential to efforts to improve performances, make lineup calls, assist in scouting and recruitment, and aid in fan engagement and media storytelling.

“With seemingly unfettered growth comes fresh uncertainties for AI,” Shaw explained. “Regulators are scrambling to keep up with the continually shifting technological goalposts, and key legal and ethical questions concerning the data collected remain unanswered.”

But the benefits of using AI to improve sports may be so substantial that many of those concerns will be eventually resolved. Regardless of how much help Wingate & Finchley’s AI coach can provide this season, the club won’t be the only one to turn to machines.

“Artificial intelligence continues to strengthen its foothold in the sports industry,” Shaw wrote. “These smart solutions are driving exciting developments for fans in how sport is being analysed and broadcast; offering clubs new and innovative methods to gain competitive advantage; broadening reach for brands and sponsors; and forging new ground in a lucrative market for ambitious software companies.”