IT is playing a key role in how the world’s most popular sport is played and experienced in Spain. The country’s premier football division, LaLiga, is leveraging artificial intelligence and machine learning (ML) to deliver new insights to players and coaches, and to transform how fans enjoy and understand the game.
The transformation, which started in partnership with Microsoft in 2016, is also enabling LaLiga to expand its business by offering technology platforms and services to the sports and entertainment industry at large.
“With our first agreement, we started becoming a technology, data-oriented, and cloud organization,” says Ana Rosa Victoria Bruno, innovation manager at LaLiga, one of the world’s top football leagues, with a worldwide audience of more than 2.8 billion.
At the core of LaLiga’s transformation is a data analysis platform called Mediacoach, which uses Azure infrastructure to collect, interpret, and showcase insights from approximately 3.5 million data points captured in near real-time per match. Mediacoach has evolved to become the centerpiece of LaLiga Tech, an end-to-end technology subsidiary that leverages LaLiga’s innovations to offer technology platforms, services, and consultancy to the sports and entertainment industry.
Insights gleaned from Mediacoach are intended for technical staff—coaches and doctors, for example—but LaLiga has also created Beyond Stats, a portal powered by Mediacoach that packages and presents data for media and fans via a range of accessible dashboards.
“We started by giving this data to the technical staff of the clubs, but we decided it was the moment to offer these advanced statistics to the fans and the media,” Bruno says. “We identified the trend that fans were eager to consume this data and know more about competitions.”
The AI advantage
LaLiga Tech is leaning on AI and ML for a number of initiatives. For example, LaLiga uses AI to engage and retain fans, by recommending content and providing additional insight into the fan experience via sentiment analysis. LaLiga has also created an ML solution called Calendar Selector to maximize TV audiences and stadium attendance when scheduling matches. It has also developed predictive models to detect trends, make predictions, and simulate results. These fan engagement, competition management, and advanced performance analytics capabilities are part of LaLiga Tech’s offerings.
During matches, 16 optical tracking cameras installed in each of the league’s stadiums capture real-time data on player positioning, referee positioning, and the ball’s movement to capture 3.5 million data points per match.
“With this huge amount of data per month, we are able to offer stats and reports,” Bruno says. “With 112,000 reports in the system and 8 million bits of information, it’s a huge amount of information for 42 clubs.”
AI takes that data and combines it with historical tracking data from about 2,000 matches to create new insights, such as the Goal Probability model, one of 21 new stats it debuted in 2022.
Created by a multidisciplinary team of football analysts, business intelligence analysts, and the analytics team, the advanced Goal Probability model leverages a range of variables, including the player’s line of sight (taking into account the positions of opposing players), the distance between the ball and the goalkeeper, the distance between the ball and the goal, and the distance and angle to the nearest defender, to measure the probability of finishing a given scoring chance. The calculation also takes into account a player’s efficiency indicator based on variables such as the player’s ratio of goals per match and per shot.
“One of the challenges is, in order to turn this raw data into knowledge, we need not just data scientists, but also football analysts, UX experts, and coaches,” Bruno says.
The platform can make the calculation within 30 seconds of a given scoring attempt, allowing broadcasters to incorporate the stat as a graphic at the frame level in near real-time.
“We followed the design thinking process,” says Bruno. “We had some tests in the laboratory first, and then we tested with the fans. They gave us interesting insights in terms of how to present the information and they gave us feedback.”
One of the things Bruno and her team learned through fan testing was the need to educate the audience about data.
“We realized with different tests with fans that sometimes the types of definitions we were preparing, or the kind of graphics to present this data, were not well understood by different people,” Bruno says. “Just the data was not enough. We needed to explain it. It’s the same with the media and commentators. We now have sessions with the commentators to help them understand the data and stats so they’re not just offering the data, they’re offering knowledge.”
Next steps for LaLiga include reimagining how to get data and knowledge to fans, including different channels.
“We are now using broadcasting and the web, and next is finding new channels and new ways to deliver this information to the fans so it’s a new experience both at home and in the stadium,” Bruno says.
LaLiga is also working closely with Microsoft on next-generation over-the-top (OTT) streaming services, advanced content protection services, and venue management systems.
Artificial Intelligence, Data Management, Innovation, IT Leadership, Machine Learning