Big Data is Changing the Football Game

The football authorities have been slow to embrace technology, at times actively resisting it. It’s only been two seasons since some of Europe’s top leagues were authorized to use goal-line technology to answer the relatively simple question of whether or not a goal has been scored, i.e., has the whole ball crossed the goal line.

This is something the games of tennis and cricket have been doing for nearly ten years, but for one of the world’s richest sports, it risked becoming a bit of a joke.  As one seasoned British manager once said, after seeing officials deny his team a perfectly good goal: "We can put a man on the moon, time serves of 100 miles per hour at Wimbledon, yet we cannot place a couple of sensors in a net to show when a goal has been scored.” The authorities eventually relented, of course, their hand forced by increasingly common, high profile and embarrassing slip-ups.

But while the sport’s governing bodies were in the grips of technological inertia, the world’s top clubs have dived in head first in the last ten to fifteen years, turning to big data analytics in search of a new competitive advantage. In turn, this has seen some innovative companies spring up to serve this new ‘industry’, companies like Intel customer Scout7.

Taking the Guesswork out of the Beautiful Game

Big data has become important in football in part because it is big business. And for a trend that is only in its second decade, things have moved fast since the days of teams of hundreds of scouts collecting ‘data’ in the form of thousands of written reports in an effort to provide teams with insights into the opposition or potential new signings.

Now, with tools like Scout7’s football database, which is powered by a solution based on the Intel® Xeon® Processor E3 Family solution, they have a fast, sophisticated system that clubs can use to enhance their scouting and analysis operations.

For 138 clubs in 30 leagues, Scout7 makes videos of games from all over the world available for analysis within two hours of the final whistle[1]. At the touch of a button, they can take some of the guess work and ‘instinct’ out of deciding who gets on the pitch, as well as the legwork of keeping tabs on players and prospects from all over the world.

Scout-7-Player-Database.png

Pass master: Map of one player’s passes and average positions from the Italian Serie A during the 2014-15 season

Using big data analytics to enable smarter player recruitment is among Scout7’s specialties. For young players, without several seasons of experience on which to judge them, this can be especially crucial. How do you make a call on their temperament or readiness to make the step up? How will they handle the pressure? As we enter the busiest recruitment period of the football calendar – the summer transfer window – questions like this are being asked throughout the football world right now.

Delving into the Data

It’s a global game, and Scout7 deals in global data, so we can head to a league less travelled for an example: the Czech First League. The UEFA Under-21 European Championships also took place this summer and, with international tournaments often acting as shop windows for the summer transfer market (which opened on 1st July – a day after tournament’s final), it makes sense to factor this into our analysis.

So, let’s look at the Scout7 player database for players in the Czech First League that are currently Under-21 internationals, to see who has had the most game time and therefore exposure to the rigors of competitive football. We can see that a 22-year-old FC Hradec Králové defender, played every single minute of his team’s league campaign this season – 2,700 minutes in total.

Another player’s on-field time for this season was 97% — valuable experience for a youngster. Having identified two potential first-team ready players, Scout7’s database would allow us to take a closer look at the key moments from these games in high-definition video.

Check out our infographic, detailing a fledgling career of another player in the context of the vast amount of data collection and analysis that takes place within Scout7.

Scout-7-Player-Profile.pngScout7 player profile

“Our customers are embracing this transition to data-driven business decision-making, breaking away from blind faith in the hunches of individuals and pulling insights from the raft of new information sources, including video, to extract value and insights from big data,” explains Lee Jamison, managing director and founder, Scout7.

Scout7's platform uses Intel® technology to deliver the computing power and video transcoding speed that clubs need to mine and analyze more than 3 million minutes of footage per year, and its database holds 135,000 active player records.

Lonely at the Top

There’s only room at the top of the elite level of sport for one and the margins between success and failure can be centimeters or split seconds. Identifying exactly where to find those winning centimeters and split seconds is where big data analytics really comes into its own.

Read the full case study.

To continue this conversation on Twitter, please follow us at @IntelITCenter or use #ITCenter.

 

Find me on LinkedIn.

Keep up with me on Twitter.

*Other names and brands may be claimed as the property of others.

[1] Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more information go to www.intel.com/performance

Intel does not control or audit the design or implementation of third party benchmark data or Web sites referenced in this document. Intel encourages all of its customers to visit the referenced Web sites or others where similar performance benchmark data are reported and confirm whether the referenced benchmark data are accurate and reflect performance of systems available for purchase.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. Check with your system manufacturer or retailer or learn more at http://www.intel.com