Go With The Flow - Part 2

Number-loving sports like baseball and basketball have plenty of individual statistics to measure a team and a player’s performance over time.  Not so for the “beautiful game.”  "In soccer there are relatively few big things that can be counted," said Luis Amaral, professor of chemical and biological engineering at Northwestern University. "You can count how many goals someone scores, but if a player scores two goals in a match, that's amazing. You can really only divide two or three goals or two or three assists among, potentially, eleven players. Most of the players will have nothing to quantify their performance at the end of the match."

Amaral and his colleagues at NU’s McCormick School of Engineering and Applied Science knew that there was plenty of information buried in the data about player movement, passing and timing, if only a logical model could be created to explain the chaos on the field.  Just as we learned in Part 1 about network models in basketball, Amaral, a lifelong soccer fan from Portugal, used his knowledge of social network analysis in biological systems to create a model of soccer ball strategy.

"You can define a network in which the elements of the network are your players," Amaral said. "Then you have connections between the players if they make passes from one to another. Also, because their goal is to score, you can include another element in this network, which is the goal."

Diagram 1 (click to zoom)

Using detailed player event data from the Euro 2008 international tournament, the researchers mapped every pass for each of the 31 matches.  By comparing the passing route that a team used to end in a shot on goal, certain patterns emerge that highlight the players that are most often involved in the build-up to a goal.  Not only could Amaral predict success for the team but also assign value ratings to each player.

"We looked at the way in which the ball can travel and finish on a shot," said Amaral, who also is a member of the Northwestern Institute on Complex Systems (NICO). "The more ways a team has for a ball to travel and finish on a shot, the better that team is. And, the more times the ball goes through a given player to finish in a shot, the better that player performed."

In Diagram 1, take a look at the bold network connections representing the most used passing paths between Euro 2008 players (denoted by their uniform numbers).  Just as in the basketball network paths, finding passing patterns that end with shots on goals can give clues to the most efficient ball movement.

Diagram 2 (click to zoom)

From their initial research paper that appeared in PLOS One, Amaral created a company, Chimu Solutions, dedicated to refining their network model by adding data from thousands of top flight games across multiple leagues.  Their goal is to produce a single metric that measures a player’s value as defined by their contribution to shots on goal.

In fact, by the time Euro 2012 came around last year, the model was able to attach an average player rating for each team.  Diagram 2 shows the table for Spain’s champion roster which most pundits would agree ranks the players in a logical order from top to bottom.

This focus on data analytics is the new standard for sports and those teams that accept the challenge to find athlete monitoring tools that reveal these trends and patterns will have the competitive advantage over those teams that do not.  Indeed, with apologies to Sun, the network is now the sport.

Follow @metrifit

Euro 2012: A New Way To Track Team Performance

Imagine if the new Adidas soccer ball that will be used in this month’s Euro 2012 tournament had a memory chip in it that could retrace its entire path through each of the scheduled thirty-one games.  Not only its direction and distance traveled, but if it could also log each player’s touch leading up to every shot on goal.

Would the sum of all of those individual path segments tell the story of the game and which players contributed the most to their team’s success?  Northwestern University engineering professor Luís A. Nunes Amaral has not only answered that question, but has now built a side business to enlighten coaches and fans.

While most sports have an abundance of statistical metrics to measure a player’s development, soccer’s fluid gameplay and low scores make it more difficult to evaluate a specific player’s impact and contribution.  To fill the void, several game analysis service firms now offer data on each action of every player during a game, but it’s left to the consumers of this data (coaches, players and fans) to interpret what combination of stats best explains if the team is improving beyond the ultimate metric of wins and losses.

Amaral, a lifelong player and fan from Portugal, saw an opportunity to help.  “In soccer there are relatively few big things that can be counted,” he said. “You can count how many goals someone scores, but if a player scores two goals in a match, that’s amazing. You can really only divide two or three goals or two or three assists among, potentially, eleven players. Most of the players will have nothing to quantify their performance at the end of the match.”

In his lab at Northwestern, Amaral and his team of researchers study complex systems and networks; everything from metabolic ecosystems, the Internet, neural networks in our brain and the propagation of HIV infection.  To him, the game of soccer is no different.

“You can define a network in which the elements of the network are your players,” he commented. “Then you have connections between the players if they make passes from one to another. Also, because their goal is to score, you can include another element in this network, which is the goal.”
They dug into the stats of the previous European championship, Euro 2008, and mapped the ball movement and player statistics for each game into a computer model.  They made the assumption that the basic strategy of every soccer team is to move the ball towards their opponent’s goal.

“We looked at the way in which the ball can travel and finish on a shot,” said Amaral, who also is a member of the Northwestern Institute on Complex Systems (NICO) and an Early Career Scientist with the Howard Hughes Medical Institute.  ”The more ways a team has for a ball to travel and finish on a shot, the better that team is. And, the more times the ball goes through a given player to finish in a shot, the better that player performed.”

By combining a player’s passing efficiency (number of successful passes divided by total passes) and the ball flow around the field, the model can draw a network diagram of the paths that most often led to a shot on goal.  These well-worn paths begin to tell a story of which players are the most reliable and effective.  Amaral has given a very sports-bar worthy name to this ability – flow centrality.  The more often that a player is involved in the build-up of passes towards a shot, the more vital he or she is to the team’s success.

The research was published in the online science journal, PLoS ONE.

Since the study came out almost two years ago, Amaral has set-up a new company, Chimu Solutions, to not only offer soccer analysis but also to expand their algorithms and software to other lines of business to reveal “intricate team dynamics as well as individual metrics with the goal of differentiating role players from superstars.”

While goal scorers and goalkeepers most often get their names in the headlines, it’s often the supporting cast of players that determine the outcome of games.  Understanding how the ball should be and how it is moving up and down the field is critical to player development and game tactics.  One of the most difficult skills for free-flowing sports like hockey and soccer is the visual awareness of teammates’ locations and quick decisions to make progress towards the goal.  Flow centrality may just be the answer.

Visit Axon Sports on Twitter and Facebook

Euro 2012: Cognitive Research Links Brain Function To Soccer Success

During the upcoming Euro 2012 tournament, you will often hear coaches and commentators refer to an athlete’s ability to “see the field” or be a play-maker.  Rookies at the next level can’t wait for the game to “slow down” so their brains can process all of the moving pieces.

What exactly is this so-called game intelligence and court vision?  Can it be recognized and developed in younger players?  For the first time, neuroscientists at Sweden’s Karolinska Institutet have found a link between our brain’s “executive functions” and sports success.

When in the middle of a heated game on the field or court, our brains are accomplishing the ultimate in multitasking.  Moving, anticipating, strategizing, reacting and performing requires an enormous amount of brain activity and the athletes who can process information faster often win.
In the everyday world, these types of activities, including planning, problem solving, verbal reasoning, and monitoring of our actions, have been called “executive functions.”  They are called into action when we face non-standard situations or problems where our automatic brain responses won’t work.  Neuroimaging studies have shown this activity happens in the prefrontal cortex of our brains. In ever-changing game situations, those abilities are often used and players need to adapt and be creative on short notice.

“Our brains have specific systems that process information in just this manner, and we have validated methods within cognitive research to measure how well the executive functions work in an individual,” says Dr Predrag Petrovic, the lead researcher in the study.

One of these standardized methods is the Delis-Kaplan executive functions system (D-KEFS) that consists of a series of tests of both verbal and non-verbal skills.  Petrovic and his team gave several of these tests to 57 elite soccer players from Sweden’s highest professional league, Allsvenskan, and the league just below known as Division 1.  After comparing the results, they found that the elite players performed significantly higher than a control group of non-players and the Allsvenskan players also outperformed the Division 1 players.

As in any sport, it’s the on-field performance that matters.  So, the researchers followed the professional players for two seasons and gathered statistics on goals and assists for each player.  There was a clear correlation between higher executive function test results and the ability to create goals.
Their study has been published in the online science journal PLoSONE.

Previous research had used sport-specific tests to measure individual abilities such as focus and attention.  Petrovic’s work was the first to link general problem solving ability with elite performance.

“We can imagine a situation in which cognitive tests of this type become a tool to develop new, successful soccer players. We need to study whether it is also possible to improve the executive functions through training, such that the improvement is expressed on the field. But there is probably a hereditary component, and a component that can be developed by training,” says Torbjörn Vestberg, psychologist and a member of the research group that carried out the study.

As Vestberg points out, this is exciting news for coaches and parents who can now link improvement in general problem-solving skills with their players’ sports performance.  Here at Axon, we are excited to be developing sport-specific cognitive training tools based on these foundational discoveries to help gain the edge over the competition.

Also follow me over at Axon Sports on Twitter and Facebook.