Before data entered sports, all coaches had in terms of statistical reporting was who played, who scored and who didn’t. This, by and large, was the basis on which players on any particular sport were evaluated.
Decisions about who to play, draft, coach or develop were being made with a “gut” feeling or adhering to past decisions.
But then, came Billy Beane, former MLB player and Oakland Athletics’ General Manager, who pioneered the use of data analytics in baseball
. Beane’s use of data analytics was detailed in the movie Moneyball
, in which he utilized computer analysis and sabermetrics, a school of baseball statistical analysis, to identify undervalued players.
Knowing he couldn't compete with the big budget teams who could pay top dollar for top talent, Beane set out to win in a different manner, namely, by evaluating players through a new lens.
This was the first time data and statistical analysis was used to make major decisions
on how a professional sport was played. This new approach revolutionized baseball and has spread throughout the world of competitive sports in many different forms. Now, every professional sports team has a data analyst or related department that helps in developing organizational philosophy and evaluating player and opponent performance.
Coaches may be the largest beneficiary of the use of data, utilizing the information to craft game plans, analyze opponent weaknesses, and evaluate their players performance using something other than their gut.
Player Selection Based on Skill on the Field
One of the goals of coaching experts in top level sports teams is to find the most suitable role and position for particular players for a match.
Every bit of data gathered, from the player’s skills to his physical abilities helps coaches determine where they profile to make the biggest contribution on the field.
Beane used sabermetric analysis to draft and sign players that fit a specific criteria. The criteria he used was contrary to the norm, and far removed from the way selections were traditionally made in professional baseball.
His system did not require that players fit a pre-determined mix of weight, speed, and body composition dictated by other clubs. Sabermetric reasoning dictates that a good player is one who scores more runs than the opposing team, not one who fits a certain physical mold.
To this end, he focused in on players that showed an ability to get on base often and be in position to score more runs. Power hitters, the big bashers in baseball, cost too much on the open market and his A's couldn't compete on that front...so Beane made a new one.
Accounting for the Little Details for Game Strategies
Coaches and trainers now use technologies that allow them to monitor aspects like a player’s physical endurance on the field in real time. The data they receive from these sessions is used to modify or improve how they maintain a player’s performance while taking fatigue into account.
A good example of how this was executed can be seen by the German football team
during the football World Cup in Brazil.
During training sessions, an Adidas miCoach system worn by each player monitored heart rate, acceleration, speed, distance and power. In addition to gauging player performance, the data collected helped coaches and trainers single out fit players and those who could use a rest.
Improving Play on the Field of Play
In competitive sports, there are some players who work well together, some who don’t and some who are better suited to face off against certain opposing players compared to their teammates.
Analytics helps coaches determine not only who the bets players are, but even deeper the best combination of players. Furthermore, the data available can help determine how the opposing team will respond to certain situations, which is a huge asset in game planning.
For example in basketball, data can help coaches determine if a player executed a jump shot well because he was skilled, the pass was good or the defense was bad. If he is skilled, he can be used to lead key strategies. If the pass is good, it identifies players that work well together and use them for the same. If the defense is bad, coaches can strategize plays that take advantage of this weakness.
Injuries are common in sports and even more so in contact sports.
Take rugby for example. Due to the physical nature of the sport, injuries increase every year. The Professional Rugby Injury Surveillance Project
(PRISP) reported an increase in concussions for the fifth season.
Lately, coaches are using data analytics tools to measure the force of hits that players sustain to figure out how to reduce these injuries before they happen.
Some sporting teams have been known to use technologies that turn everything measurable, from a player’s body chemistry to movement and physical interactions on the field, into data. Once analyzed, the data gathered can indicate distressing patterns in player behavior that may result in injuries.
Additionally it can also be used to gain deeper insights into injuries that often go undetected.
To illustrate, consider concussions that often go undetected due to the subjective methods of evaluating and reporting head injuries in contact sports. If left undetected and untreated, injuries like these can result in serious brain injuries.
Progress has already been made in this regard. Sensor equipped mouth guards can detect when a player receives an impact that is above the preset safety threshold during play. A companion app sends this information to the coach who then has the incentive to remove this player from the field and examine him for signs of serious head trauma.
Predicting an Opponent’s Next Move
There are patterns and trends in our behavior.
When it comes to contact sports, players who have the ability to think on their feet often score the most, but those with additional information can take it even one step further.
Predictive data analysis can help identify tendencies in opponents - how a pitcher may approach a certain situation, how a soccer striker likes to enter the attack zone, how a quarterback likes to execute third down pass plays.
All of this data can be processed to give an advantage to the team that uses it best.
Another example data being used to predict an opponent’s intentions beforehand is in tennis. IBM’s monitoring system SlamTracker
uses around 39 million data points gathered from seven years of Grand Slam tennis matches to detect player patterns (when they choose to volley, how frequently they use their forehand, etc). Combined with video data from cameras across the tennis court, the system determines the winners in a live match before it ends.
Analyzing player behavior in real time and using it to predict how matches might pan out can help coaches adjust play against certain opponents.
It is a coach’s job to put his team in situations where they can be successful.
Data analytics offers them an intuitive way to make sense of the information gained from the field and make insightful decisions that can help teams not only outplay, but outsmart their opponents.
Farheen Shahzeb is a copywriter and content strategist who loves all things tech. An avid writer, she author in depth posts on various topics, especially concerning the impact of technological innovations on different industries like competitive sports. When she is not writing about the latest software innovations for Cygnis Media
, she catches up on the latest news and trends on the same.