There are countless contributors to athletic success, including a coach with good planning and decision-making skills, talented and well prepared players, and good data analytics.
In the athletics industry, analytics packs a winning punch in previously unimagined ways, and the number of potential uses of sports analytics continues to increase. There’s even a prominent, annual MIT Sloan Sports Analytics Conference dedicated to the ever-growing field.
There are all kinds of categories of sports-related analytics such as performance analytics, predictive analytics, coach analytics, referee analytics, fan analytics, ticketing analytics, and many others.
Here are just a few examples of how analytics is currently used in athletic activity:
Let’s dive into some scenarios.
The right data and analytics can influence strategy. Imagine cameras that track players’ movements across a basketball court, as described in Changing the Game: The Rise of Sports Analytics:
“Teams in the NBA are now using six cameras installed in the catwalks of arenas to track the movements of every player on the court and the basketball 25 times per second. The data collected provides a plethora of innovative statistics based on speed, distance, player separation and ball possession. Some examples include how fast a player moves, how far he traveled during a game, how many times he touched the ball, how many passes he made… and much more.”
At World Cup Players’ Penalty Kick Patterns, there’s very interesting data about penalty kicks of athletes in the World Cup by team, including information about whether the player tends to kick left, center, or right. You can see how many goals were made, and how many were saved by the goalie, hit, or missed. Analytics like this can help coaches and goalies make decisions, based on who’s doing the penalty kick.
Another fascinating performance-related area is studying traits and strategies to help the “underdogs” win. How do you then try and convince a team, coach, or others of these potentially-winning strategies and traits? A useful statistic to track in soccer is the number of expected goals (or xG). Information like this is used in events like the Women’s World Cup, for instance. The article Advanced Soccer Statistic Shows Better Team Doesn’t Always Win talks more about how statisticians compile xG, to help measure a team’s performance and to influence decision-making:
“Analysts at Opta, a sports statistics service, studied thousands of shots and used logistic regression analysis to determine how likely each was to go in. With those numbers in hand, Opta can now assess any shot by evaluating it in categories including where it was taken (the closer the better), the angle on the goal, and whether it was by foot or head (foot is better).”
The article Brain mapping: the future of scouting talks about studying brain activity in athletes while they are training or competing. The premise is that it’s possible to learn more about whether the athletes are capable not only of rote learning and improving skills through practice, but also the degree to which they can think on their feet to meet challenges.4 This information could be useful in decisions related to scouting and investing in a player’s development, for instance.
A coach might want to look at how players tend to perform under pressure. This information is useful in helping prepare players for the World Cup, for example.
Changing the Game: The Rise of Sports Analytics talks about how analytics could potentially even be used to examine a person’s psychology, to figure out how suitable that person is to the job demands:
“Look for the next analytical breakthrough to come in the areas of predicting how a player’s mental make-up will adjust to the rigors of professional sports and how the emotional aspect of the responsibility correlates to on-the-field performance.”
Sports analytics can help with understanding a player’s risk of injuries and knowing when the athlete is at peak performance. This type of information can even extend the athlete’s career. Decisions can be made in real-time during games, according to how tired a player is or their determined risk of injuries.
Using fan analytics to predict outcomes, personalize an experience, and increase revenues
Fans can also get in on the game—such as on http://www.wimbledon.com/en_GB/slamtracker/—with statistics that show which player is predicted to win, based on criteria like first-serve percentage. Or they can see stats about favorite tennis players on sites like http://www.atpworldtour.com/en/stats.
Also, fan-related analytics can be used to track fan engagement and provide a personalized experience. For example, suppose data shows that a particular fan watches a lot of videos about a specific team via Twitter and other specific channels. Data can be gathered from these channels to get a complete fan profile. As a result, future engagement and content delivery can be tailored accordingly.
Or suppose a fan tries to buy a ticket, but the ticket isn’t available at that time. It’s possible to reach out if a ticket becomes available, via the fan’s preferred channel, and potentially increase sales revenue.
Sports analytics is a promising, proven field. Nevertheless, sports analytics—rather than replacing the decisions of coaches, players, and others—can complement decision-making. Performance tracking, pattern detection, predictive analytics, and other types of analytics can score big!