The devil, as they say, is in the details. But there are angels in the data.
Sports organizations are looking for advantages in business and on-the-field competition by gleaning hidden insights from the data they own. They’re using data analytics tools to improve their decision-making, which enables them to plan better and innovate faster.
Use cases for data analytics tools in the sports world vary widely. On the practice court and in training sessions, data can tell an athlete how fatigue is affecting a workout. In the coach’s film room, analysis of game information can help determine the best play to call in a specific situation, or the optimal lineup to win a game. In the arena, studying data can help teams deliver a better experience for fans.
NBA Establishes Leadership in Analytics
The NBA has embraced data analytics in a way that surpasses most other major U.S. sports leagues. To highlight this point, the Golden State Warriors, which has dominated the leagues in recent years, has one of the NBA’s most effective analytics departments. Data analysis is largely credited with the significant increase around the league in 3-point shooting, which has risen in each of the last eight seasons.
Nearly every team in the NBA has hired data analysts as full-time staff members to work with coaches and front office staff. These analysts help teams identify trends that may improve on-court tactics or practice habits. They also help general managers spot undervalued players, so a team can make a trade that works in its favor. Players themselves have utilized analytics tools and devices such as wearables to monitor their sleep and fatigue levels, which can help them to avoid injury and train more effectively.
The league also supports efforts to find new ways to use analytics, holding an annual Hackathon, which also helps it find talented new data analysts.
Data Serves Up an Ace for USTA
Other sports can gain an advantage by breaking down data. Professional tennis players in the U.S. Tennis Association are using analytics through Watson, an analytics engine developed by IBM, to improve their tactics on the court as well as their training regimens.
The analytics engine digests video footage captured during matches and training sessions to reveal insights such as opponents’ tendencies that can be exploited or when and how fatigue affects a player’s workouts. For example, if a specific opponent favors cross-court shots early in a point but hits forehand shots down the line more often as a point progresses, a player can use the observation to position himself more effectively.
USTA employs IBM Watson for various use cases. At the 2017 U.S. Open, for example, the association began using the artificial intelligence technology to generate highlights. The tool also can be used to guide development of younger players who are years away from playing professionally.
NFL Excels with Hard-Hitting Analysis
A few NFL teams have used analytics for more than a decade, and more teams are expanding their analytics departments to help them find an edge. Gleaning an advantage from data analysis can be particularly valuable in a league where teams ascend and drop in the standings quickly from year to year.
To capitalize on this opportunity, teams are looking for analysts to find the insights they need. For example, the Baltimore Ravens have hired two analysts: Sandy Weil, who studies game trends and helps with scouting decisions; and Eugene Shen, who works with the coaching staff to evaluate player performance.
Teams use analytics in scouting operations for draft and free agency decisions, as well as to improve player health (every team in the league uses an electronic health record that can be accessed by on-field personnel via tablets), a crucial consideration for a sport with a concussion epidemic. Some organizations have even advanced to using predictive and prescriptive analytics to enhance their game strategies.
Advances in Soccer, but Skepticism Remains
Soccer has proved to be a particularly difficult game to analyze. It combines the free-flowing nature of a sport like basketball with the same number of players as football (11) and a field of roughly the same size.
Early soccer analytics focused on statistics such as passing percentage and shooting efficiency, but teams in leagues such as the MLS now analyze player movement and action away from the ball. These data are used to create algorithms to improve individual and team behavior, as well as substitution patterns. The success of those efforts is helping the practice catch on: A few years ago, the MLS launched a data and sports science subcommittee, with representatives from every team.
Still, data analytics efforts face skepticism from influential corners in soccer. Former U.S. National Team Coach Bruce Arena, who has won five NCAA titles and five MLS Cups, said, “Analytics in soccer doesn’t mean a whole lot. Analytics and statistics are used for people who don’t know how to analyze the game. This isn’t baseball or football or basketball. We have a very important analytic, and that’s the score. That distorts all the other statistics.”