The use of Big Data analytics in the world of sports has seen significant growth in recent years. For example, a company known as Baseball Info Solutions (BIS) provided data to 21 of the 30 major league clubs during the 2014 season.
As NBC’s Ronald Blum reports, digital innovations on the field are now touted with the intensity of agents trumpeting players. Indeed, data from BIS helped convince San Francisco to position Juan Perez near the left-field line and shallow in Game 7 of the World Series against Kansas City’s Nori Aoki, a left-handed spray hitter.
“A ball off the end of Aoki’s bat that at first seemed headed to the corner for a tying fifth-inning double instead became an out,” Blum explained. “Madison Bumgarner found his dominating form and the Giants held their 3-2 lead to win their third title in five seasons.”
According to BIS president Ben Jedlovec, the company reviews each big league game three times: once live, then twice more the next day. The resulting data is then made available to teams, which have the option to purchase customized analytics reports or just the raw data.
Big Data also play a major role in scouting, with companies like Inside-Edge offering an analytics-based approach to the activity.
“Instead of just using a spray chart to calculate a player’s defensive value, their scouts watch every single play from every single team—twice,” writes Andrew Beaton and Michael Salfino of the WSJ. “By taking positioning into account in grading the difficulty of plays, Inside-Edge scouts not only found that the range of many players was being overstated, but so too was the overall importance of defense in preventing runs.”
Interestingly, Big Data analytics revealed the quality of a fielder doesn’t actually seem to matter on most plays.
“Inside-Edge partner Kenny Kendrena says 24% of plays are almost always hits and 62% are almost always outs,” Beaton and Salfino confirmed. “The remaining plays where defenders can really distinguish themselves are so infrequent, he said, that the success in converting them can distort a fielder’s true skill.”
Similar to its evolutionary role in baseball, Big Data is also in the process of changing basketball. As Discovery’s Eric Niller points out, high-definition cameras and data analytics are replacing human statisticians and scouts – giving coaches an edge in the game of predicting scores and evaluating performance. More specifically, pro and college teams reportedly use Big Data analytics and machine learning algorithms to analyze games by reviewing images of each player’s activity that are snapped 25 times per second.
“We can extrapolate a ton of information on what they are doing on the floor through machine learning processes,” said Ryan Warkins, associate VP at Stats. “In the past you would need a human to log in this information themselves. You can find out efficiencies of teams and players and it’s all based on storing that raw information at 25 frames per second.”
According to Warkins, SportVU’s algorithms can help coaches determine what a certain player will do at the beginning at end of the shot clock, or help them better understand how players perform when matched up against certain individual opponents. Perhaps not surprisingly, all 30 pro NBA teams, plus five college squads, actively use SportVU.
“You can break down a potential draftee or free agent by their performance,” he added. “Say the Chicago Bulls are looking for someone to replace Tony Snell. (They) want a decent perimeter defender and shoots a corner three-pointer, as well as someone who can dribble-penetrate. You can measure this analytically.”
As we’ve previously discussed on Rambus Press, Big Data analytics span multiple verticals, including healthcare, smart grids, banking and agriculture. In fact, Wikibon analysts see the Big Data market topping $84B in 2026, attaining a 17% compound annual growth rate (CAGR) for the forecast period 2011 to 2026. Meanwhile, IDC estimates the global Big Data and Analytics market will hit $125B in hardware, software and services revenue this year (2015).
Interested in learning more about Big Data? You can check out our article archive here.