Return to site

Second Spectrum Aims to Change how We View the Game of Basketball

· Second Spectrum,NBA,Basketball,Machine Learning,Ai

Second Spectrum Aims to Change how We View the Game of Basketball

 

Upon hearing “artificial intelligence in basketball,” most people will think of robots sinking shot after shot. With recent technological advancements, these robots are all too common. For instance, Toyota, an automobile company, developed a robot named Cue using machine learning so that the robot was able to make free throws with almost 100% accuracy after 200,000 practice shots. Machines have come a long way from just shooting basketballs. Software companies like Second Spectrum are developing machines that will change the way we view and understand the game.

On September 22, 2016, the NBA (National Basketball Association) partnered with Second Spectrum and Sportsradar in order to “expand the league’s global distribution of statistics and implement a new, state-of-the-art league wide player-tracking system” as stated on the official NBA press release. The partnership made Sportsradar the official provider of real-time NBA statistics while making Second Spectrum the official optical tracking provider of the league. While Sportsradar’s role focuses more on the widespread distribution of player and game data, Second Spectrum uses its unique technology and player-tracking systems to “provide advanced statistics, such as [player] speed, distances, drives, paint touches, and defensive impact.”

In two separate interviews, Second Spectrum computer vision engineer Jenna Lake and Board Observer Steve Ballmer explain aspects of their software and its practical uses. “So, we’ve been focused in on [NBA players]...” Jenna Lake states in her interview with Mike Delgado on Experian. “We said, ‘How is this player in this position with these other people?’ And you can watch every single person, so you can say, ‘I would like to see the defensive moves that this person can do. I’d like to see is this person on the court most effective.’

You can be looking at maps and say, ‘Of this player, on the court, he is successful more on the left than the right or he’s more successful if he works with these people or those people.’ So, it’s a very interesting kind of way of exposing the data even more for these coaches, for them to understand in even greater detail what’s happening.” Clearly, Jenna and Second Spectrum believe their technology can become extremely useful for coaches and training staff. Optimally, the software would be able to identify player weaknesses and strengths using exact statistics. For instance, after a Lebron James drive results in a layup, the system may detect that Lebron scores on 80% of his drives. Labeling this as a strength, the coaches may call for more floor spacing in order to encourage Lebron to drive into the paint more.

Steve Ballmer, a former Microsoft CEO, continues this discussion at a Recode conference. “I get jazzed up about what’s possible [with Second Spectrum].” He then plays a video which showcases the company’s software: the video is of a few Clippers plays from the past season, and while each play is going on, information about players on the court are displayed including names, fantasy points, stats, and more. The video also presents the customizations that the company is proposing, an example being the “fun view,” depicting Blake Griffin jamming a hammer into a rim with flashy side effects instead of a regular dunk.

Ballmer goes on to explain how these customizations allow various customers to be satisfied with the company’s product as it addresses the needs of the casual viewer, the stats nerd, or a young kid looking for excitement. Interestingly, Ballmer was also asked by a person who didn’t follow sports whether artificial intelligence could one day replace human players. Laughing at first, Ballmer proceeds to state the obvious; because of the “energy [and] charisma of the guys, I’m not real worried about this [sport] getting virtualized out of existence.” The accomplished tech CEO reminds us that despite AI’s rapid advancement, it should still be used as a tool.

This artificial intelligence has major implications for the league. Second Spectrum’s software improves NBA teams, coaches, players, and fans’ ability to analyze the game. Easy access to advanced statistics allows precise analysis of team strengths and weaknesses, leading to more accurate moves in trades, free agency, and the draft. Even though there are plenty of human analysts who analyze teams and interpret game data, there is simply too much information. For instance, any analyst could tell you that Lebron drives a lot, and does it well. However, machines can efficiently track specific data such as Lebron’s number of drives and what % success he has when driving, data which may take multiple human analysts a longer time to get right. As artificial intelligence continues to improve and scientists achieve new breakthroughs, Second Spectrum’s software will inevitably follow along and provide more game-changing support to NBA teams and players.

Written by Michael Ding, Edited by Jack Vasquez & Alexander Fleiss

All Posts
×

Almost done…

We just sent you an email. Please click the link in the email to confirm your subscription!

OKSubscriptions powered by Strikingly