How the U.S. Open Is Using Artificial Intelligence to Stay Running Smoothly

How the U.S. Open Is Using Artificial Intelligence to Stay Running Smoothly

The U.S. Open pits 256 players against each other, competing for more than $50 million in prize money in this year's Grand Slam event. A quarter-million points will be scored during the two-week tournament in Queens, N.Y. and at any given time, 17 different matches can be in progress.

To make sense of all that, and serve up better, quicker digital access, the U.S. Tennis Association is using a special weapon: IBM Watson. The artificial intelligence system will help the USTA sort through thousands of highlights each day, selecting the best ones using its own scoring system. Fans not in front of a TV will then be able to see those highlights almost instantly.

"The question is, how do we give our fans the best experience?" says Kirsten Corio, the USTA's managing director of digital strategy, from within Watson's control room in the bowels of Arthur Ashe Stadium. "We have to deliver them content in near real time."

Watson's new system, called Cognitive Highlights, measures the volume of the crowd (which is known to be raucous), the commentator's analysis, and the players' reactions. It assigns each of those a score from 0 to 1.00, then uses those inputs to determine an Overall Excitement score. A point that results in a player yelling and fist pumping, then, will generate a higher score than one in which she pats her racket against her leg. The system can also parse the analysts' language, so a "solid" shot won't score as well as an "awesome" one.

The system was first rolled out at the Masters golf tournament in April. At the time it was only used internally, with the Augusta National team using it as a guide as to what highlights to feature on its app and website. Now, Watson's algorithm will decide which clips are worthy, and those videos will be pushed directly to the phones of those who downloaded the U.S Open app and opted in. Fans are able to choose which players' highlights they want delivered.

IBM is dubbing its new set of video tools Watson Media, and the company says it envisions the system being used for TV broadcasts. ESPN, for example, has to sort through highlights of every major sport for its programming, and local news stations need to come up with highlights of hometown teams for their nightly rundowns. If Watson Media works as advertised, it could help make that process faster and easier.

IBM has been seeking ways to monetize Watson ever since it burst on the scene by soundly defeating Jeopardy champions in 2011. The A.I. system is currently the brains of Pepper, the robot from SoftBank meant to serve as an assistant-slash-companion to humans. Whirlpool uses Watson to look for flaws in its connected devices, and Under Armour's health app uses the tech to give users insights about their fitness and sleep habits.

The A.I. system's role at the Open also extends to the fan experience: Using the tournament's app, a spectator can ask Watson a question, like "What court is Nick Kyrgios playing on?" or "Where is the nearest ATM?" and Watson should be able to provide an answer.

The U.S. Open draws about 700,000 fans to the Billie Jean King National Tennis Center over the course of 14 days. This year's tournament is set to wrap up September 10.

Images Powered by Shutterstock