This is not a snub; not everyone can be a professional in the chair.
“A few years ago, we did a study that showed us that the majority of people who play Wimbledon are not really year-round tennis fans,” says Alexandra Willis, director of marketing and communications for the host All England Club. .
“We accidentally heard, ‘I’ve heard of a few top players, but I haven’t really heard of many others,’ and ‘It all seems a bit confusing and misleading,'” she adds.
This is clear. Tennis is in an era where the men’s and, to some extent, the women’s game has been defined by a small proportion of dominant players with astonishing career lengths.
To fill the knowledge gap, the All England Club has teamed up with IBM to use artificial intelligence (AI) and big data to increase engagement and try to predict the winner of each match in the process.
Think of Moneyball, which is only for fans.
“Rankings are based on an analysis of the form, performance and momentum of the athletes,” explains Kevin Farrar, Head of IBM Sports Partnerships in the UK and Ireland. “Because it’s updated daily… you can see (players) that need to be watched, (and) it can start to pick up potential upset warnings – all of which are interesting for fans,” he explains.
The idea is to help less-initiated fans find players to follow, “growing their own fandom,” Willis says. Users can track players and receive personalized reviews as the tournament progresses.
Part of Watson’s party uses the data to predict the winner of each match. Displayed as a simple percentage chance, the AI makes the call based on millions of data points recorded before and during the tournament. Factors include previous performance between athletes, current form, and more details such as 1st inning win percentage, aces frequency, and percentage of points won since 1st inning.
However, not all data fed into the predictor is based on exact statistics. Curiously, positive or negative sentiment in the media is also taken into account when scanning thousands of news articles about players.
“One of the markers of “who cares?” “Who cares about the media?” Willis says. “Many members of the media, especially in a sport like tennis where they spend week after week with the players, feel and understand how well people play—those soft factors that don’t necessarily show up at (structured data points) . “
Farrar reported that Watson predicted the results with “virtually 100% accuracy” on the first day of the tournament, but the third day was the first big disappointment when women’s No. 2 seed and match favorite 66% Anette Kontaveit was beaten by unseeded Jule Niemeyer in straight sets. .
Despite using one of the world’s most famous artificial intelligences, Willis insists that “this does not pretend to be exact or exact science.”
And even if Watson loses, it’s still a win-win, Farrar insists. “It’s an interesting topic to talk about and it’s fan engagement that’s a key goal.”
“Sports fans love debate. Therefore, we give them a reason for discussion.”