DailyExpertNews
†
The organizers of Wimbledon, the world’s oldest tennis grand slam and most prestigious grass court tournament, think some of its followers don’t know much about the modern game.
It’s not meant to be a trifle; not everyone can be a recliner pro.
“We did some research a few years ago which showed that most people who engage in Wimbledon aren’t actually tennis fans who play tennis all year round,” said Alexandra Willis, director of marketing and communications at the All England Club, who tournament. †
“What we heard anecdotally was, ‘I’ve heard from a few top players, but I haven’t actually heard from many others’ and ‘this all feels a bit confusing and deceiving,’” she adds.
It is understandable. Tennis is living in an era where the game of men and to some extent the game of women is determined by a small number of dominant players with astonishing career lengths.
To fill the knowledge gap, the All England Club is working with IBM to use artificial intelligence (AI) and big data to increase fan engagement — and predict every match winner in the process.
Think Moneyball, only aimed at the fans.
As part of the “Match Insights with Watson” feature on the Wimbledon app and Wimbeldon.com, each player has been assigned an ever-changing “IBM Power Index” ranking courtesy of IBM Watson, the AI for businesses at the company.
The rankings are generated by analyzing the form, performance and momentum of athletes, explains Kevin Farrar, sports partnership leader at IBM UK & Ireland. “Because it’s updated daily… you can see (players) to watch, (and) it can start identifying possible disrupted alerts – all of which are of interest to the fans,” he explains.
The idea is to help less-initiated fans find players to follow, “to develop their own fandom,” Willis says. Users can choose to follow players and will be presented with personalized highlights as the tournament progresses.
Watson’s party piece uses data to predict each match winner. Shown as a simple percentage probability, the AI makes the call by using millions of data points captured before and during the tournament. Factors include past results between the athletes, current form, and more detailed details such as percentage of first serve won, ace frequency, and percentage of points won when returning first serve.
Farrar explains that tournament data is collected by a team of “very good tennis players” – usually at the provincial level and above – who watch every match at Wimbledon, with three statisticians on show courts and one on the outdoor courts. Hawk-Eye ball and player tracking is also used.
However, not all data entered into the forecaster is based on hard statistics. Intriguingly, positive or negative media sentiment is also taken into account, scanning thousands of news articles about players.
“One of the hallmarks of ‘who is interesting?’ is ‘who is the media excited about?’” says Willis. “Many members of the media, especially in a sport like tennis, where they are with the players week in, week out, have a sense and understanding of how good people – those kinds of soft factors that don’t necessarily show up in (structured data points).”
Farrar reported that Watson predicted the results with “nearly 100% accuracy” on day one of the tournament, but day three caused the first major dismay when the women’s No. 2 and 66% of match favorite Anett Kontaveit were defeated by the unseeded Jule Niemeier in straight sets.
Despite employing one of the world’s most famous AIs, Willis insists “this is not meant to be exact or an exact science.”
And even if Watson loses, it’s still a win-win situation, Farrar emphasizes. “That’s an interesting topic of conversation and it’s engaging with fans, which is the main goal.”
“Sports fans love debate. So we give them something to discuss.”