Wimbledon is a unique event on the British sports calendar. While football, rugby and cricket fans follow their teams throughout the year, the country’s tennis obsession only comes to the fore during a two-week tournament in London.
In many cases, spectators don’t even know the names of most of the players† Their main attraction for the championship is: a summer day indulging in the traditions of a national institution.
Wimbledon organizers want to turn these casual fans into lifelong devotees. To make this possible, they applied a state-of-the-art science to the world’s oldest tennis tournament: AI.
The All England Lawn Tennis Club has partnered with IBM to bring the technology to the masses.
“Lt all starts with the data,” Kevin Farrar, IBM’s leader in UK sports partnerships, told TNW.
game time
At each of Wimbledon’s 18 lanes, analysts record a wide range of data points, from the serve to the winning shot.
They are all high level tennis players. Instead of teaching AI experts about the sport, IBM trains athletes in the basics of data science.
“They are at the provincial level and above tennis players – because they have to interpret the game,” said Farrar. “How do you decide between a forced and unforced error? It helps if you play the game.”
In addition to the statistics recorded in court, IBM uses historical data, automated match tracking systems and NLP analysis of media buzz to gather insights about the players.
Algorithms then convert the data into digital functions, which fans can access in the Wimbledon app.
A Center Court debut to remember @EmmaRaducanu†
IBM’s Match Insights crunch the numbers for Raducanu ? Van Uytvanck @IBM † #Wimbledon
— Wimbledon (@Wimbledon) June 27, 2022
They include the IBM Power Index, which ranks players before and during the tournament. A predictive model then identifies their probability of winning each match.
In the opening days of the tournament, the predictions were 100% accurate on the center and number one courses.
However, this success is not matched on the smaller courts.
“If you go to some outdoor courts and lesser-known players, there’s less data available, so it’s more difficult to get that prediction right,” Farrar said.
Future fans
IBM also uses AI to produce a “Match Insights” feature, which generates player factsheets for matches, and an “In the Media” section, which analyzes expert insights.
Fans can also enter their own predictions, access custom recommendations, and view personalized highlights.
“All of this is designed to spark debate and engage with fans so that Wimbledon can pursue its goal of growing its fan base,” said Farrar.
The tournament’s center court just celebrated a century of play. AI could help lure fans to the sacred grass for the next 100 years.
Contents