Leer en Español
Start of the third set of the Australian Open final. Daniil Medvedev has won two sets and is ahead 0-1 in the third. The TV picture shows on the court the probability of victory: 96% for the Russian, 4% for the Spaniard Rafael Nadal. The rest is the story of an epic comeback and the milestone of the 21st Grand Slam for the Spaniard. But did Nadal beat the mathematical algorithm? Several experts in sports data analytics analyzed it.
That 4% that the ‘win predictor’ of the Australian tournament gave at that time to a comeback of Nadal –at the beginning of the match gave him a 36% chance of winning– has been the subject of jocular comments of all kinds on social media, all made after the fact, when the tenacity of the player with more major tournaments in the history of men’s tennis turned an almost lost match into an epic triumph.
However, judging by experts consulted by the EFE news agency, the percentage was justified. In 338 matches played by the Spanish tennis player in Grand Slam tournaments, the four main tournaments of the circuit, out of 19 situations in which Nadal had started losing 0-2, he had only come back from two; and in 13 of them in which he faced a player of the top ten of the ATP circuit he had not won in any of them. Until Sunday.
“An algorithm doesn’t beat or beat you. What an algorithm does is from information, such as Rafa Nadal’s results history, see how he has fared in that situation. Nadal had never won in that situation. Does that mean that 4% means that he is not going to win a match? No, but that match, in that situation, played 100 times he would have won it in 4,” explained Jesús Lagos, a partner at ScoutAnalyst, a consulting firm that provides data services to Spanish and European soccer clubs.
In the open era, since 1974, only six tennis players had come back from two sets down in a Grand Slam final: Bjorn Borg (Roland Garros 1974), Ivan Lendl (Roland Garros 1984), André Agassi (Roland Garros 1999), Gastón Gaudio (Roland Garros 2004), Dominic Thiem (US Open 2020) and Novak Djokovic (Roland Garros 2021).
“To be frank, 4% was very generous,” adds Salvador Carmona, CEO of soccer analytics company Driblab, which works with clubs, player agents, and federations.
“From now on, what we all have to think about is whether we are going to have to include other variables in the prediction model, such as fatigue, how much they have run, or whether we only take into account the result. There are things that the model does not take into account. And then there is the Nadal factor, who is not just any tennis player, he is a player with 21 Grand Slams,” he said.
For the data analyst of the sports representation agency YouFirst, Sara Carmona, this case is an example that data in sport is “a complement” and should not be treated as if it were an absolute truth.
“That 4% gives circumstantial information, a probability that does not have to be fulfilled. Although the normal thing would have been that Nadal did not achieve victory, mainly because of the dynamics that the match had, but with Nadal we are talking about an out of series. A competitive animal with a mind as hard-working as his game,” Carmona points out.
Nadal’s epic
The key, Jesús Lagos points out, is to understand how Nadal managed to squeeze out that 4%. “The trick would be to find out under what patterns that 4% occurs. If it’s because you serve less and the opponent misses more, for example. But that in real-time is complicated, and that’s where artificial intelligence brings more value,” he explains.
The Australian Open analyzes its data through a company called Game Insight Group, formed by the Australian Tennis Federation and the University of Victoria in Melbourne. In addition, it is sponsored in this area by the technology consulting firm Infosys, also a sponsor of the ATP circuit, to which it offers its technology platform for data visualization.
This company recently revealed some data that help to understand how Nadal squeezed that 4% chance. After averaging 55% accuracy on his first serve in the first two sets, in the third set, the Spanish champion raised his effectiveness with his serve to 82%. He also went from 11% accuracy with his forehand in the first set to 35% in the fourth.
Another element that shines in the case of Rafa Nadal is mental strength. A key that, according to experts, is not possible to translate into data that can be incorporated into a probabilistic model. “You can’t put it into the model if there is no psychological data provider, and as far as I know, at least in soccer, there isn’t one. In soccer, we usually take into account the idea of playing at home or away, but in tennis, they always play away. Nor do we take into account the weather, or the quality of the playing field,” says Salvador Carmona.
A blow to the industry
The big data analysis sector applied to sports is a booming business. According to the American consulting firm Markets and Markets, these services will grow by 22% annually to add up to a market size of over $5.2 billion by 2024.
Can Rafa Nadal’s achievement against the odds associated with the algorithm affect the credibility of the sector in any way? “It hurts us as an industry. What happened with Nadal happens with this type of predictions in soccer. There are companies that tell clubs that a player is going to score 25 goals, and they don’t get it right. They generate a lot of noise and dissatisfaction,” says Jesús Lagos, of ScoutAnalyst.
For Salvador Carmona, this case will probably be used “as a weapon against the sector,” but it also generates interest that can help the public to get a more accurate idea of what data analytics is. “There is a lot of overinformation, so there will be people who will be curious and read about the subject,” says the founder of Driblab.
