Forward of a grand prix weekend, most of us prefer to share predictions or try to guess who will come out on prime on a Sunday. Knowledge scientist Mariana Antaya took these chats one stage additional and constructed a machine studying mannequin to try to predict F1 race outcomes. To date, her mannequin has appropriately known as the winners of three grands prix this season.
“I am a very large Components 1 fan,” says Antaya when talking with Motorsport.com. “Machine studying and all these algorithms are actually extensively utilized in Components 1 by the groups. I do not assume as many individuals know, however the race engineers are utilizing this for his or her technique in actual time.
“So, I wished to attempt to predict the winner as a enjoyable train, simply to see, like, how good we will get with the info that is accessible.”
To do that, Antaya began constructing a mannequin of her personal. Armed with lap instances from final yr’s Australian Grand Prix, which was sourced from the FastF1 API knowledge retailer, Antaya set about evaluating the 2024 race outcome with qualifying performances in 2025.
As soon as the rookies have been faraway from this system, which Antaya admits is the one issue she “interfered with” as there was no knowledge to benchmark towards, she started coaching her mannequin. Utilizing a gradient boosting device, Antaya predicted the lap instances for the race in Albert Park, and her program appropriately picked Lando Norris because the winner.
“I stated on the finish of the video, that is clearly a easy mannequin, and I did not comprehend it was going to foretell proper,” Antaya says. From there, the undertaking began rising because the F1 neighborhood gathered round to see what number of extra races Antaya might appropriately name.
“I wished it to be a crowdsourced kind of factor,” she provides. “So, all the viewers might say ‘I really need you to incorporate climate knowledge in it,’ or ‘I really need you to incorporate the follow classes within the mannequin.’
“I wished folks to inform me what different options they wished so as to add to the mannequin to enhance it over the course of the season.”
Components 1 Fan Mariana Antaya
Picture by: Mariana Antaya
And enhance it has, because the machine studying mannequin is constant to foretell race winners appropriately. This doesn’t imply it’s good, nonetheless, and Antaya is now including extra datapoints to this system to assist enhance its accuracy.
“Having extra knowledge goes to assist the mannequin study extra and it is going to have the ability to make higher predictions,” she explains. “In the event you solely have a lot knowledge, it’ll have a really small thoughts, I assume, and it will not be capable to perceive as a lot.”
In an effort to increase the thoughts of her mannequin, Antaya added climate knowledge forward of the Japanese Grand Prix, which included the prospect of rain throughout the race and observe temperatures at Suzuka. Along with this, wet-weather efficiency of the drivers was additionally added, and this system used this to appropriately predict Max Verstappen’s victory on the race.
The subsequent large step for the mannequin got here forward of the Saudi Arabian Grand Prix this weekend, when it was skilled on every staff’s efficiency up to now this yr. Antaya defined that the additional strand of information would assist her program perceive that groups like McLaren and Williams have made a step ahead in 2025, whereas others equivalent to Crimson Bull aren’t performing persistently in addition to they have been in 2024.
“Now we’re taking into account extra of a holistic image of how effectively the automotive and the staff is performing,” she explains.
‘Shocked’ by the collection
The collection of posts on Instagram and TikTok has been rising in recognition with every successive add, and the clips have even reached Components 1 itself. A handful of engineers from F1 groups on the grid reportedly reached out to Antaya after she began importing, and he or she’s now trying ahead to discovering out how shut she bought to the prediction fashions used within the collection.
“I have been shocked [by the response]. I have been actually, actually stunned,” she says. “I actually do not know [how the teams do it]. That is a black field to me, I want I knew. However I hope I am doing it appropriately or one thing comparable. They’re utilizing, most likely, far more complicated fashions and far more knowledge that they’ve on the automotive although, for certain.”
Hannah Schmitz, Principal Technique Engineer of Crimson Bull Racing
Picture by: Peter Fox – Getty Photos
With three out of 5 race winners appropriately predicted, Antaya is not resting on her laurels as she hopes to make the predicter much more correct. Forward of the Miami Grand Prix, the info scientist says she needs to begin experimenting with extra complicated machine studying processes to extend the accuracy of her predictions and cut back the imply absolute error of the mannequin, which might be regarded as the common distinction between the mannequin’s predictions and the race outcome.
However whereas the accuracy of the mannequin might enhance because of extra datapoints and new processes being carried out, Antaya is conscious that in F1 there’ll all the time be unpredictable components.
“I feel there’s all the time going to be that barrier,” she provides. “It is actually arduous to have the ability to inform that there is going to be a security automotive this lap, and that that is then going to set off another stream of occasions.
“Perhaps we might pull previous knowledge on crash proportion throughout the race, and that is one thing that we will add as one other characteristic. Nevertheless it’s additionally a sport, so it isn’t like we will look into the longer term and see what is going on to occur on a regular basis.”
Learn Additionally:
On this article
Be the primary to know and subscribe for real-time information e mail updates on these matters
Subscribe to information alerts
