Science

Who Wins Steelers at Buccaneers? A.I. Predicts

Pittsburgh's in crisis ahead of this Week 3 match-up.

by Michael Cahill
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 18.0px Georgia} Roy K. Miller/Icon Sportswire

The big storyline this weekend is going to be how the Steelers play after a week of rumors that the locker room has become a complete disaster. Mike Tomlin has reportedly lost the team, Antonio Brown no-showed for practice, and Le’Veon Bell continues his holdout. Other than that, everything is great in Pittsburgh.

For the Buccaneers, the question is whether or not Ryan Fitzpatrick can continue his early season magic and put pressure on management to make a difficult choice when Jameis Winston comes off his four game suspension.

To predict the result of this Week 3 match-up, Unanimous A.I. used what’s known as swarm intelligence to forecast the week’s slate. About 40 NFL enthusiasts worked together as a hive mind to make picks. As you can see in the animation below, each participant controlled a little golden magnet and used it to drag the puck toward the answer they thought was the most likely outcome. As the users saw the puck move toward a particular decision, it triggered a psychological response. They readjusted their decision-making, building toward the consensus you see below.

Vegas has this as a toss-up with the Steelers owning a slight edge. The swarm thinks that it’s a game that can be won by the Buccaneers. QB Ben Roethlisberger looks like a shell of his former self, and the chaos inside the club could give the Bucs a chance steal one from a team that, on paper, is superior.

The Steelers play the Buccaneers at 8:15 p.m. Eastern Monday on ESPN.

Unanimous A.I. has made some scarily accurate predictions in the past using swarm intelligence, as our this article explains. For instance, the swarm picked this year’s Oscar winners with 94 percent accuracy. Here’s Unanimous A.I. founder Louis Rosenberg explaining swarm intelligence at a recent TEDx Talk:

In related news, Unanimous A.I. recently presented a scientific study of its ability to forecast games in the National Hockey League. In a 200-game, 20-week-long study of its Swarm AI in the NHL, it was able to easily outperform Las Vegas expectations, and its “Pick of the Week” was right 85 percent of the time, producing a 170 percent ROI. The paper, titled “Artificial Swarm Intelligence versus Vegas Betting Markets,” was presented at the at the IEEE Developments in eSystems Engineering Conference (DeSE 2018) this month at Downing College in Cambridge, England. In a press release issued with the study, co-author Gregg Wilcox says the technology can be applied to matters outside sports, too. “While it’s fun to predict sports, we are currently applying the same techniques to a wide variety of other domains, including financial forecasting, business forecasting, and medical diagnosis, all with positive results.”

Want to join the hive mind that picks NFL matches every week? Sign up to participate in future predictions

Related Tags