Science

Who Wins Lions at Cowboys? A.I. Predicts

Call this one the Relevance Bowl.

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

Call this one the Relevance Bowl. In this battle between 1-2 teams, someone will claw its way back to the break-even mark, while the other will likely slide out of the playoff picture entirely, ne’er to return. First-year Lions coach and Belichick disciple Matt Patricia managed to knock off his former employer last week after dropping a brace of games to start 2018. The Lions even managed to produce a 100-yard rusher in rookie Kerryon Johnson for the first time in the past five years. Not bad against New England, the resident Baba Yaga of the NFL.

Meanwhile, all is not well in Jerry World. A year ago, dem Boys built their identity by relying on the league’s second-best rushing attack. This season, injuries along the front line have downgraded the Dallas rushing offense from elite to merely above-average. Quarterback Dak Prescott’s development also appears to have stalled after a promising debut in 2016, and the team lacks a true No. 1 receiver after Dallas released Dez Bryant in the offseason. The Cowboys will also take the field without the services of the talented but fragile linebacker Sean Lee.

Even so, mount up with the Cowboys this weekend. Call it a hunch, or call it the self-loathing of a Jets fan who saw Gang Green beat the Lions like a dusty rug in Week 1, only to regress to the mean in the two games since. My prediction: Cowboys 27, Lions 19. But how did an NFL hive-mind decide?

To predict the result of this Week 4 match-up, Unanimous A.I. used what’s known as swarm intelligence to forecast the week’s slate. A swarm of 34 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. It’s an artificial intelligence produced by human brains working together as a swarm.

The 34 NFL experts have 73 percent confidence that they have low confidence that the Cowboys will indeed beat the visiting Lions, moving quickly to make their decision.

The Lions play at the Cowboys at 1 p.m. Eastern Sunday on Fox.

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