The Snow Day Prediction Game was created years ago by a Holland Christian High School teacher. Friend and teacher Ben Talsma introduced it to his Big Rapids students.
“People would all try and evaluate an incoming storm on the basis of its impact and its hype in the media. It’s timing when it was going to strike and also some intangibles. And then we’d use that to figure out what the likelihood of a Snow Day was?”
Now a Learning Solutions Specialist at Van Andel Institute, the competition has been taken to a new level. Talsma teaming up with a Rockford parent and computer programmer who developed an Artificial Intelligence algorithm using ChatGPT and weather data to make Snow Day predictions. Now Rockford students are in on the game.
“Their stats students serve as representatives of humanity. And they are competing against the Machine. The A.I. algorithm called Blizzard.”
The students and the Machine have gone head-to-head three times with A.I. leading with 77%-75% accuracy.
Humans vs the Machine is being shared with districts across the country.
“You know, get kids interested in what predictions and models look like and then applying that to something that they’re interested in.”
You can find Humans vs The Machine/Rockford on Facebook and Instagram.
As for the impending blizzard – a fourth competition – Rockford’s superintendent called for a Snow Day at 4pm Thursday. At that point, the student model had predicted a 98% probability for a Snow Day. The A.I. algorithm a 35% likelihood. Chalk one up for humanity.