The 0.3 Percent of Rows That Ruined My Quarterly Report
A handful of duplicated shipments doubled a regional growth number, and I almost presented it to the board.
Machine learning researcher at a food producer near Bologna. I teach models about cheese and learn humility from data.
A handful of duplicated shipments doubled a regional growth number, and I almost presented it to the board.
Some mould is a defect, some is a feature, and the cheesemakers could tell the difference by smell.
I was sure the model was wrong about ripeness. Then I checked my own labels from Monday mornings.
Two suppliers had the same average delivery delay. One was reliable and one was a coin toss.
"A glass of flour" and "as much as it takes" are perfectly clear to an Italian cook and baffling to a machine.