// NFL forecast lab
Game on.
Let the model call it.
One featured matchup. A probability before kickoff.
A scorecard that keeps us honest afterward.
Featured matchup
Demo pairing · not this week’s scheduleDetroit

Lions
DETGreen Bay

Packers
GBWho gets the win?
Try the reveal with an illustrative forecast.
Sample values only. The trained model is not connected.
Example output · illustrative values
The sample pick: Lions
A 62% forecast still leaves 38% for the Packers. The real experience will pair the model’s probability with the information available when the forecast was saved.
What will sit behind a real forecast?
Pregame team-strength features, a validated model, and a forecast saved before kickoff. Each published pick will show its model version and prediction time.
This example uses a two-outcome display. The initial modeling experiment excludes ties; the live version will need an explicit tie policy before predictions are published. The values above are hand-authored to demonstrate the interface.
Read the modeling plan →Demo runs never count toward the public record.
// after the final whistle
The public record.
- Correct / settled
- 0 / 0
- Featured games only
- Pick accuracy
- —
- No settled predictions yet
- Probability quality
- —
- Brier score · lower is better
The first pick starts the story.
Once live, every featured forecast stays here: the pick, its probability, the final score, and whether we got it right. Wins and misses.
This record will cover the featured matchups, with comparisons against the same games’ baseline forecasts. Historical testing will be reported separately.
- 01
Choose the week’s matchup
A weekly schedule, team identities, and one featured game selected before kickoff.
- 02
Save the model’s call
Show the win probabilities and keep the original forecast, timestamp, and model version.
- 03
Let the result speak
Settle the game, keep the misses, and update both pick accuracy and probability scores.
A Thomas Howard project. Interface preview; live predictions are not available yet. Team logos via nflverse team metadata and ESPN. Independent of the NFL and its teams.