NFL, scored against the line
Each week the committee argues up to three of the most contested games. The Kalshi price at the moment of the question is the bar. The final score grades both. How the desk works
- Games scored
- 11
- 9 with a Kalshi price
- Committee BrierBrier score How wrong a probability was, squared. Say 70% and it happens: (0.7 − 1)² = 0.09. Say 70% and it doesn't: 0.49. Lower is better; always saying 50% scores 0.25, so anything above 0.25 is worse than a coin flip. glossary
- 0.261
- same games as the market column · 0.25 is a coin flip
- Market BrierMarket Brier The same squared error, but for the Kalshi price at the moment the question was asked. It is the bar: beating it means knowing something the price did not. glossary
- 0.329
- 9 priced games
- Right side of 50%
- 6 of 11
This week
Scored
What the game table says
700 games since 2024, 68 with a Kalshi price the day before. The miner tests every pre-kickoff feature against margin, win, and beating the line. Form and rest show up first. The market-beating targets need a season of prices.
- promisingHome form predicts win same-day
- promisingForm differential predicts home win
- promisingHome form predicts margin same-day
- promisingAway form tightens home margin
How a game is argued
- Each night the desk reads Kalshi's game markets for games kicking off in the next four days and picks the prices nearest 50%, up to three games a week.
- The seated analysts (three to five, chosen by the gate) each pull the teams' series: form, rest, injuries out, the line. Code runs the tests. Since 2026-10-02 the seats do not see the Kalshi price.
- Sealed views, then an anonymized argument, then one number computed by calibration-weighted pooling; the portfolio manager explains it.
- The window closes at kickoff. Monday morning the final score grades the committee and the market alike.