Project 01 · Win-probability engine · 405,000 NFL plays · 2015–2024

SHOULD THEY HAVE
GONE FOR IT?

Set any game state. Get the call the math actually favors: go, punt, or field goal, with the win probability each choice buys. This is expected-value maximization under uncertainty, applied to the most-second-guessed decision in football.

GAME STATE
OWN
OPP
OPP 45 · 4th & 3
THE VERDICT
GO FOR IT
+0.0 win-prob points vs. the next-best option

Win probability is modeled from every 1st-and-10 outcome each choice can lead to. Rare, extreme states carry more noise. v1 has no weather, injuries, or timeout context.

WIN PROBABILITY BURNED BY KICKING

For every real 4th-down punt or field-goal attempt from 2020–2024, when the model preferred going for it, the coach is charged the win probability they gave up. Summed across five seasons. Lower is bolder.

# Coach Team WP burned ▾ Conservative kicks Per kick

HOW THE MODEL DECIDES

A 4th down is a choice between three lotteries. The model prices each one in the only currency that matters at the end of a game: win probability.

  1. Win probability model. A gradient-boosted model trained on ~450,000 plays (nflverse play-by-play, 2015–2024) learns the chance the team with the ball wins, given score, time, field position, down, and distance.
  2. Go for it. Win prob = P(convert) × WP(1st-and-10 at the new spot) + P(fail) × WP(opponent takes over on downs). Conversion rates come from a decade of 3rd- and 4th-down attempts by distance.
  3. Field goal. WP = P(make) × WP(up 3, opponent receives) + P(miss) × WP(opponent takes over at the spot). Make rates are empirical by kick distance.
  4. Punt. WP = WP(opponent takes over at the expected post-punt field position), measured from real punt outcomes by field position.
  5. The option with the highest win probability is the call. The edge shown is how many win-probability points it beats the next-best option by.

Honesty

  • Empirical win probability is noisy in rare states (long distances, extreme score gaps, final seconds). Treat those calls as directional.
  • v1 ignores weather, injuries, kicker/defense quality, and timeouts. A great or terrible kicker moves the field-goal line the model can't see.
  • The coach leaderboard uses the model's own preference as the yardstick. It measures conservatism against this model, not against ground truth. Public models like nfl4th reach the same broad conclusion: coaches kick too much.

Data & build

Play-by-play from nflverse (open, no scraping of Sports-Reference). The Python pipeline pulls ten seasons locally, trains the model, and bakes small JSON lookup tables; the page does all the decision math in your browser, so there is zero server cost and the arithmetic is fully inspectable. Academic anchor: arXiv:2311.03490.

Built end-to-end with Claude Code — data pipeline, win-probability model, and this interface. Source: github.com/agv117/nfl-4th-down. Project 01 in a series of interactive sports-analytics builds.