New to these reports? Start here

Dotted-underlined words have a plain-English definition — hover or tap them. Every term is also on the glossary page.
"Null" means we found nothing, not that something broke. Most reports here are negative results, on purpose — knowing an idea doesn't work is the point.
Two questions get asked separately. First, is the effect real? Second, is it already priced into the betting odds? An effect can be completely real and still useless to bet on.
A "calibration" row is a self-check. It runs the same method on something already known to be true. If that fails, the whole report is unreliable — so it's reported alongside the findings.
If a confidence interval includes zero, the real effect might be nothing at all, so no claim gets made.

Pre-registration: kicker-points unders in forecast wind (frozen 2026-10-21)

Written after the no-odds analysis (FINDINGS.md, results.json) and BEFORE any kicker prop price was looked at. Do not edit; add dated amendments below.

Rule

Market: player_kicking_points, Under.
Games: outdoor/open US stadiums only (the wind_unders station list).
GFS MOS forecast wind at kickoff of ≥ 12 mph.
Use the latest run issued ≥ 6 h before kickoff (as in backtests/wind_unders).
Line and price: the posted line at the best available price among the captured books, in the last pre-kickoff snapshot.
For historical games, the snapshot ~2 h before kickoff.
Stake: 1 unit on every qualifying kicker, both teams. No other filter.

Data

Historical: Odds API historical event odds, player_kicking_points, 2023–2025 regular season.
Every qualifying windy game, plus an equal random sample of calm (< 10 mph) outdoor games as a control.
The calm sample is drawn with seed 20261021 before purchase.
Forward: every 2026+ game from the live capture (started 2026-10-21).

Pass criteria (all three)

Historical windy-game unders: ROIreturn on investmentProfit as a percentage of the money wagered. +2% means $2 profit per $100 bet. > 0 with a 95% bootstrapbootstrapRe-running a calculation on thousands of resampled versions of the data to see how much the answer wobbles. The spread of those answers becomes the confidence interval. CI (by game) whose lower bound is > −5%, and n ≥ 150 bets.
The calm control shows no comparable under edge (ROI < +3%). If calm unders win too, the finding is "kicker unders win", not wind.
Forward 2026–27: ROI > 0 on the first 100 qualifying bets.

Secondary (reported, not part of pass/fail): field goals made unders under the same rule; line shading (do books post lower lines in wind?).

Why expect it

From the no-odds analysis, 2006–2025: kicker points are 0.37 below the implied-team-total expectation at ≥ 12 mph (CI −0.51 to −0.23), and both halves are negative.
At a 22-point team total, P(under 7.5) rises from 56% to 62%.
The closing total only falls ~0.5 points per team in the same wind.

Risk: books may already shade kicker lines in wind. That is what the prices will show.

Terms in this report

bootstrap return on investment

Kicker-wind pre-registration: historical result (2026-11-02) Kicker scoring and forecast wind (2026-10-21)

Source

          backtests/nfl_kicker_wind/PREREG.md
        

updated 2026-10-21 05:05