Fourth & Value · Weekly market review
NFL Week 9 review: the model receipts and the Week 10 watchlist
An audited Week 9 scorecard using frozen pregame data, plus Fourth & Value model-market disagreements to research for Week 10.
Week 9: the market scoreboard
Recorded closes produced 7 overs, 8 unders and 0 pushes. Against our archived market median, 7 games finished over, 8 under and 0 pushed.
The raw totals model direction went 10–5 with 0 pushes and +4.30u across 15 games with archived same-line prices; 0 unpriced directions are excluded from profit/loss. Mean absolute error was 11.03 points for the model versus 10.27 for the archived market median and 10.10 for the recorded close.
The model scorecard
The deduplicated published shortlist contained 130 selections; 119 were conservatively graded and 11 remain unresolved. The graded set went 59–60 with 0 pushes for +3.72u, or 3.1% on units risked. Missing participation or missing statistics remain unresolved rather than becoming automatic unders.
| Market | W–L | Net units | Unresolved |
|---|---|---|---|
| Receptions | 29–21 | +11.13u | 5 |
| Rushing attempts | 11–8 | +2.73u | 0 |
| Rushing yards | 5–3 | +1.76u | 2 |
| Passing completions | 4–4 | +0.30u | 0 |
| Passing yards | 0–1 | -1.00u | 0 |
| Passing touchdowns | 7–11 | -1.90u | 2 |
| Passing attempts | 3–12 | -9.31u | 2 |
Closing-line value report card
Each published pick’s price compared with the closing market: the median no-vig chance across US books at the pick’s exact line, captured in the final minutes before the start. Value at the close is how much more the published price paid than that closing chance justified; beat the close is the share of picks where it was positive; market move is how far the closing chance moved toward our side (positive) or away from it (negative) after the pick. Over many picks, value at the close is the earliest reliable sign of a real edge, long before win–loss results settle down. It is a measure of price, not a guarantee.
| Edition | Picks | Closing prices | Value at the close | Beat the close | Market move |
|---|---|---|---|---|---|
| Morning picks | 2 | 2 | +5.3% | 50% | +3.4 pts |
| Afternoon picks | 0 | 0 | — | — | — |
| All picks this week | 2 | 2 | +5.3% | 50% | +3.4 pts |
| All picks since 2026-10-19 | 7 | 7 | +2.4% | 57% | +0.6 pts |
Probability quality, not just profit
Across 289 representative non-push outcomes with both probabilities available, the model Brier score was 0.2535 versus 0.2493 for the de-vigged consensus. The game-block 95% interval for model minus market Brier was -0.0028 to +0.0121.
A positive one-week return and a better probability score are different claims. This report keeps both because a profitable slate can still expose probability weaknesses, and vice versa.
Week 10: disagreement is a research question
The new weekly refresh is frozen before the first kickoff. The largest raw totals disagreements are:
- HOU @ CLE: model 46.7 vs archived median 40.0 (+6.7). This is a research gap, not a calibrated edge.
- LA @ ARI: model 45.9 vs archived median 39.5 (+6.4). This is a research gap, not a calibrated edge.
- CAR @ NO: model 42.6 vs archived median 48.5 (-5.9). This is a research gap, not a calibrated edge.
- SF @ DAL: model 50.1 vs archived median 55.5 (-5.4). This is a research gap, not a calibrated edge.
- SEA @ LV: model 44.7 vs archived median 40.5 (+4.2). This is a research gap, not a calibrated edge.
Player props to recheck
- Fernando Mendoza Passing touchdowns under 0.5 at draftkings (+192); saved model mean 0.01, model probability 55.8%, estimated EV +62.9%. Calibration fitted; not prospectively validated
- Tanner Arkin Receiving yards over 0.5 at betrivers (+200); saved model mean 26.15, model probability 51.6%, estimated EV +54.9%. Calibration fitted; not prospectively validated
- Cam Ward Passing touchdowns under 0.5 at draftkings (+203); saved model mean 0.78, model probability 50.0%, estimated EV +51.5%. Calibration fitted; not prospectively validated
- Quinshon Judkins Receptions over 1.5 at draftkings (+162); saved model mean 2.65, model probability 54.8%, estimated EV +43.5%. Calibration fitted; not prospectively validated
- Drew Sample Receptions over 1.5 at betonlineag (+161); saved model mean 1.98, model probability 54.8%, estimated EV +42.9%. Calibration fitted; not prospectively validated
These are saved prices from the weekly archive. Recheck the current line, price, injury status and role before treating any one of them as actionable. Model status labels are shown rather than hidden.
Audit notes
The scorecard uses hash-verified immutable weekly pregame archives.
The completed-week scorecard uses only the frozen pregame archive for Week 9 and official results/player statistics available after the games. The preview uses a separate frozen Week 10 archive. The workflow refuses to create a new archive after a game has started, refuses to overwrite an existing archive whose hashes do not match, and refuses to publish a review while any official Week 9 game remains unplayed.
Download the public review data · Current NFL board · How updates work · All recaps · Previous weekly review · Back to Fourth & Value