NFL Passing Yards
PROP / UNVALIDATED39 projections26 with a posted line0 model + marketMAE 66.1 vs 68.8 (last-5 average)not tracked in the public results
Lines updated 14 min ago
| SCORE | PLAYER | GAME | MARKET & LINE | MODEL | MARKET FAIR | FORM | BEST PRICE | EDGE / EV |
|---|---|---|---|---|---|---|---|---|
| 17WATCH |  Dak Prescott DAL | DAL@ GBSUN 7:20 PM CT | Under 275.5 Pass Yds | 27052% | 50% -100 3 bk | L5 20% · L10 30% | DraftKings-112 | +2.4%-5.4% |
| 12WATCH |  Jordan LoveGB | DAL@GBSUN 7:20 PM CT | Over 274.5 Pass Yds | 27851% | 50% +101 4 bk | L5 60% · L10 50% | ProphetX-103 | +1.6%-1.9% |
| -- |  Tyrod TaylorGB | DAL@GBSUN 7:20 PM CT | Pass Yds (no line yet) | 99.4 | -- | L10 avg 111 · szn 0.00 | -- | -- |
Model is the expected value for the stat and the probability the model gives the listed side. Market fair is the de-vigged consensus probability for that side, its American price and how many books it rests on. Form is the share of recent games that landed on the listed side of the line, or the player’s own average when there is no line. Edge is the model minus the market; the second figure is the best price against the market. Rows with no line are projections only: prices have not posted.
Market prices
PREVIEW. NFL sportsbook and exchange prices beating the consensus of the other books on the same player, stat and line. Not yet tracked in the public results. Updating live. Kalshi asks are on the +EV terminal.
No prices beating the market
No NFL prop price is beating the other books at the moment. Rows appear around game windows, before the game starts.
Open the +EV terminalMethodology
DISTRIBUTION
Live board. Empirical EWM + Normal. The daily board runs an empirical estimator: exponentially weighted game-log average, blended with a usage-adjusted rate, scaled by an opponent-allowed factor, with a negative-binomial or normal spread fitted from the league's own game-to-game variance. NFL means are calibrated on 2021-2025 outcomes (accuracy only: the pool of quoted players is over-projected by 3-7%). It does not model injuries, lineups, minutes, weather or teammate absences, and it has not been validated against prices.
Research model. XGBoost (Tweedie) + Hurdle-Gamma / Normal, chosen by out-of-sample log score
WHAT THE LIVE BOARD LOOKS AT
- Exponentially weighted game-log average
- Usage-adjusted rate (pass attempts)
- Opponent-allowed factor, shrunk and clipped
LIVE BOARD ACCURACY
SAMPLE
2021-2025 regular seasons
PLAYER-GAMES
2,626
MAE (ENGINE VS L5)
66.1 vs 68.8
MAE CHANGE
-3.9% (se 0.5%)
Full serving-code replay (nfl.props.engine_eval), opponent factor included, as of each regular-season week, 2021-2025. Accuracy of the projection only; it says nothing about beating a price.
RESEARCH MODEL VALIDATION
SAMPLE
Walk-forward 2021-2025
MAE (MODEL VS BASELINE)
--
CRPS (MODEL VS BASELINE)
--
BRIER
--
ECE
--
BLEND c (t)
+0.43 (+2.0)
Result. Beats trailing-mean baselines
Against prices. No edge shown. On the banked weeks (main line, 3+ books) the model-minus-market Brier gap was -0.005 +/- 0.013 (n=83), indistinguishable from zero.
Record. No graded history is published for NFL projections: they are not logged to the public ledger, so there is no win rate or ROI to show.
Source: Walk-forward and banked-market study, 2026-10-14 (NFL prop systems handoff). MAE and CRPS: lower is better. The live board does not run the research model.
Quarterback passing yards against the books' consensus line, from pass volume and the opponent's passing defense.