Week 7 · National Football League

WWCD Picks Board

Sunday, October 25 · today
built 8:00 AM Eastern · odds as of 8:00 AM Eastern · ratings from 7,370 completed games

12
games on the slate
12
still open
0
kicked off
4
ATS fades the winner
Read this before betting any of it

Over 1,138 games this model sits 0.4 points behind the closing spread, and the one promising signal it produced failed a pre-registered out-of-sample test at 18–23. No edge against the spread has been demonstrated. Treat the ATS column as a record of where the model and the market disagree, not as plays.

The straight-up column is the part that earns its keep, in a pick’em pool where you are beating other entrants rather than a sportsbook. A straight-up pick is a moneyline bet, so the moneyline column shows the price it would be taken at and whether the model’s probability beats it. That comparison has not been validated either.

9:30 amopen1 game
PIT-3.0
atNO+3.0
sitting on 3 · 14.7% of games land here
against the spread
NO +3.0
50% below break-even
gap +0.6 · model +2.4 vs market +3.0
229 past games at this gap · +0.1σ from a coin flip
moneyline · to win outright
PIT -155
61% toss-up
pool rank 7 of 12
calibrated on 448 held-out games · model says PIT 58%
best number · where to get it
NO +3.0
every book on the same number no better number
consensus is the best on offer
consensus +3.0 · +0.0 better at MyBookie.ag
over / under
over 43.5
48% below break-even
gap +3.4 · model 46.9 vs market 43.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 59%, model says 61% · poor price
points per play PIT 26.1, NO 24.3 · reference only, not used in any pick

1:00 pmopen7 games
IND+6.5
atMIN-6.5
half a point past 6 · 6.7% of games
against the spread
MIN -6.5
48% below break-even
gap +2.2 · model -8.7 vs market -6.5
178 past games at this gap · -0.6σ from a coin flip
moneyline · to win outright
MIN -295
73% lean
pool rank 11 of 12
calibrated on 448 held-out games · model says MIN 78%
best number · where to get it
MIN -6.5
every book on the same number no better number
consensus is the best on offer
consensus -6.5 · +0.0 better at MyBookie.ag
over / under
over 41.5
50% below break-even
gap +2.0 · model 43.5 vs market 41.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 73%, model says 73% · fair price
points per play IND 19.6, MIN 25.2 · reference only, not used in any pick

NYG+10.5
atHOU-10.5
half a point past 10 · 5.0% of games
against the spread
NYG +10.5
52% above break-even, unproven
gap -4.2 · model -6.3 vs market -10.5
101 past games at this gap · +0.5σ from a coin flip
moneyline · to win outright
HOU -485
84% strong
pool rank 12 of 12
calibrated on 448 held-out games · model says HOU 71%
best number · where to get it
NYG +10.5
every book on the same number no better number
consensus is the best on offer
consensus +10.5 · +0.0 better at BetMGM
over / under
over 42.5
48% below break-even
gap +4.3 · model 46.8 vs market 42.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 81%, model says 84% · poor price
points per play NYG 23.8, HOU 24.2 · reference only, not used in any pick

SF-2.5
atATL+2.5
against the spread
SF -2.5
47% below break-even
gap -3.1 · model +5.6 vs market +2.5
118 past games at this gap · -0.6σ from a coin flip
moneyline · to win outright
SF -140
60% toss-up
pool rank 2 of 12
calibrated on 448 held-out games · model says SF 69%
best number · where to get it
SF -2.0
crosses nothing games land on slightly better
BetUS · consensus -2.5
consensus -2.5 · +0.5 better at BetUS
over / under
under 50.5
53% above break-even
gap -2.4 · model 48.1 vs market 50.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 57%, model says 60% · fair price
points per play SF 25.7, ATL 20.5 · reference only, not used in any pick

TB+3.0
atCAR-3.0
sitting on 3 · 14.7% of games land here
against the spread
CAR -3.0
50% below break-even
gap +1.7 · model -4.7 vs market -3.0
206 past games at this gap · -0.1σ from a coin flip
moneyline · to win outright
CAR -148
61% toss-up
pool rank 5 of 12
calibrated on 448 held-out games · model says CAR 66%
best number · where to get it
CAR -2.5
worth 14.7% of win rate take it
FanDuel · consensus -3.0
picks up 3 · 14.7% of games land there
over / under
over 44.5
50% below break-even
gap +1.0 · model 45.5 vs market 44.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 58%, model says 61% · fair price
points per play TB 21.7, CAR 27.7 · reference only, not used in any pick

CIN-3.0
atBAL+3.0
sitting on 3 · 14.7% of games land here
against the spread
BAL +3.0
57% above break-even, unproven
gap +6.2 · model -3.2 vs market +3.0
44 past games at this gap · +0.9σ from a coin flip
moneyline · to win outright
CIN +136
61% toss-up
pool rank 6 of 12
model disagrees: it likes BAL at 61%
best number · where to get it
BAL +3.0
every book on the same number no better number
consensus is the best on offer
consensus +3.0 · +0.0 better at MyBookie.ag
over / under
over 46.0
50% below break-even
gap +1.3 · model 47.3 vs market 46.0
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 42%, model says 61% · fair price
points per play CIN 23.9, BAL 23.9 · reference only, not used in any pick

MIA+4.0
atNYJ-4.0
sitting on 4 · 5.0% of games land here
against the spread
MIA +4.0
50% below break-even
gap -1.5 · model -2.5 vs market -4.0
206 past games at this gap · -0.1σ from a coin flip
moneyline · to win outright
NYJ -198
65% lean
pool rank 9 of 12
calibrated on 448 held-out games · model says NYJ 59%
best number · where to get it
MIA +4.5
worth 5.0% of win rate take it
BetMGM · consensus +4.0
picks up 4 · 5.0% of games land there
over / under
over 39.5
48% below break-even
gap +3.1 · model 42.6 vs market 39.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 65%, model says 65% · poor price
points per play MIA 15.7, NYJ 22.3 · reference only, not used in any pick

CLE-1.5
atTEN+1.5
against the spread
CLE -1.5
50% below break-even
gap -0.9 · model +2.4 vs market +1.5
229 past games at this gap · +0.1σ from a coin flip
moneyline · to win outright
CLE -130
56% toss-up
pool rank 1 of 12
calibrated on 448 held-out games · model says CLE 59%
best number · where to get it
CLE -1.0
crosses nothing games land on slightly better
BetOnline.ag · consensus -1.5
consensus -1.5 · +0.5 better at BetOnline.ag
over / under
over 37.0
53% above break-even
gap +2.6 · model 39.6 vs market 37.0
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 55%, model says 56% · fair price
points per play CLE 18.5, TEN 15.5 · reference only, not used in any pick

4:05 pmopen1 game
DEN-4.5
atARI+4.5
half a point past 4 · 5.0% of games
against the spread
DEN -4.5
50% below break-even
gap -1.1 · model +5.6 vs market +4.5
206 past games at this gap · -0.1σ from a coin flip
moneyline · to win outright
DEN -224
67% lean
pool rank 10 of 12
calibrated on 448 held-out games · model says DEN 69%
best number · where to get it
DEN -4.5
every book on the same number no better number
consensus is the best on offer
consensus -4.5 · +0.0 better at BetMGM
over / under
over 43.0
53% above break-even
gap +2.4 · model 45.4 vs market 43.0
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 67%, model says 67% · fair price
points per play DEN 24.1, ARI 20.7 · reference only, not used in any pick

4:25 pmopen2 games
GB+3.5
atDET-3.5
half a point short of 4 · 5.0% of games
against the spread
GB +3.5
50% below break-even
gap -0.1 · model -3.4 vs market -3.5
229 past games at this gap · +0.1σ from a coin flip
moneyline · to win outright
DET -185
63% lean
pool rank 8 of 12
calibrated on 448 held-out games · model says DET 62%
best number · where to get it
GB +4.0
crosses nothing games land on slightly better
Bovada · consensus +3.5
consensus +3.5 · +0.5 better at Bovada
over / under
under 55.5
45% below break-even
gap -6.4 · model 49.1 vs market 55.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 63%, model says 63% · poor price
points per play GB 23.1, DET 26.8 · reference only, not used in any pick

LA-3.0
atLV+3.0
sitting on 3 · 14.7% of games land here
against the spread
LA -3.0
50% below break-even
gap -0.0 · model +3.0 vs market +3.0
229 past games at this gap · +0.1σ from a coin flip
moneyline · to win outright
LA -173
61% toss-up
pool rank 4 of 12
calibrated on 448 held-out games · model says LA 61%
best number · where to get it
LA -3.0
every book on the same number no better number
consensus is the best on offer
consensus -3.0 · +0.0 better at BetOnline.ag
over / under
no lean
50% below break-even
gap +0.2 · model 48.7 vs market 48.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 62%, model says 61% · poor price
points per play LA 26.1, LV 25.7 · reference only, not used in any pick

8:20 pmopen1 game
KC+3.0
atSEA-3.0
sitting on 3 · 14.7% of games land here
against the spread
SEA -3.0
50% below break-even
gap +1.6 · model -4.6 vs market -3.0
206 past games at this gap · -0.1σ from a coin flip
moneyline · to win outright
SEA -143
61% toss-up
pool rank 3 of 12
calibrated on 448 held-out games · model says SEA 66%
best number · where to get it
SEA -2.5
worth 14.7% of win rate take it
BetRivers · consensus -3.0
picks up 3 · 14.7% of games land there
over / under
over 42.5
50% below break-even
gap +1.2 · model 43.7 vs market 42.5
no totals edge found in 1,156 games · widest gaps do worst

price check market implies 58%, model says 61% · fair price
points per play KC 24.5, SEA 20.6 · reference only, not used in any pick

Over / under
The scoring model’s lean against the market’s total. Across 1,156 games the model’s error is 10.55 points against the market’s 10.22, and no disagreement band beats a coin flip — the widest gaps do worst, 45.4% at five points or more. Shown because the pool asks for a pick, not because there is an edge.
Against the spread
Which side the model prefers at the market’s number, and how often a disagreement that size actually covered across 876 graded games. Every card shows the sample behind its number. No band reaches even one standard error from a coin flip, so none of these is a proven edge, and none is coloured as one.
Moneyline · to win outright
Which side wins the game, with the confidence taken from the closing spread rather than from Elo. Both were scored on 448 held-out games from 2024 and 2025: the market number won on Brier (0.2037 vs 0.2135), log loss and accuracy (68.8% vs 66.5%), and a blend search put zero weight on the model. Every band lands within two points of its label, so 70% on this page means about 70%.
Gap
Model line minus market line. Larger is not better; the 4-point bucket went 18–23 in a clean holdout.
Points per play
A popular whiteboard projection: each team’s points per play times its plays per game, averaged with what the opposing defense allows per play, from this season’s games before this week. Printed for reference and used in no pick. Across 1,074 games from 2022 to 2025 it went 508–538 against the closing spread and missed the margin by 10.5 points against the market’s 9.6.
In play
The game is under way. Only lines quoted before kickoff are shown; live prices move with the scoreboard and are not comparable to a pre-game model.
Confidence
Pool points, highest on the most likely winner. Assigned across the whole slate.

WWCD · lines from The Odds API, results from nflverse · Elo ratings walked forward, never trained on a game they predict.