NFL Week 7
THU · 7:15 PM
NE50.54-2
CHI-34-2
SUN · 8:30 AM
PIT-3.54-2
NO44.52-4
SUN · 12:00 PM
CIN-1.53-2
BAL48.54-2
SUN · 12:00 PM
CLE-1.54-2
TEN37.51-5
SUN · 12:00 PM
IND41.52-4
MIN-6.55-0
SUN · 12:00 PM
MIA39.50-5
NYJ-4.52-4
SUN · 12:00 PM1 Pick
NYG42.53-2-1
HOU-10.52-4
SUN · 12:00 PM2 Picks
SF-36-0
ATL49.52-4
SUN · 12:00 PM
TB44.51-5
CAR-33-2
SUN · 3:05 PM
DEN-4.54-2
ARI43.52-4
SUN · 3:25 PM1 Pick
GB53.54-2
DET-33-2
SUN · 3:25 PM
LA-4.52-4
LV48.53-3
SUN · 7:20 PM
KC42.55-0
SEA-2.53-3
MON · 7:15 PM
DAL-4.52-4
PHI44.52-4
← Models / WR Model

How the WR Model Works

What you're looking at

Each week our model projects a receiving-yards and receptions line for every team's WR1 and WR2 (plus other receivers who play at least 40% of snaps). "Our Line" is the model's median projection rounded to the nearest half point; "Range" is its 25th–75th percentile band.

The model

A LightGBM quantile ensemble trained on 2021-present player-game data: target and air-yards share, snap rates, depth-chart role, injuries, team pass-rate-over-expected and pace, opponent pass-defense EPA and pressure, Vegas totals/spreads, and Next Gen Stats separation metrics. The five quantile predictions form a full probability curve, so any sportsbook line can be priced as a calibrated P(over).

Edges and flags

"Book" is the sportsbook line we evaluated (Hard Rock when it posts one). "P(Over)" is the model's calibrated probability the player clears that line. "Edge" compares that to the de-vigged sharp-market consensus (Pinnacle preferred). The ⚑ flag marks plays where the edge is at least 4 points AND the sharp market leans the same way against Hard Rock's price.

Grading

After games finish, every prediction is graded against the evaluated line, and flagged edges get closing-line-value (CLV) tracking — how much the market moved toward or away from our number by kickoff, in probability terms. The performance strip shows the last four graded weeks.

Receiving Yards Receptions WR1/WR2 only
Flagged edges (last 4 graded wks)8-5
Hit rate61.5%
Mean CLV+2.59 pts
Player Team Opp Our Line Range (q25–q75) Book Book Line P(Over) Edge ⚑
A.J. Brown WR1 NE CHI 47.0 30.3–77 hardrockbet 69.5 48.1% -5.3 pts
DK Metcalf WR1 PIT NO 50.5 30.5–80.9 hardrockbet 53.5 48.8% -1.2 pts
Amon-Ra St. Brown WR1 DET GB 71.0 42.3–90.3 hardrockbet 78.5 48.8% -1.2 pts
Chris Olave WR1 NO PIT 70.0 47.2–103.7 hardrockbet 76.5 48.8% -1.2 pts
Jaxon Smith-Njigba WR1 SEA KC 77.5 50.2–102.2 hardrockbet 92.5 48.8% -1.2 pts
Matthew Golden WR1 GB DET 62.0 38.5–87.6 hardrockbet 73.5 48.8% -1.2 pts
Luther Burden III WR1 CHI NE 47.5 25.5–68.4 hardrockbet 55.5 48.8% -1.2 pts
Keenan Allen WR1 IND MIN 37.5 21.6–61.7 — — — —
Mike Evans WR1 SF ATL 61.5 33–82.6 — — — —
Justin Jefferson WR1 MIN IND 68.5 33–91 — — — —
CeeDee Lamb WR1 DAL PHI 64.5 47.4–91.1 — — — —
Nico Collins WR1 HOU NYG 60.0 32.6–88.6 — — — —
Jaylen Waddle WR1 DEN ARI 40.0 25.3–66.5 — — — —
Ja'Marr Chase WR1 CIN BAL 61.5 37.1–90.7 — — — —
DeVonta Smith WR1 PHI DAL 55.5 36.7–82.2 — — — —
Drake London WR1 ATL SF 68.0 42.3–94.7 — — — —
Garrett Wilson WR1 NYJ MIA 58.0 35.7–82.6 — — — —
Michael Wilson WR1 ARI DEN 59.0 37.4–92.4 — — — —
Tre Tucker WR1 LV LA 43.5 22.9–65 — — — —
Zay Flowers WR1 BAL CIN 77.5 42.9–107.8 — — — —
Rashee Rice WR1 KC SEA 47.5 31.3–77.3 — — — —
Puka Nacua WR1 LA LV 71.5 50.4–99.9 — — — —
Malik Nabers WR1 NYG HOU 63.0 39.8–77.8 — — — —
Malik Washington WR1 MIA NYJ 40.0 23.1–64.4 — — — —
Tetairoa McMillan WR1 CAR TB 61.0 40.6–87.7 — — — —
Emeka Egbuka WR1 TB CAR 46.5 24–73.6 — — — —
Carnell Tate WR1 TEN CLE 56.0 33.8–74.5 — — — —
KC Concepcion WR1 CLE TEN 31.0 16.5–50.9 — — — —
Cooper Kupp WR2 SEA KC 28.5 13.9–48.8 hardrockbet 24.5 51.5% +2 pts
Rome Odunze WR2 CHI NE 43.0 22.3–70 hardrockbet 45.5 48.8% -1.7 pts
Devaughn Vele WR2 NO PIT 44.0 26.5–68.9 hardrockbet 41.5 51.5% +1.6 pts
Christian Watson WR2 GB DET 61.0 33.7–95.5 hardrockbet 73.5 48.8% -1.6 pts
Jameson Williams WR2 DET GB 52.5 20.8–67.7 hardrockbet 53.5 48.8% -1.2 pts
Germie Bernard WR2 PIT NO 36.0 18–63.5 hardrockbet 53.5 48.8% -1.2 pts
Davante Adams WR2 LA LV 61.0 31.2–82.6 — — — —
Tyreek Hill WR2 MIA NYJ 40.0 20.6–61.1 — — — —
Kendrick Bourne WR2 ARI DEN 25.5 10.3–47.7 — — — —
Mack Hollins WR2 NE CHI 40.0 21.3–64.4 — — — —
Courtland Sutton WR2 DEN ARI 29.0 10.6–52.5 — — — —
Darius Slayton WR2 NYG HOU 16.0 10.7–35.9 — — — —
Brandon Aiyuk WR2 SF ATL 42.0 17–53.5 — — — —
Tee Higgins WR2 CIN BAL 60.5 34.6–89.7 — — — —
Rashod Bateman WR2 BAL CIN 25.5 13.8–45.2 — — — —
George Pickens WR2 DAL PHI 53.0 29.2–76.2 — — — —
Jahan Dotson WR2 ATL SF 31.0 13.3–56 — — — —
Wan'Dale Robinson WR2 TEN CLE 38.0 25.8–61.6 — — — —
Tank Dell WR2 HOU NYG 28.5 15.6–48.5 — — — —
Jordan Addison WR2 MIN IND 40.5 16.2–64.8 — — — —
Josh Downs WR2 IND MIN 38.5 24.4–61.9 — — — —
Jalen Coker WR2 CAR TB 54.0 31.7–78 — — — —
Adonai Mitchell WR2 NYJ MIA 51.0 24.4–70.2 — — — —
Xavier Worthy WR2 KC SEA 36.5 19.9–52.8 — — — —
Makai Lemon WR2 PHI DAL 26.5 10.5–46.2 — — — —
Denzel Boston WR2 CLE TEN 50.0 25.2–77.6 — — — —
Methodology. A LightGBM quantile model (q10–q90) trained on nflverse player-game data since 2021 projects each receiver's yardage and receptions distribution from role (target/air-yards share, snaps, depth chart, injuries), team tendencies (pass rate over expected, pace), opponent pass defense (EPA, pressure), and game environment (Vegas totals, spread, venue). Quantiles become a full probability curve, calibrated against three seasons of real closing lines, so P(over) is priced for the actual book line. Edges compare our probability to the de-vigged sharp market; validation is strictly walk-forward (the model never sees the week it predicts). Predictions freeze when published and grade automatically after games — history and CLV are tracked on every flagged edge.