Current stored projection week
Football intelligence
Open the football site ↗The players behind the forecast.
Inspect the stored weekly fantasy projections, their ranges and the populations behind them.
Coverage in this snapshot
From the same source
Projection leaders
Stored top 20, not the full player universe. Ranges are model outputs; calibration is evaluated separately.
| Player | Pos | Team | Opponent | Projected points | 10th percentile | 90th percentile |
|---|---|---|---|---|---|---|
| Cam Skattebo | RB | NYG | WAS | 35.5 | 0.7 | 13.8 |
| Brock Purdy | QB | SF | DAL | 26.9 | 15.8 | 38.8 |
| Ja'Marr Chase | WR | CIN | PIT | 25.8 | 5.5 | 32.9 |
| Chris Olave | WR | NO | CAR | 24.8 | 3.7 | 28.2 |
| Josh Downs | WR | KC | ATL | 24.0 | 1.3 | 18.9 |
| Josh Allen | QB | BUF | NYJ | 23.0 | 12.4 | 34.6 |
| Jonathan Taylor | RB | IND | MIA | 21.8 | 8.3 | 31.0 |
| Jaylen Warren | RB | PIT | CIN | 21.4 | 6.1 | 27.5 |
| Jahmyr Gibbs | RB | DET | NE | 20.9 | 8.8 | 32.5 |
| Jalen Coker | WR | CAR | NO | 20.7 | 0.1 | 16.2 |
| Drake Maye | QB | NE | DET | 20.2 | 9.6 | 31.5 |
| Jayden Daniels | QB | WAS | NYG | 20.0 | 9.3 | 31.4 |
| Joe Burrow | QB | CIN | PIT | 19.9 | 9.2 | 31.3 |
| Bijan Robinson | RB | ATL | KC | 19.5 | 8.2 | 32.8 |
| Matthew Stafford | QB | LA | ARI | 19.3 | 7.9 | 30.5 |
| Justin Jefferson | WR | MIN | GB | 19.3 | 12.5 | 46.7 |
| Jordan Love | QB | GB | MIN | 19.2 | 7.7 | 30.4 |
| Patrick Mahomes | QB | KC | ATL | 19.1 | 7.5 | 30.3 |
| Dak Prescott | QB | DAL | SF | 18.8 | 6.8 | 29.9 |
| Justin Herbert | QB | LAC | BAL | 18.2 | 5.6 | 29.1 |
Position coverage
| Position | Players | Average projection |
|---|---|---|
| WR | 208 | 3.8 |
| RB | 134 | 5.4 |
| TE | 120 | 2.4 |
| QB | 63 | 8.8 |
| DEF | 28 | 11.4 |
| K | 10 | 8.3 |
Projection measurement · Nov 17 · 10:41 AM MT
Build commitments
Source: executable build plan. A completed item is not proof of betting edge.
| Item | State | Work |
|---|---|---|
| T-02 | done | T-02 — Regularised adjusted plus-minus at the play grain: a sparse design matrix (players on field × ro |
| A-02 | done | A-02 — P(active) → P(plays \| active) → snap share \| plays. LightGBM plus isotonic, fitted at each loc |
| A-05 | done | A-05 — For each trajectory, draw who is active, the role depth chart, and the on-field set for each per |
| T-05 | done | T-05 — Weekly state-space update per player-skill: process noise by age and position, a shock term on r |
| A-03 | done | A-03 — Bets go down early, so forecast the injury report itself: P(Friday status \| Tuesday information |
| A-04 | done | A-04 — Per-snap exit hazard by position, age, injury history, surface and workload. Inside the simulato |
| A-06 | done | A-06 — Role regime changes as a changepoint posterior on snap share (`regime.py` and `kalman_share` exi |
| A-07 | done | A-07 — Audit: when a player is removed, where do the opportunities go, in the simulator and in reality. |
| T-08 | done | T-08 — Every rating family is scored on what it adds to the kernel and logged to the ledger. | — |
| T-09 | done | T-09 — Shrinkage audit DONE: five families, each with a held-out comparison |
| T-01 | done | T-01 — The role of every player on every play: passer, carrier, target, route runner, pass blocker, run |
| T-03 | done | T-03 — Directly measured component skills with shrinkage, from NGS, PFR advanced, FTN and pbp (the comp |
| T-06 | done | T-06 — The lineup → unit function: a learned map from the on-field players' vectors to the unit quantit |
| T-07 | done | T-07 — From the tracking releases: speed, acceleration, separation at throw, get-off, closing speed. Th |
| T-04 | done | T-04 — Priors for players with little history: draft pick (the only B-hypothesis that ever paid, B13/B4 |
| A-01 | done | A-01 — The Wed/Thu/Fri practice-status and game-status ladder, 2016–2026, as-of, from `inj_raw` and C-1 |
Desk roster
5 staffed, 1 partial, 0 struck. Every job the operating model charters for this desk (docs/WHAT-I-WAS-MISSING.md #4), against what actually runs in this repo -- not what the tab above implies.
| Job | Status | Evidence |
|---|---|---|
| Scheme & Film Analyst Represents concepts, fronts, coverages, protections, route families, and matchup mechanisms. | partial | research/build_defense_policy.py measures each defence's man-vs-zone coverage rate off nflverse coverage tags (2018+, ~40-50% of plays) and feeds it to the defensive policy -- a coverage tendency, not a route-family, front, or protection concept model; the film sensor that would add those (C-16) is not commissioned. [independent review 2026-09-23: was struck] |
| Roster & Role Analyst Maintains who can play, where, how much, and whose opportunity changes. | staffed | research/playgrain/participation_impute.py and playerweek/coachsnap.py track depth charts and snap share, though participation_impute.py's own gate (Jaccard >= 0.85) is not yet met (measured 0.7299, P-08). |
| Coaching Policy Analyst Models play-caller behavior as context-dependent choices rather than personality labels. | staffed | research/playgrain/policy/policy_offense.py (B-02) and research/build_defense_policy.py model play-callers as context-dependent, not personality labels. |
| Sports Medicine & Workload Scientist Estimates availability and performance distributions from injury, recovery, and load. | staffed | the P(play) table (playprob.py) and inj_snapshot, backfilled by the C-14 wayback injury-ladder, estimate availability from injury and workload. |
| Officials & Rules Analyst Models crew tendencies, enforcement, replay, rule changes, and legal transitions. | staffed | research/playgrain/sensors/officials_capture.py and playerweek/institute/official_gamebook_coverage.py capture crew and gamebook data. |
| Weather, Surface & Travel Scientist Connects forecast vintages and environmental exposure to play and player states. | staffed | playerweek/weather.py backfills and live-captures hourly conditions keyed to roof/dome state. |