DET @ BUF
Detroit Lions at Buffalo Bills at Highmark Stadium.
Regular season · week 2 · Thursday, Sep 17, 8:15 PM ET
Detroit Lionsat
Buffalo BillsEXPERIMENTAL
Highmark Stadium
70°F · 5 mph wind from the N · 7% chance of rain · mostly cloudy — not used by the model; no weather term enters the numbers below.
Simulation story
5 chapters · read from the published artifact› Loading the matchup model› Reading the outcome distribution from 10,000 simulated games› Preparing the score scenariosPress Play to step through what the model expects, chapter by chapter, or read the report below.
Simulation
What our model expects
10,000 simulated games · model nfl-regular-season-public-v1
Projected score
DET 25 — 29 BUF
the middle of our simulated outcomes, not a call on the exact final
Win chance
DET 34.9% · BUF 62.4%
how often each side won in 10,000 simulations · ties 2.8%
Total points (both teams)
54
8 in 10 simulations landed between 37 and 71
BUF winning margin
+4
a minus means DET wins by that much · 8 in 10 between -13 and 20
Model details
From the margin-of-victory Elo win head, published exactly as evaluated on held-out 2006–2021 — no shrink toward 50% is applied, and no claim to out-predict the sportsbook market is made. Generated 2026-09-17T14:17:00Z under model nfl-regular-season-public-v1 and frozen pre-kickoff; every forecast is settled against the official result.
Projected scorecard
expected statistical summaries · not one simulated gameDET 25 — 29 BUFwin chance DET 34.9% · BUF 62.4%total 54 (37–71)margin +4
DET
Likely TD scorers
Jahmyr Gibbs 70.3% · available role uncertain
Amon-Ra St. Brown 51.1% · available role uncertain
Jameson Williams 29.8% · available role uncertain
Passing
Jared Goff 227 pass yds (128–368) · available role uncertain
Rushing leaders
Jahmyr Gibbs 81 rush yds (26–185) · available role uncertain
Justin Jackson 4 rush yds (0–35) · available role uncertain
New arrivals · not in these numbers
Per game at their previous club — history, not a projection.
Isiah Pacheco 1.3 rec · 7.7 yds/g at KC
Receiving leaders
Amon-Ra St. Brown 7 rec · 76 yds · available role uncertain
Jameson Williams 4 rec · 49 yds · available role uncertain
Sam LaPorta 4 rec · 44 yds · available role uncertain
BUF
Likely TD scorers
James Cook 52.5% · available role uncertain
DJ Moore 44.2% · available role uncertain
Josh Allen 41.2% · available role uncertain
Passing
Josh Allen 239 pass yds (131–396) · available role uncertain
Rushing leaders
James Cook 61 rush yds (18–150) · available role uncertain
Josh Allen 22 rush yds (3–76) · available role uncertain
New arrivals · not in these numbers
Per game at their previous club — history, not a projection.
DJ Moore 3 rec · 39.4 yds/g at CHI
Receiving leaders
DJ Moore 5 rec · 66 yds · available role uncertain
Khalil Shakir 5 rec · 49 yds · available role uncertain
Dalton Kincaid 4 rec · 47 yds · available role uncertain
pass interceptions · First/last/2+ touchdown — withheld, with the exact bar each failed
- pass interceptions: RESEARCH_ONLY
- First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities
Range
How wide the outcomes are
the 10th to 90th percentile of each team's simulated score
| Team | Low (10th) | Projected | High (90th) |
|---|---|---|---|
| Detroit Lions | 13 | 25 | 37 |
| Buffalo Bills | 17 | 29 | 41 |
Exact score
The likeliest final scores
from an event-based simulation of touchdowns and field goals, solved onto the median margin and total above
| Score (DET – BUF) | Chance |
|---|---|
| 27–30 | 0.70% |
| 24–27 | 0.58% |
| 20–23 | 0.56% |
| 27–24 | 0.53% |
| 30–27 | 0.53% |
| 23–20 | 0.50% |
No single scoreline is likely — these are the most common of hundreds. The projected score above is derived from the medians and answers a different question: the middle of the distribution, not its most common point.
Key numbers
How often it lands on 3, 7, 10 or 14
football's margins pile up on those four — this is the one thing a normal-draw model cannot show you
| Margin | This game | Last 3 regular seasons |
|---|---|---|
| Decided by exactly 3 | 9.5% | 14.2% |
| Decided by exactly 7 | 5.7% | 8.3% |
| Decided by exactly 10 | 5.5% | 4.2% |
| Decided by exactly 14 | 4.5% | 4.4% |
| Any of the four | 25.2% | 31.1% |
The right-hand column is what actually happened across 816 regular-season games (2023, 2024, 2025) — the same finals this engine was fitted to. It gets the shape right, with 3 the most common margin by a distance, and it is not calibrated to the number: it puts less weight on 3 and more on 10 than those seasons did.
DET touchdowns
2.8
BUF touchdowns
3.1
DET field goals
1.9
BUF field goals
2.1
Tied after regulation
3.3%
Comparison
Us versus the sportsbooks
two independent reads, shown side by side
Our win chance
62.4%
BUF to win
Sportsbook win chance
67.4%
BUF to win, read from 6 sportsbooks' odds with their built-in margin removed
Difference
-5 pp
ours minus the sportsbooks', in percentage points — not a recommendation
Total points: ours vs sportsbooks
54 vs 55
our projected total against the sportsbooks' over/under line
The sportsbook numbers are the books' own, shown for context. A difference is a difference — this model is not validated to out-predict the sportsbook market.
Prices captured 2026-09-17T14:17:00Z — before kickoff.
Player projections · 17 modelled
The player board
Every modelled player, with his availability. Players listed out carry no volume projection.
Every receiving family for one player on one row, ranked by expected receptions.
| Player | Team | Availability | Receptions (10th–90th) | Rec yards (10th–90th) | TD chance |
|---|---|---|---|---|---|
| Amon-Ra St. Brown | DET | role uncertain | 7 (3–14) | 76 (35–140) | 51.1% |
| DJ Moore | BUF | role uncertain | 5 (2–11) | 66 (27–133) | 44.2% |
| Khalil Shakir | BUF | role uncertain | 5 (1–10) | 49 (18–101) | 28.5% |
| Jameson Williams | DET | role uncertain | 4 (1–8) | 49 (17–105) | 29.8% |
| Sam LaPorta | DET | role uncertain | 4 (1–9) | 44 (15–94) | 27.5% |
| Dalton Kincaid | BUF | role uncertain | 4 (1–8) | 47 (14–105) | 26.3% |
| Jahmyr Gibbs | DET | role uncertain | 3 (1–7) | 32 (9–72) | 70.3% |
| James Cook | BUF | role uncertain | 2 (0–5) | 19 (0–53) | 52.5% |
| Ty Johnson | BUF | questionable | 2 (0–4) | 15 (0–47) | 25.1% |
| Dawson Knox | BUF | role uncertain | 2 (0–4) | 15 (0–47) | 13.3% |
| Josh Palmer | BUF | role uncertain | 1 (0–4) | 15 (0–49) | 14.7% |
| Keon Coleman | BUF | role uncertain | 1 (0–4) | 13 (0–42) | 12.6% |
| Brock Wright | DET | role uncertain | 1 (0–3) | 8 (0–34) | 8.9% |
New arrivals · not in the simulated numbers above
Per game at their previous team — history, not a projection.
| Player | Team | Availability | Last club | Per game (prior club) |
|---|---|---|---|---|
| DJ Moore WR | BUF | active uncertain | CHI · 21g | 3 rec · 39.4 yds |
| Isiah Pacheco RB | DET | out | KC · 16g | 1.3 rec · 7.7 yds · 30.7 rush yds |
Families not shown, and the exact bar each failed (2)
- pass interceptions: RESEARCH_ONLY
- First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities
Scoring outlooktop 6 of 17 by TD chance · full list in the board’s TD tab
- 70.3% Jahmyr Gibbs · DET · available role uncertain
- 52.5% James Cook · BUF · available role uncertain
- 51.1% Amon-Ra St. Brown · DET · available role uncertain
- 44.2% DJ Moore · BUF · available role uncertain
- 41.2% Josh Allen · BUF · available role uncertain
- 29.8% Jameson Williams · DET · available role uncertain
Anytime-scorer probability means scoring a touchdown — never throwing one. Void if the player does not play; questionable players carry their state above.
Reading key
What these numbers mean
- Projected score
- The middle outcome across every simulated game — not a prediction of the exact final.
- Win chance
- How often each side won across the simulations, after the calibration described above.
- 80% range
- Eight in ten simulated games landed inside this band. Real games land outside it too.
- pp (percentage points)
- The plain difference between two percentages. A gap is a difference, not an advantage.
- Experimental
- Published while its out-of-sample record is still accumulating. Every forecast is frozen before kickoff and graded against the official result.
Provenance
Where this came from
- model
- nfl-regular-season-public-v1 v2
- simulations
- 10,000
- input hash
- 5657b1e45746b99c
- generated
- 2026-09-17T14:17:00Z
- kickoff
- 2026-09-18T00:15Z
- state
- UPCOMING
Player-family model provenance (4 published)
- Rushing yards: Share-level model: cleared every bar when re-tested on 2014–2021 (14,502 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
- Receiving yards: Share-level model: cleared every bar when re-tested on 2014–2021 (27,134 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
- Receptions: Share-level model: cleared every bar when re-tested on 2014–2021 (27,134 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
- Anytime touchdown: Opportunity touchdown model: cleared every bar on a blind test of 2014–2021 (35,128 player-games never used to build it). Probabilities condition on playing — a player who does not play settles void. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
Our win chances come from a team rating that weights how decisively teams win. Tested on 4,281 past games it had never seen (2006–2021), it scored 0.629 on log loss (lower is better) — better than our previous rating's 0.642 and a coin flip's 0.693, but short of the sportsbooks' own odds at 0.610. It has NOT been shown to beat the sportsbook market. Where our win and margin ratings disagree on the favourite, the previous rating is used for that game. The 2026 season evaluation still runs under bars frozen in August, so every forecast stays experimental.
Educational and paper-only — not betting advice.
More
Other games with a simulation
- CAR @ ATLSunday, Sep 20, 1:00 PM ET
- MIN @ CHISunday, Sep 20, 1:00 PM ET
- PHI @ TENSunday, Sep 20, 1:00 PM ET
- PIT @ NESunday, Sep 20, 1:00 PM ET
- GB @ NYJSunday, Sep 20, 1:00 PM ET
- CLE @ TBSunday, Sep 20, 1:00 PM ET
- NO @ BALSunday, Sep 20, 1:00 PM ET
- CIN @ HOUSunday, Sep 20, 1:00 PM ET
- JAX @ DENSunday, Sep 20, 4:05 PM ET
- LV @ LACSunday, Sep 20, 4:05 PM ET
- WSH @ DALSunday, Sep 20, 4:25 PM ET
- SEA @ ARISunday, Sep 20, 4:25 PM ET
- MIA @ SFSunday, Sep 20, 4:25 PM ET
- IND @ KCSunday, Sep 20, 8:20 PM ET
- NYG @ LARMonday, Sep 21, 8:15 PM ET