Today· Sep 17Pregame slateSettled· Sep 16

Regular season · week 1 · Sunday, Sep 13, 1:00 PM ET · started

Buffalo BillsatHouston TexansEXPERIMENTAL

Reliant Stadium

Buffalo BillsHouston TexansSaved on this device

Archived pregame read · published before kickoff. Everything below is the forecast revision the graded record names, read from its committed file and not regenerated. The final was BUF 36 – 31 HOU, from the Week 1 record.

Simulation story

5 chapters · the forecast as it stood before the start

Skip to the report ↓

› 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.

BUF @ HOU

Buffalo Bills at Houston Texans, 2026-09-13. This game has been played — what follows is the forecast as it was frozen BEFORE kickoff, not a current read.

Simulation

What our model expects

10,000 simulated games · model nfl-regular-season-public-v1

Projected score

BUF 23 — 25 HOU

the middle of our simulated outcomes, not a call on the exact final

Win chance

BUF 43.1% · HOU 54.0%

how often each side won in 10,000 simulations · ties 2.9%

Total points (both teams)

8 in 10 simulations landed between 31 and 65

HOU winning margin

a minus means BUF wins by that much · 8 in 10 between -15 and 20

Model details

From the replay-validated Elo-logistic head, published exactly as evaluated on a held-out 2025 season — no shrink toward 50% is applied, and no claim to beat the market is made. Generated 2026-09-13T13:48:01Z 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 game

BUF 23 — 25 HOUwin chance BUF 43.1% · HOU 54.0%total 48 (31–65)margin +2

BUF

Likely TD scorers

Josh Allen 37.5%

James Cook III 24.2%

Keon Coleman 23.1%

Passing

Josh Allen 191 pass yds (68–317)

Rushing leaders

James Cook III 48 rush yds (15–97)

Josh Allen 20 rush yds (2–55)

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

Khalil Shakir 4 rec · 40 yds · available role uncertain

Keon Coleman 2 rec · 17 yds

Dalton Kincaid 2 rec · 22 yds

HOU

Likely TD scorers

Nico Collins 29.2%

Woody Marks 24.3%

Dalton Schultz 19.8%

Passing

C.J. Stroud 129 pass yds (26–252)

Rushing leaders

Woody Marks 38 rush yds (13–78)

Jawhar Jordan 19 rush yds (2–53) · available role uncertain

New arrivals · not in these numbers

Per game at their previous club — history, not a projection.

David Montgomery 1.4 rec · 11.3 yds/g at DET

Kayshon Boutte 2.3 rec · 38.3 yds/g at NE

Mitchell Tinsley 1.4 rec · 20.4 yds/g at CIN

Receiving leaders

Nico Collins 3 rec · 38 yds

Dalton Schultz 3 rec · 24 yds

Xavier Hutchinson 2 rec · 20 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)
Buffalo Bills	11	23	35
Houston Texans	14	25	37

Comparison

Us versus the sportsbooks

two independent reads, shown side by side

Our win chance

54.0%

HOU to win

Sportsbook win chance

47.9%

HOU to win, read from 8 sportsbooks' odds with their built-in margin removed

Difference

+6.1 pp

ours minus the sportsbooks', in percentage points — not a recommendation

Total points: ours vs sportsbooks

48 vs 44.5

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 has not been shown to beat the market.

Prices captured 2026-09-13T13:48:01Z — before kickoff.

Player projections · 20 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
Khalil Shakir	BUF	role uncertain	4 (1–8)	40 (9–89)	—
Nico Collins	HOU	projected active	3 (1–7)	38 (6–91)	29.2%
Dalton Schultz	HOU	projected active	3 (1–5)	24 (1–65)	19.8%
Keon Coleman	BUF	projected active	2 (0–4)	17 (0–52)	23.1%
Dalton Kincaid	BUF	projected active	2 (0–5)	22 (0–66)	22.6%
Dawson Knox	BUF	projected active	2 (0–4)	17 (0–55)	12.3%
Xavier Hutchinson	HOU	role uncertain	2 (0–5)	20 (0–59)	—
James Cook III	BUF	projected active	1 (0–3)	9 (0–40)	24.2%
Ty Johnson	BUF	questionable	1 (0–3)	10 (0–42)	19.5%
Cade Stover	HOU	role uncertain	1 (0–3)	7 (0–36)	—
Joshua Palmer	BUF	role uncertain	1 (0–4)	11 (0–44)	—

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)
David Montgomery RB	HOU	active uncertain	DET · 17g	1.4 rec · 11.3 yds · 42.1 rush yds
Kayshon Boutte WR	HOU	active uncertain	NE · 19g	2.3 rec · 38.3 yds
Mitchell Tinsley WR	HOU	active uncertain	CIN · 10g	1.4 rec · 20.4 yds
DJ Moore WR	BUF	active uncertain	CHI · 21g	3 rec · 39.4 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 14 by TD chance · full list in the board’s TD tab

37.5% Josh Allen · BUF
29.2% Nico Collins · HOU
24.3% Woody Marks · HOU
24.2% James Cook III · BUF
23.1% Keon Coleman · BUF
22.6% Dalton Kincaid · BUF

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 v1
simulations: 10,000
input hash: 41709a5e2b6e2884
generated: 2026-09-13T13:48:01Z
kickoff: 2026-09-13T17:00Z
state: SETTLED

Player-family model provenance (3 published)

Receiving yards: props-v1 evaluation: n=3575, all promotion bars pass
Receptions: props-v1 evaluation: n=3575, all promotion bars pass
Anytime touchdown: anytime-td-v1 calibration: held-out 2025 n=3965, beats both baselines; DNP settles void, so probabilities condition on playing

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.