Saturday 19 Sept, 17:30 · engine xGB Core v1 · doesn't know lineups or injuries · reassessed after this week's earlier results (rev 3)

Nottingham Forest

40Index38Attack46Defense
DDLDL
38%NOT WIN
10
Likeliest NOT win · 10%

Coventry City

46Index32Attack63Defense
LLL
FOREST 38%DRAW 30%COVENTRY 31%
Over 2.5 goals
44%
Both teams score
51%
Expected goals
1.3 · 1.1
Why
Forest — projected scorers
Morgan Gibbs-White32%21% ast90'
Igor Jesus28%7% ast77'
James McAtee3%18% ast54'
Neco Williams6%9% ast90'
Dan Ndoye5%9% ast39'
Chris Wood10%2% ast36'
Coventry — projected scorers
Jack Rudoni27%13% ast52'
Taiwo Awoniyi32%3% ast60'
Bobby Thomas5%28% ast87'
Loum Tchaouna4%10% ast57'
Ellis Simms11%1% ast30'
Milan van Ewijk0%7% ast90'

Projections assume recent minutes patterns — the model doesn’t know lineups.

What the grid implies
Goals
Over 1.5 goals71%
Over 2.5 goals44%
Over 3.5 goals23%
Both teams score51%
Double chance
NOT or draw69%
Draw or COV62%
NOT or COVno draw70%
Draw no bet
NOTstake returned on a draw55%
COV45%
Clean sheets
NOT clean sheet32%
COV clean sheet28%

Model probabilities, not odds and not advice. Our own leaderboard shows no model here beats the closing market once the bookmaker’s margin is paid.

Every scoreline, priced — tap a cell
NOTCOV012345
0
1
2
3
4
5
Darker green = likelier. Rows are NOT goals, columns COV. Scores of six or more each way carry the remaining probability.
Price movement — 3 pre-kickoff assessments, every one kept
5 Sept, 20:11NOT 38.2% (−22.3 since first)draw 30.4%COV 31.4%
What this is built from
The engine weighs
  • Chance quality created and conceded, both sides, all season
  • Opponent strength and venue
  • Recent play, weighted toward now
It cannot see
  • Confirmed lineups
  • Injuries and suspensions
  • Cup rotation plans

Engine internals are proprietary. The complete performance record — including every miss — is public on the record.