Sunday, 13/09/2026 at 17:30
Full timeManchester United 0:1 Manchester City
Manchester United were the model's likeliest winner before kick-off at 40%. Manchester City won 1–0. The biggest difference was Manchester United's attack: 1.00 xG against 1.60 projected (−0.60). Manchester City produced 1.10 xG against 1.44 projected (−0.34).
Goals
- 60' Erling Haaland Manchester City · 0.46 xG chance 0–1
The model against the result
- Manchester United
- 40%
- Draw
- 28%
- Manchester City
- 32% What happened
Data coverage Both teams have the full 20-match model window available.
Projected vs produced
Manchester United produced 0.60 xG less than projected
Projected before kick-off Produced on the night
The shots behind it
- Shots
- 16
- 6
- On target
- 3
- 2
- Inside the box
- 6
- 2
- xG per shot
- 0.06
- 0.18
- Open play xG
- 0.80
- 0.65
- Set-piece xG
- 0.20
- 0.46
- Penalties
- —
- —
Shot map
Both teams shown attacking the same goal for comparison.
All shots
22 shots · 2.11 xG
Hover or tap a shot, or step through them with the arrows.
- Manchester United
- Manchester City
- Filled = goal
- Dot area = xG (the smallest chances drawn at a minimum size)
Figures read 7 November, 17:04 · final
Recent form
2.36 xG created 1.33 xGA
- D 0.62 created, 1.25 conceded against Sunderland
- W 4.57 created, 1.88 conceded against Nottingham Forest
- W 1.66 created, 0.79 conceded against Brighton & Hove Albion
- L 1.83 created, 1.01 conceded against Hull City
- W 4.77 created, 2.06 conceded against Ipswich Town
- D 0.69 created, 1.01 conceded against Everton
1.84 xG created 1.24 xGA
- W 1.66 created, 0.73 conceded against Crystal Palace
- D 1.48 created, 2.25 conceded against Bournemouth
- L 1.34 created, 1.77 conceded against Aston Villa
- W 2.25 created, 0.65 conceded against Bournemouth
- W 2.21 created, 0.66 conceded against Crystal Palace
- W 2.12 created, 1.37 conceded against Coventry City
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
6 signals flagged1 won5 lost
- Lost
- Lost
- Won
- Lost
- Lost
- Lost
View pre-match record Hide pre-match record
| Selection | Price | Model-implied edge | Result |
|---|---|---|---|
| Manchester United to win | 3.10 | +22.7% | Lost |
| Manchester City not to score | 5.50 | +16.0% | Lost |
| Manchester City at most 1 goal | 2.00 | +13.2% | Won |
| Draw | 3.75 | +5.6% | Lost |
| Manchester United 2+ goals | 2.10 | +2.8% | Lost |
| Manchester United to score | 1.22 | +0.5% | Lost |
Pre-match model vs market
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Manchester United | 39.6% | 30.9% | +8.7 pp | 2.53 |
| Draw | 28.2% | 25.5% | +2.6 pp | 3.55 |
| Manchester City | 32.3% | 43.5% | −11.3 pp | 3.10 |
Other markets
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Manchester United to score | 82.2% | 76.6% | +5.6 pp | 1.22 |
| Manchester United not to score | 17.8% | 23.4% | −5.6 pp | 5.62 |
| Manchester City to score | 78.9% | 82.8% | −3.9 pp | 1.27 |
| Manchester City not to score | 21.1% | 17.2% | +3.9 pp | 4.74 |
| Both teams to score | 66.4% | 64.5% | +1.9 pp | 1.51 |
| Both teams not to score | 33.6% | 35.5% | −1.9 pp | 2.98 |
| Manchester United 2+ goals | 48.9% | 44.3% | +4.7 pp | 2.04 |
| Manchester United at most 1 goal | 51.1% | 55.7% | −4.7 pp | 1.96 |
| Manchester City 2+ goals | 43.4% | 53.7% | −10.3 pp | 2.31 |
| Manchester City at most 1 goal | 56.6% | 46.3% | +10.3 pp | 1.77 |
| Over 1.5 goals | 84.4% | 81.1% | +3.4 pp | 1.18 |
| Under 1.5 goals | 15.6% | 18.9% | −3.4 pp | 6.43 |
| Over 2.5 goals | 60.3% | 62.0% | −1.6 pp | 1.66 |
| Under 2.5 goals | 39.7% | 38.0% | +1.6 pp | 2.52 |
Prices and probabilities are the ones stored before kick-off; nothing here is recalculated. The model-implied edge is the model's probability times the price, minus one: what a stake of one would return on average if the model is right, not observed return, so a flagged outcome that lost is the ordinary case rather than a contradiction.
Model details
Show Hide
- Fit window
- the last 20 matches, recency weighted (a match 107 days old counts half)
- Manchester United sample
- 20 matches
- Manchester City sample
- 20 matches
- Computed
- 7 hours before kick-off
- Prices taken
- 7 hours before kick-off
Limitations
The model reads expected goals and nothing else. It does not know the lineups, who is injured or suspended, what either side has to play for, the weather, or how congested the schedule around this match is.