Sunday, 20/09/2026 at 17:30
Full timeFulham 1:1 Manchester United
Manchester United were the model's likeliest winner before kick-off at 37%. It finished 1–1. Both teams produced xG close to their pre-match projections.
Goals
- 63' Lisandro Martínez (o.g.) Fulham 1–0
- 89' Matheus Cunha Manchester United · 0.02 xG chance 1–1
The model against the result
- Fulham
- 34%
- Draw
- 29% What happened
- Manchester United
- 37%
Data coverage Both teams have the full 20-match model window available.
Projected vs produced
Projected before kick-off Produced on the night
The shots behind it
- Shots
- 13
- 29
- On target
- 6
- 6
- Inside the box
- 11
- 17
- xG per shot
- 0.12
- 0.05
- Open play xG
- 1.59
- 1.17
- Set-piece xG
- 0.00
- 0.42
- Penalties
- —
- —
Fulham's shots add up to 1.59 xG and Manchester United's to 1.59; the published figures are 1.62 and 1.60. Leaving out penalties and own goals, Fulham's shots come to 1.59 against a published non-penalty xG of 1.62: more than rounding can explain, so the two figures were not read at the same point of the provider's revisions. The provider computes a match's total xG and its non-penalty xG separately, so the difference between the two is not what a penalty was worth.
Shot map
Both teams shown attacking the same goal for comparison.
All shots
42 shots · 3.18 xG
Hover or tap a shot, or step through them with the arrows.
- Fulham
- Manchester United
- Filled = goal
- Dot area = xG (the smallest chances drawn at a minimum size)
Figures read 7 November, 17:04 · final
Recent form
1.59 xG created 1.54 xGA
- D 1.59 created, 1.40 conceded against Wolverhampton
- W 1.81 created, 0.31 conceded against Newcastle United
- L 1.33 created, 2.24 conceded against Chelsea
- L 0.95 created, 2.02 conceded against Sunderland
- L 3.14 created, 1.97 conceded against Crystal Palace
- D 0.70 created, 1.28 conceded against Liverpool
2.42 xG created 1.31 xGA
- 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
- L 1.00 created, 1.10 conceded against Manchester City
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
6 signals flagged3 won3 lost
- Lost
- Won
- Won
- Lost
- Lost
- Won
View pre-match record Hide pre-match record
| Selection | Price | Model-implied edge | Result |
|---|---|---|---|
| Fulham to win | 3.50 | +19.7% | Lost |
| Draw | 3.80 | +9.3% | Won |
| Manchester United at most 1 goal | 2.00 | +8.2% | Won |
| Manchester United not to score | 5.50 | +7.2% | Lost |
| Fulham 2+ goals | 2.38 | +3.8% | Lost |
| Fulham to score | 1.29 | +1.7% | Won |
Pre-match model vs market
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Fulham | 34.2% | 27.2% | +7.0 pp | 2.92 |
| Draw | 28.8% | 25.1% | +3.7 pp | 3.48 |
| Manchester United | 37.1% | 47.7% | −10.6 pp | 2.70 |
Other markets
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Fulham to score | 79.1% | 73.1% | +6.0 pp | 1.26 |
| Fulham not to score | 20.9% | 26.9% | −6.0 pp | 4.79 |
| Manchester United to score | 80.5% | 82.8% | −2.3 pp | 1.24 |
| Manchester United not to score | 19.5% | 17.2% | +2.3 pp | 5.13 |
| Both teams to score | 65.3% | 62.5% | +2.8 pp | 1.53 |
| Both teams not to score | 34.7% | 37.5% | −2.8 pp | 2.88 |
| Fulham 2+ goals | 43.7% | 39.2% | +4.5 pp | 2.29 |
| Fulham at most 1 goal | 56.3% | 60.8% | −4.5 pp | 1.78 |
| Manchester United 2+ goals | 45.9% | 53.7% | −7.8 pp | 2.18 |
| Manchester United at most 1 goal | 54.1% | 46.3% | +7.8 pp | 1.85 |
| Over 1.5 goals | 83.4% | 81.1% | +2.3 pp | 1.20 |
| Under 1.5 goals | 16.6% | 18.9% | −2.3 pp | 6.02 |
| Over 2.5 goals | 58.5% | 60.2% | −1.7 pp | 1.71 |
| Under 2.5 goals | 41.5% | 39.8% | +1.7 pp | 2.41 |
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)
- Fulham sample
- 20 matches
- Manchester United sample
- 20 matches
- Computed
- 1 day before kick-off
- Prices taken
- 1 day 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.