Saturday, 21/11/2026 at 13:30
Full timeManchester City 1:1 Fulham
Manchester City were the model's likeliest winner before kick-off at 59%. It finished 1–1. Both teams produced xG close to their pre-match projections.
Goals
- 16' Rodrigo Muniz Fulham · 0.15 xG chance 0–1
- 57' Elliot Anderson Manchester City · 0.03 xG chance 1–1
The model against the result
- Manchester City
- 59%
- Draw
- 25% What happened
- Fulham
- 15%
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
- 15
- 5
- On target
- 3
- 4
- Inside the box
- 12
- 4
- xG per shot
- 0.13
- 0.15
- Open play xG
- 1.44
- 0.57
- Set-piece xG
- 0.45
- 0.16
- Penalties
- —
- —
Manchester City's shots add up to 1.89 xG and Fulham's to 0.73; the published figures are 1.87 and 0.74. Leaving out penalties and own goals, Manchester City's shots come to 1.89 against a published non-penalty xG of 1.87: more than rounding can explain, so the two figures were not read at the same point of the provider's revisions. Leaving out penalties and own goals, Fulham's shots come to 0.73 against a published non-penalty xG of 0.74: 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
20 shots · 2.62 xG
Hover or tap a shot, or step through them with the arrows.
- Manchester City
- Fulham
- Filled = goal
- Dot area = xG (the smallest chances drawn at a minimum size)
Figures read 22 November, 04:01 · provisional, next reading 23 November 2026
Recent form
2.10 xG created 1.47 xGA
- W 2.82 created, 3.57 conceded against Sunderland
- W 1.28 created, 0.94 conceded against Liverpool
- W 3.53 created, 1.66 conceded against Ipswich Town
- L 1.56 created, 0.61 conceded against Aston Villa
- L 1.64 created, 1.00 conceded against Brighton & Hove Albion
- L 1.76 created, 1.06 conceded against Nottingham Forest
1.38 xG created 1.07 xGA
- D 1.62 created, 1.60 conceded against Manchester United
- L 1.81 created, 1.15 conceded against Ipswich Town
- W 1.38 created, 0.16 conceded against Hull City
- W 0.55 created, 0.51 conceded against Coventry City
- D 2.24 created, 1.83 conceded against Aston Villa
- D 0.70 created, 1.14 conceded against Newcastle United
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
7 signals flagged4 won3 lost
- Lost
- Won
- Won
- Won
- Lost
- Lost
- Won
View pre-match record Hide pre-match record
| Selection | Price | Model-implied edge | Result |
|---|---|---|---|
| Manchester City not to score | 11.00 | +42.6% | Lost |
| Manchester City at most 1 goal | 3.25 | +35.3% | Won |
| Under 2.5 goals | 3.00 | +34.0% | Won |
| Draw | 5.25 | +33.8% | Won |
| Fulham to win | 7.50 | +14.8% | Lost |
| Under 1.5 goals | 6.00 | +12.3% | Lost |
| Fulham at most 1 goal | 1.33 | +1.5% | Won |
Pre-match model vs market
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Manchester City | 59.2% | 69.4% | −10.2 pp | 1.69 |
| Draw | 25.5% | 18.0% | +7.5 pp | 3.92 |
| Fulham | 15.3% | 12.6% | +2.7 pp | 6.54 |
Other markets
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Manchester City to score | 87.0% | 91.3% | −4.2 pp | 1.15 |
| Manchester City not to score | 13.0% | 8.7% | +4.2 pp | 7.72 |
| Fulham to score | 63.9% | 64.5% | −0.6 pp | 1.56 |
| Fulham not to score | 36.1% | 35.5% | +0.6 pp | 2.77 |
| Both teams to score | 57.1% | 58.9% | −1.7 pp | 1.75 |
| Both teams not to score | 42.9% | 41.1% | +1.7 pp | 2.33 |
| Manchester City 2+ goals | 58.4% | 70.9% | −12.6 pp | 1.71 |
| Manchester City at most 1 goal | 41.6% | 29.1% | +12.6 pp | 2.40 |
| Fulham 2+ goals | 23.8% | 29.1% | −5.2 pp | 4.19 |
| Fulham at most 1 goal | 76.2% | 70.9% | +5.2 pp | 1.31 |
| Over 1.5 goals | 81.3% | 84.2% | −2.9 pp | 1.23 |
| Under 1.5 goals | 18.7% | 15.8% | +2.9 pp | 5.34 |
| Over 2.5 goals | 55.3% | 68.2% | −12.9 pp | 1.81 |
| Under 2.5 goals | 44.7% | 31.8% | +12.9 pp | 2.24 |
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 City sample
- 20 matches
- Fulham sample
- 20 matches
- Computed
- 59 minutes before kick-off
- Prices taken
- 1 hour 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.