xgEdge

Saturday, 19/09/2026 at 18:00

Full time
Match report · Serie A

Roma 2:2 Inter

Roma Home 1.66 xG · 18 shots
Inter Away 2.86 xG · 16 shots
22 Inter had the better chances, but it finished level

Roma were the model's likeliest winner before kick-off at 42%. It finished 2–2. The biggest difference was Inter's attack: 2.86 xG against 1.27 projected (+1.59).

Goals

  1. 6' Manu Koné Roma · 0.16 xG chance 1–0
  2. 37' Manu Koné Roma · 0.26 xG chance 2–0
  3. 46' Lautaro Martínez Inter · 0.13 xG chance 2–1
  4. 79' Lautaro Martínez Inter · 0.36 xG chance 2–2

The model against the result

priced before kick-off
Roma
42%
Draw
29% What happened
Inter
29%

Data coverage Both teams have the full 20-match model window available.

Projected vs produced

Expected goals
Roma The model projected 1.54 Produced 1.66 Difference +0.12
Inter The model projected 1.27 Produced 2.86 Difference +1.59

Inter produced 1.59 xG more than projected

Projected before kick-off Produced on the night

The shots behind it

Roma Inter
Shots
18
16
On target
4
5
Inside the box
12
11
xG per shot
0.09
0.19
Open play xG
1.42
1.15
Set-piece xG
0.26
1.93
Penalties
—
—

Roma's shots add up to 1.68 xG and Inter's to 3.09; the published figures are 1.66 and 2.86. Leaving out penalties and own goals, Roma's shots come to 1.68 against a published non-penalty xG of 1.66: 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, Inter's shots come to 3.09 against a published non-penalty xG of 3.07: 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.

Inter · Lautaro Martínez · 29' · No goal · 4 m · 0.61 xG Inter · Lautaro Martínez · 79' · No goal · 2 m · 0.54 xG Inter · Manuel Akanji · 79' · No goal · 4 m · 0.38 xG Roma · Gianluca Mancini · 37' · No goal · 7 m · 0.37 xG Inter · Lautaro Martínez · 79' · Goal · 9 m · 0.36 xG Inter · Marcus Thuram · 79' · No goal · 5 m · 0.33 xG Inter · Yann Bisseck · 26' · No goal · 11 m · 0.26 xG Roma · Manu Koné · 37' · Goal · 3 m · 0.26 xG Roma · Donyell Malen · 25' · No goal · 11 m · 0.16 xG Roma · Manu Koné · 6' · Goal · 10 m · 0.16 xG Roma · Donyell Malen · 68' · No goal · 5 m · 0.15 xG Inter · Alessandro Bastoni · 33' · No goal · 4 m · 0.15 xG Inter · Lautaro Martínez · 46' · Goal · 14 m · 0.13 xG Roma · Niccolò Pisilli · 61' · No goal · 18 m · 0.10 xG Roma · Bryan Cristante · 68' · No goal · 8 m · 0.09 xG Roma · Donyell Malen · 53' · No goal · 13 m · 0.07 xG Inter · Yann Bisseck · 79' · No goal · 10 m · 0.07 xG Inter · Marcus Thuram · 59' · No goal · 10 m · 0.07 xG Roma · Paulo Dybala · 18' · No goal · 15 m · 0.06 xG Roma · Paulo Dybala · 13' · No goal · 14 m · 0.06 xG Roma · Paulo Dybala · 62' · No goal · 23 m · 0.04 xG Inter · Lautaro Martínez · 52' · No goal · 20 m · 0.04 xG Roma · Wesley · 34' · No goal · 13 m · 0.04 xG Inter · Andy Diouf · 70' · No goal · 27 m · 0.04 xG Inter · Lautaro Martínez · 78' · No goal · 14 m · 0.04 xG Inter · Marcus Thuram · 88' · No goal · 26 m · 0.03 xG Inter · Luís Henrique · 70' · No goal · 19 m · 0.03 xG Roma · Matías Soulé · 37' · No goal · 9 m · 0.03 xG Inter · Piotr Zieliński · 62' · No goal · 28 m · 0.03 xG Roma · Matías Soulé · 41' · No goal · 38 m · 0.02 xG Roma · Wesley · 67' · No goal · 4 m · 0.02 xG Roma · Paulo Dybala · 20' · No goal · 27 m · 0.02 xG Roma · Bryan Cristante · 12' · No goal · 24 m · 0.02 xG Roma · Nahuel Molina · 54' · No goal · 22 m · 0.01 xG

All shots

34 shots · 4.77 xG

Hover or tap a shot, or step through them with the arrows.

  • Roma
  • Inter
  • Filled = goal
  • Dot area = xG (the smallest chances drawn at a minimum size)

Figures read 7 November, 17:08 · final

Recent form

Last 6 · xG per match
Roma

2.62 xG created 0.71 xGA

  • W 1.19 created, 0.69 conceded against Lazio
  • W 3.39 created, 0.84 conceded against Hellas Verona
  • W 3.07 created, 0.35 conceded against Fiorentina
  • W 3.27 created, 0.80 conceded against Lecce
  • W 2.97 created, 0.70 conceded against Atalanta
  • W 1.85 created, 0.86 conceded against Torino
Inter

2.66 xG created 1.28 xGA

  • D 2.56 created, 1.19 conceded against Hellas Verona
  • D 1.78 created, 1.40 conceded against Bologna
  • W 1.05 created, 1.23 conceded against Monza
  • W 3.67 created, 0.48 conceded against Cagliari
  • W 3.86 created, 2.43 conceded against Napoli
  • W 3.05 created, 0.92 conceded against Udinese

xG created xG conceded (xGA) W / D / L: the match result

Head to head

Roma: 0 won · 0 drawn · 2 lost

Pre-match model & market record

3 signals flagged0 won3 lost

  • Lost
  • Lost
  • Lost
View pre-match record
The outcomes the model flagged on Roma against Inter before kick-off, in the order they ranked, with the price, the model-implied edge and what became of each.
Selection Price Model-implied edge Result
Roma to win 2.70 +12.8% Lost
Inter at most 1 goal 1.73 +8.5% Lost
Inter not to score 4.33 +8.4% Lost

Pre-match model vs market

Outcome Model Market Disagreement Model price
Roma 41.8% 35.0% +6.8 pp 2.39
Draw 29.4% 28.6% +0.8 pp 3.40
Inter 28.8% 36.4% −7.5 pp 3.47

Other markets

Outcome Model Market Disagreement Model price
Roma to score 81.2% 76.6% +4.6 pp 1.23
Roma not to score 18.8% 23.4% −4.6 pp 5.33
Inter to score 75.0% 78.3% −3.3 pp 1.33
Inter not to score 25.0% 21.7% +3.3 pp 4.00
Both teams to score 62.6% 62.5% +0.1 pp 1.60
Both teams not to score 37.4% 37.5% −0.1 pp 2.67
Roma 2+ goals 47.1% 44.3% +2.8 pp 2.12
Roma at most 1 goal 52.9% 55.7% −2.8 pp 1.89
Inter 2+ goals 37.1% 46.3% −9.2 pp 2.69
Inter at most 1 goal 62.9% 53.7% +9.2 pp 1.59
Over 1.5 goals 81.3% 78.9% +2.4 pp 1.23
Under 1.5 goals 18.7% 21.1% −2.4 pp 5.36
Over 2.5 goals 55.0% 56.9% −1.9 pp 1.82
Under 2.5 goals 45.0% 43.1% +1.9 pp 2.22

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
Fit window
the last 20 matches, recency weighted (a match 107 days old counts half)
Roma sample
20 matches
Inter sample
20 matches
Computed
9 hours before kick-off
Prices taken
9 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.