← KICK90 board
Serie AT-7dlineups pending

Roma vs Inter

Saturday 19 Sep, 16:00 UTC · Stadio Olimpico

Referee not appointedWeather pending
Most probable outcome
ROMA WIN

Outcome distribution

Calibrated 1X2 probabilities

40.7%
Roma
26.2%
Draw
33.1%
Inter
Home xG
1.73
Away xG
1.63
Likely score
1–1
10.1%
Completeness
76.3%
input coverage

Why the model says this

Ranked contributing factors

  • Roma attacking output+32

    1.69 xG and 1.69 goals per match over the last 23.

  • Inter defensive record-13

    1.12 xG and 1.12 goals conceded per match.

  • Roma home record+53

    20.4 scored / 8.8 conceded across 11 home matches.

  • Inter away record-38

    18.3 scored / 10.8 conceded across 10 away matches.

  • Squad availability-5

    Roma: Evan Ndicka (out), Devyne Rensch  (out), Leonardo Balerdi  (out) · Inter: Djed Spence (out)

  • Squad depth-1

    Roma: 27 registered, 0 regular starters, fit cover 4GK/9DEF/6MID/4FWD, 0% of squad minutes unavailable · Inter: 25 registered, 0 regular starters, fit cover 3GK/7DEF/10MID/4FWD, 0% of squad minutes unavailable

  • Recent transfer activity-32

    Roma: 15 in (0 on loan), 23 out including 0 regulars — Robinio Vaz to Hull City, Mattia Mannini to Benevento, Neil El Aynaoui to RB Leipzig · Inter: 5 in (0 on loan), 13 out including 0 regulars — Kristjan Asllani to Al Jazira, Ebenezer Akinsanmiro to Monza, Yann Sommer to Club Brugge

  • Roma last 6 played+100

    D W W W W — 2.66 scored / 0.55 conceded per match, 2.41 points per game (recency weighted).

  • Inter last 5 played-53

    L W W W W — 2.29 scored / 1.22 conceded per match, 2.25 points per game (recency weighted).

  • Model agreementneutral

    Elo 35% · form 36% · goal model 40% · results history 56% for the home win.

  • Expected attacking output+3

    Goal-expectancy model: Roma 1.73 xG, Inter 1.63 xG.

Most likely outcomes

Ranked by model probability · confidence is per outcome, from the raw sample behind it

Betting parameters

Full-time 1X2 and derived result combinations.

Probabilities are model estimates from the same score distribution as the 1X2 line. KICK90 publishes likelihoods, not tips.

Team comparison

Last-10 window

MetricRomaInter
Elo16481706
Record15W 2D 6L15W 5D 2L
Goals for / against38.77394719357762 / 21.81877617556756751.06422495576021 / 25.83243176115866
xG for / againstDATA UNAVAILABLEDATA UNAVAILABLE
Possession55%60%
Rest daysDATA UNAVAILABLEDATA UNAVAILABLE
Venue split11 matches, 20.441914793761793–8.78127601303936710 matches, 18.290454593435342–10.779602569766261

AI briefing

The model explains the numbers — it does not produce them

Generate a written analyst briefing that separates verified data from interpretation.

Confidence

Separation · completeness · model agreement

46Low

Confidence reflects how strongly the evidence points one way — not how attractive the outcome is. It rises as lineups confirm and data completeness improves.

Probability evolution

How the answer moved toward kickoff

  • T-7dcompleteness 76.3%
    40.7% / 26.2% / 33.1%

Squad availability

Weighted by importance and output

Roma
  • Evan Ndicka Defenderout
  • Devyne Rensch  Defenderout
  • Leonardo Balerdi  Defenderout
Inter
  • Djed Spence Defenderout

Availability impact: 4.2% home attack, 1.4% away attack.