Saturday 12 Sept, 15:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
2–3✗ missed — the IPS win we priced at 14% · RPS 0.589
The claim — frozen at kickoff

Crystal Palace

39Index53Attack27Defense
WDLWL
67%CRY WIN
2–1
Most likely score

Ipswich Town

14Index25Attack8Defense
WLWLL
CRYSTAL PALACE 67%DRAW 19%IPSWICH 14%
FT 2–3 — the model missed (RPS 0.589). Graded 2026-09-12 · permanent record at /model.
Over 2.5 goals
72%
Both teams score
64%
Expected goals
2.6 · 1.2
Head to head · 2 league meetings since 2024/25
CRY 20 drawn0 IPS
2024/25CRY1–0IPS2025-03-08
2024/25IPS0–1CRY2024-12-03
Crystal Palace — projected scorers
Adam Wharton3%48% ast—
Daichi Kamada5%41% astAST
Tyrick Mitchell25%24% ast—
Eddie Nketiah13%23% ast—
Jean-Philippe Mateta25%1% ast—
Ismaila Sarr22%4% ast—
Ipswich — projected scorers
Julio Enciso26%26% ast—
Abdul Fatawu1%36% ast—
Emersonn19%17% astGOAL
Leif Davis19%8% astGOAL
Daizen Maeda21%0% ast—
Sasa Lukic1%3% ast—

These are the projections exactly as published before kickoff — never edited after the fact.

What this is built from
The engine weighs
  • Chance quality created and conceded, both sides, all season
  • Opponent strength and venue
  • Recent play, weighted toward now
It cannot see
  • Confirmed lineups
  • Injuries and suspensions
  • Cup rotation plans

Engine internals are proprietary. The complete performance record — including every miss — is public on the record.