Monday 24 Aug, 20:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
2–3✓ called — the CHE win we priced at 39% · RPS 0.251
The claim — frozen at kickoff

Fulham

35Index33Attack40Defense
LDDLL
39%CHE WIN
1–1
Most likely score

Chelsea

54Index64Attack44Defense
WLDLW
FULHAM 35%DRAW 26%CHELSEA 39%
FT 2–3 — the model called it (RPS 0.251). Graded 2026-08-25 · permanent record at /model.
Over 2.5 goals
59%
Both teams score
62%
Expected goals
1.5 · 1.6
Head to head · 12 league meetings since 2018/19
FUL 31 drawn8 CHE
2025/26FUL2–1CHE2026-01-07
2025/26CHE2–0FUL2025-08-30
2024/25FUL1–2CHE2025-04-20
2024/25CHE1–2FUL2024-12-26
2023/24CHE1–0FUL2024-01-13
Fulham — projected scorers
Rodrigo Muniz27%7% ast—
Timothy Castagne10%24% astAST
Harry Wilson11%19% ast—
Antonee Robinson11%9% ast—
Oscar Bobb6%12% ast—
Emile Smith-Rowe11%6% ast—
Chelsea — projected scorers
Enzo Fernández19%30% ast—
Cole Palmer20%12% astGOAL
João Pedro26%4% astGOAL
Malo Gusto1%24% ast—
Moisés Caicedo3%10% ast—
Liam Delap10%1% 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.