Saturday 12 Sept, 15:00 · engine xGB Core v1 · doesn't know lineups or injuries · reassessed after this week's earlier results (rev 5)
Chelsea
61Index68Attack49Defense
WWLWD
72%CHE WIN
2–0
Likeliest CHE win · 10%
Hull City
39Index28Attack55Defense
WWLLL
CHELSEA 72%DRAW 17%HULL 11%
Over 2.5 goals
69%
Both teams score
57%
Expected goals
2.6 · 0.9
Why
- Hull City attack index 28 meets Chelsea defense index 49 — an away-side mismatch the table won't show you.
- The model makes this 72% vs 11% — a clear favorite on the numbers.
Head to head · 4 league meetings since 2014/15
CHE 40 drawn0 HUL
2016/17CHE2–0HUL2017-01-22
2016/17HUL0–2CHE2016-10-01
2014/15HUL2–3CHE2015-03-22
2014/15CHE2–0HUL2014-12-13
Chelsea — projected scorers
Hull — projected scorers
No qualified projections yet.
Projections assume recent minutes patterns — the model doesn’t know lineups.
What the grid implies
Goals
Over 1.5 goals88%
Over 2.5 goals69%
Over 3.5 goals47%
Both teams score57%
Double chance
CHE or draw89%
Draw or HUL28%
CHE or HULno draw83%
Draw no bet
CHEstake returned on a draw87%
HUL13%
Clean sheets
CHE clean sheet39%
HUL clean sheet8%
Model probabilities, not odds and not advice. Our own leaderboard shows no model here beats the closing market once the bookmaker’s margin is paid.
Every scoreline, priced — tap a cell
| CHE↓ HUL→ | 0 | 1 | 2 | 3 | 4 | 5 |
|---|---|---|---|---|---|---|
| 0 | ||||||
| 1 | ||||||
| 2 | ||||||
| 3 | ||||||
| 4 | ||||||
| 5 |
Darker green = likelier. Rows are CHE goals, columns HUL. Scores of six or more each way carry the remaining probability.
Price movement — 5 pre-kickoff assessments, every one kept
30 Aug, 20:24CHE 71.9% (+0.8 since first)draw 17.2%HUL 10.9%
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
Thin evidence: the engine has seen little recent top-flight data on Hull — this assessment leans on conservative defaults more than usual.
Engine internals are proprietary. The complete performance record — including every miss — is public on the record.