Manchester City v Hull — Prediction, Odds & Stats
Saturday 19 December 2026 · ENG-Premier League · 2627
Premier League
xG Prediction generated
AI prediction
ai-blend v1.0 dailyRaw model output; no calibration record for this fixture's bands yet.
Top 5 scorelines
- 2-0 12.3%
- 1-0 11.5%
- 2-1 9.6%
- 1-1 9.0%
- 3-0 8.8%
Goals
| Over 2.5 | 56.0% | Under 2.5 | 44.0% |
| BTTS yes | 48.0% | BTTS no | 52.0% |
| Manchester City 1+ | 88.3% | Manchester City 2+ | 63.1% |
| Hull 1+ | 54.3% | Hull 2+ | 18.5% |
Expected goals 2.14 – 0.78. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Manchester City carry the stronger rating, 1874 Elo against 1527.
- Form is good: 3.00 points a match from the last five.
- At home Manchester City average 2.54 xG a match.
Risk factors
- Hull have only 7 matches on record.
Why the model thinks this
The price
Manchester City have an estimated 68.6% win probability, against 18.9% for the draw and 12.4% for Hull. Expected goals from the ensemble are 2.14 for Manchester City and 0.78 for Hull.
Why Manchester City
Manchester City carry the stronger rating, 1874 Elo against 1527. Form is good: 3.00 points a match from the last five. At home Manchester City average 2.54 xG a match.
Why the draw is live
The draw sits at 18.9%. Draws run at 25% in this competition.
Why Hull can win
Away from home Hull average 0.89 xG a match. Their last eleven was closer to full strength: Manchester City were missing 1.05 expected goal involvements a match against 0.33.
Key players
Manchester City's leading contributors by expected goal involvements a match: Erling Haaland (0.87), Mathis Cherki (0.41), Phil Foden (0.38). Hull's leading contributors by expected goal involvements a match: Oliver McBurnie (0.35), Mohamed Belloumi (0.20), Sorba Thomas (0.19).
Availability
1 of Manchester City's top three contributors did not start their last match.
The matchup, as far as the data reaches
Manchester City: 60% possession, 15.2 shots a match, 11.8 faced, 0.30 xG a match from set pieces. Hull: 32% possession, 11.8 shots a match, 14.0 faced, 0.18 xG a match from set pieces.
Inputs last refreshed: matches 2026-10-21 11:56 · team_stats 2026-10-20 06:04 · availability 2026-10-21 15:05 · prediction 2026-09-18 10:37 ·
Manchester City are the model's most likely outcome at 68.6%. The likeliest scoreline is 2-0 at 12.3%. Confidence 79/100, data quality 70/100. These are probabilities, not certainties: the less likely outcome happens as often as its number says.
Written from the numbers the model saw, not by a language model; nothing here is a statistic the snapshot does not hold. How predictions work.
Was this pick made in advance?
-oos is out of sample: it was fitted only on matches
played before this one, so its pick is a genuine forecast rather than hindsight.
Anything without that suffix was fitted on all available data.What the chances say
Manchester City are finishing above their chances — 2.8 goals more than expected across 10 matches, which usually cools off. They are also conceding fewer than expected — 3.9 goals saved beyond what the chances suggest.
Hull are conceding sharply fewer than expected — 5.3 goals saved beyond what the chances suggest.
Finishing swings far more than chance creation, so a gap this size usually narrows. Over ten matches it is suggestive, not settled — a genuinely elite finisher beats expected goals for years.
What the model said
| Model | Home / Draw / Away | Expected goals | Likeliest score | O2.5 | BTTS |
|---|---|---|---|---|---|
| ai-blend | 2.14–0.78 | 0% | 0% | 0% | |
| dc-goals | 1.14–0.84 | 0-0 15% | 32% | 40% | |
| dc-xg | 2.50–0.79 | 2-0 12% | 64% | 50% |
A model whose name ends -oos was produced by the walk-forward backtest:
it was fitted only on matches played before this one, so the pick is genuinely out of sample.