Gameweek 10 Verdict — FootyPulse

Premier League · Gameweek 10 Verdict

Gameweek 10 Verdict: 5 of 10 correct as Forest shock City

Published 9 November 2026 · FootyPulse AI Analysis

The model went 5 for 10 in Gameweek 10, a return to mid-table form after recent struggles. Season accuracy now sits at 46% — 45 correct calls from 97 fixtures — as cup ties and upset results tested the algorithm's assumptions.

The scoreboard

Five correct predictions from ten fixtures leaves the AI with a 50% hit rate for Gameweek 10. Season accuracy stands at 46% — 45 correct from 97 total matches across all competitions.

Biggest upset

Nottingham Forest 3-1 Manchester City delivered the round's most painful miss. The model backed City with 58% confidence, only to watch Forest dismantle the champions at the City Ground. A 58-point probability swing represents the largest gap between expectation and reality this gameweek.

Win probability — Nottingham Forest 18%, Draw 24%, Manchester City 58%

Best correct call

Fulham 1-1 Newcastle United was the model's least confident correct prediction, called as a draw with just 38% probability. Threading that needle — correctly identifying a stalemate when the data suggested modest home or away edges — demonstrates the value of probabilistic thinking over forced certainty.

Win probability — Fulham 32%, Draw 38%, Newcastle United 30%

Every fixture

  • Everton 3-1 Coventry City — Predicted home win (58%). ✅ Correct.
  • Leeds United 1-0 Tottenham Hotspur — Predicted away win (42%). ❌ Wrong.
  • Fulham 1-1 Newcastle United — Predicted draw (38%). ✅ Correct.
  • Arsenal 1-0 Hull City — Predicted home win (74%). ✅ Correct.
  • Nottingham Forest 3-1 Manchester City — Predicted away win (58%). ❌ Wrong.
  • Brighton & Hove Albion 2-0 Brentford — Predicted home win (68%). ✅ Correct.
  • Crystal Palace 1-3 Liverpool — Predicted away win (60%). ✅ Correct.
  • Ipswich Town 1-2 Bournemouth — Predicted home win (42%). ❌ Wrong.
  • Sunderland 1-0 Chelsea — Predicted away win (55%). ❌ Wrong.
  • Manchester United 4-4 Aston Villa — Predicted away win (41%). ❌ Wrong.

Five wrong calls tell their own story: cup ties involving lower-league sides (Coventry, Hull, Sunderland), Chelsea's continued inconsistency, and City's shock collapse. The model continues to favour elite teams in hostile territory, a bias that cost it three picks this week. A 46% season mark isn't elite, but it reflects the inherent chaos of knockout football and mid-season volatility. See the pre-match preview for the thinking that preceded these results.

Half-time re-predictions this gameweek

At half-time the AI re-reads each match and re-predicts. Here is how those calls did against the pre-match calls, on the same set of Gameweek 10 matches.

Pre-match

5/10

50% correct

At half-time

6/10

60% correct

    Where half-time changed the call

    Nottingham Forest 3–1 Manchester City

    Pre-match: Manchester City ✗ · Half-time: Draw (2–2) ✗

    Why the call changed

    • xG 0.8 v 0.9
    • Shots on target 4 v 3
    • Possession 25% v 75%

    Sunderland 1–0 Chelsea

    Pre-match: Chelsea ✗ · Half-time: Draw (1–1) ✗

    Why the call changed

    • xG 1.7 v 0.2
    • Shots on target 1 v 2
    • Possession 32% v 68%

    Ipswich Town 1–2 Bournemouth

    Pre-match: Ipswich Town ✗ · Half-time: Bournemouth (1–2) ✓

    Why the call changed

    • xG 0.1 v 1.4
    • Shots on target 1 v 3
    • Possession 56% v 44%

    Manchester United 4–4 Aston Villa

    Pre-match: Aston Villa ✗ · Half-time: Manchester United (4–3) ✗

    Why the call changed

    • xG 1.7 v 1.2
    • Shots on target 5 v 3
    • Possession 52% v 48%

    This is a single gameweek — far too small a sample to read anything into, in either direction. See the running pre-match vs half-time comparison on our accuracy page for the season picture.

    Share this verdict:

    Prediction figures in this article reflect the data available at the time of publication and may have shifted since. See the live Gameweek 10 fixtures for the current numbers on each match.

    See how the AI called it before kickoff:

    Read the Gameweek 10 preview →