AI Game Review
Geelong Cats defied the model's 63% prediction for Hawthorn, a notable upset. The margin model missed here, predicting 23.8 but the actual margin was 7 points. Total score prediction of 160 was close to the actual 165, within 5 points. The model went 1/3 on this match. The under 172.5 total call was correct.
Model vs actual outcomes • Post-match analysis
Quarter-by-Quarter Win Probability
AI Win Probability
Geelong Cats
37%
Hawthorn
63%
AI Match Overview
Hawthorn hold the advantage at 63% win probability, though Geelong Cats are far from out of this at 37%. The model sees Hawthorn ahead on 4 of 7 key factors including ELO Difference, Midfield ELO and Recent Win Rate. Hawthorn carry a 41-point ELO rating advantage (1565 vs 1525). Recent form favours Hawthorn with 3 wins from their last 5 compared to 1 for Geelong Cats. The margin model predicts Hawthorn by 23.8 points with a combined total of 160.
Generated from model features • Pre-kick-off analysis
Edge Analysis
2 ACTIVE EDGESEach market is predicted by an independent model, H2H, margin, and totals may occasionally disagree.
H2H Recommendation
Hawthorn to Win @1.93
Lost ✗
Edge
+11.4%
Line / Spread
Hawthorn +1.5 @1.91
Lost ✗
Edge
+11.4%
Total Points
Under 172.5 @1.91
Winner ✓
Edge
+2.6%
Form & History
| Team | Last 5 | Avg Pts |
|---|---|---|
Geelong Cats | W L L L L | 107.4 |
Hawthorn | W W W L L | 102.5 |
Avg Conceded
90.1
Geelong Cats
70.5
Hawthorn
Avg Margin
-7.6
Geelong Cats
2.3
Hawthorn
Disposals
350.9
Geelong Cats
379.3
Hawthorn
Inside 50s
56.9
Geelong Cats
42.9
Hawthorn
📊Team ELO Ratings
🏈Positional Matchups
Player ELO aggregated by position group, higher = stronger unit
📈Recent Form (Last 5)
🔑Key Prediction Factors
What the model weighted most in this prediction
Model Confidence
63%
Hawthorn predicted to win by 24 points
Predicted total: 160 · Line: -23.8
Player Work Effort
Per-minute effort vs effectiveness (vs personal average)Team Effort
-0.20
Team Effectiveness
-0.21
Effort = pressure acts + tackles + contested possessions per minute on field, z-scored vs career avg. Effectiveness = disposal efficiency + fantasy/min + score involvements − errors, z-scored vs career avg.
Goal Scorer Predictions
AI-powered goal scorer predictions and player prop markets, built on our 6-model player stats engine.