AI Game Review
Geelong Cats defied the model's 85% prediction for Collingwood — a notable upset. The margin model missed here — predicting 17.9 but the actual margin was 3 points. Geelong Cats trailed 49–42 at half-time before staging a second-half comeback to win 87–90. A tough result for the model — all 3 picks missed on this one.
Model vs actual outcomes • Post-match analysis
Quarter-by-Quarter Win Probability
AI Win Probability
Collingwood
85%
Geelong Cats
15%
AI Match Overview
Collingwood are clear favourites here at 85%, with our model expecting a comfortable victory over Geelong Cats. The model sees Collingwood ahead on 6 of 7 key factors including ELO Difference, Midfield ELO and Recent Win Rate. Collingwood carry a 152-point ELO rating advantage (1801 vs 1650). Recent form favours Collingwood with 5 wins from their last 5 compared to 3 for Geelong Cats. The margin model predicts Collingwood by 17.9 points with a combined total of 170.
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
Collingwood to Win @1.45
Lost ✗
Edge
+16.3%
Line / Spread
Collingwood -13.5 @1.91
Lost ✗
Edge
+16.3%
Total Points
Under 172.5 @1.91
Lost ✗
Edge
+2.6%
Form & History
| Team | Last 5 | Avg Pts |
|---|---|---|
Collingwood | WWWWW | 92.0 |
Geelong Cats | WWWLL | 85.4 |
Avg Conceded
62.6
Collingwood
77.8
Geelong Cats
Avg Margin
29.4
Collingwood
7.6
Geelong Cats
Disposals
359.0
Collingwood
345.2
Geelong Cats
Inside 50s
50.0
Collingwood
50.0
Geelong Cats
📊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
85%
Collingwood predicted to win by 18 points
Predicted total: 170 · Line: +17.9
Player Work Effort
Per-minute effort vs effectiveness (vs personal average)Team Effort
-0.23
Team Effectiveness
+0.13
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.