AI Game Review
Our model correctly predicted Collingwood to win at 52% probability. The predicted margin of 6.7 was reasonable against the actual 14-point result. The game's 180 points came in 17 points higher than the predicted 163. The model went 2/3 on this match. The 1-39 margin band call landed.
Model vs actual outcomes • Post-match analysis
Quarter-by-Quarter Win Probability
AI Win Probability
Fremantle
48%
Collingwood
52%
AI Match Overview
This shapes up as one of the tightest matchups of the round. Our model gives Collingwood a marginal 52% edge, making this essentially a coin-flip contest. The model sees Collingwood ahead on 6 of 7 key factors including ELO Difference, Midfield ELO and Recent Win Rate. Collingwood carry a 332-point ELO rating advantage (1767 vs 1435). Recent form favours Collingwood with 4 wins from their last 5 compared to 3 for Fremantle. The margin model predicts Collingwood by 6.7 points with a combined total of 163.
Generated from model features • Pre-kick-off analysis
Edge Analysis
Each market is predicted by an independent model — H2H, margin, and totals may occasionally disagree.
H2H Recommendation
Collingwood to Win @1.77
Winner ✓
Edge
-4.4%
Line / Spread
Collingwood +3.5 @1.91
Winner ✓
Edge
-4.4%
Total Points
Under 163.5 @1.91
Lost ✗
Edge
+2.6%
Form & History
| Team | Last 5 | Avg Pts |
|---|---|---|
Fremantle | WWWLL | 84.0 |
Collingwood | WWWWL | 94.2 |
Avg Conceded
79.2
Fremantle
66.6
Collingwood
Avg Margin
4.8
Fremantle
27.6
Collingwood
Disposals
335.0
Fremantle
356.6
Collingwood
Inside 50s
50.0
Fremantle
50.0
Collingwood
📊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
52%
Collingwood predicted to win by 7 points
Predicted total: 163 · Line: -6.7
Player Work Effort
Per-minute effort vs effectiveness (vs personal average)Team Effort
-0.25
Team Effectiveness
+0.01
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.