AI Game Review
Our model correctly predicted St Kilda to win at 60% probability. The margin model missed here — predicting 3.3 but the actual margin was 82 points. The game's 188 points came in 30 points higher than the predicted 158. St Kilda led 42–34 at the break and pulled away in the second half to win by 82. The model went 1/3 on this match.
Model vs actual outcomes • Post-match analysis
Quarter-by-Quarter Win Probability
AI Win Probability
St Kilda
60%
Richmond
40%
AI Match Overview
St Kilda hold the advantage at 60% win probability, though Richmond are far from out of this at 40%. The model sees St Kilda ahead on 6 of 7 key factors including ELO Difference, Midfield ELO and Recent Win Rate. St Kilda carry a 245-point ELO rating advantage (1482 vs 1237). Recent form favours St Kilda with 4 wins from their last 5 compared to 1 for Richmond. The margin model predicts Richmond by 3.3 points with a combined total of 158.
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
St Kilda to Win @1.24
Winner ✓
Edge
-20.8%
Line / Spread
Richmond -27.5 @1.91
Lost ✗
Edge
-20.8%
Total Points
Under 170.5 @1.91
Lost ✗
Edge
+2.6%
Form & History
| Team | Last 5 | Avg Pts |
|---|---|---|
St Kilda | WWWWL | 90.4 |
Richmond | WLLLL | 67.0 |
Avg Conceded
88.0
St Kilda
106.6
Richmond
Avg Margin
2.4
St Kilda
-39.6
Richmond
Disposals
376.8
St Kilda
346.8
Richmond
Inside 50s
50.0
St Kilda
50.0
Richmond
📊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
60%
St Kilda predicted to win by 3 points
Predicted total: 158 · Line: -3.3
Player Work Effort
Per-minute effort vs effectiveness (vs personal average)Team Effort
-0.50
Team Effectiveness
+0.43
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.