AI Game Review
Our model correctly predicted St Kilda to win at 84% probability. The margin model missed here, predicting 37.3 but the actual margin was 4 points. The game's 108 points came in 29 points lower than the predicted 137. A clean sweep, all 3 model picks hit for this match.
Model vs actual outcomes • Post-match analysis
Quarter-by-Quarter Win Probability
AI Win Probability
Richmond
16%
St Kilda
84%
AI Match Overview
St Kilda are clear favourites here at 84%, with our model expecting a comfortable victory over Richmond. Both sides are evenly matched across the key prediction factors, which explains the tight margin between them. Recent form favours St Kilda with 3 wins from their last 5 compared to 2 for Richmond. The margin model predicts St Kilda by 37.3 points with a combined total of 137.
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
St Kilda to Win @1.36
Winner ✓
Edge
+10.8%
Line / Spread
St Kilda +18.5 @1.91
Winner ✓
Edge
+10.8%
Total Points
Under 162.5 @1.91
Winner ✓
Edge
+2.6%
Form & History
| Team | Last 5 | Avg Pts |
|---|---|---|
Richmond | W W L L L | 83.4 |
St Kilda | W W W L L | 102.7 |
Avg Conceded
73.6
Richmond
69.0
St Kilda
Avg Margin
14.7
Richmond
2.1
St Kilda
Disposals
339.0
Richmond
365.1
St Kilda
Inside 50s
46.1
Richmond
49.6
St Kilda
ELO–Market Disagreement
Richmond hold the ELO advantage (1494 vs 1488), but the market favours St Kilda (@1.36).
The model sides with the market, other factors override the ELO gap.
📊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
84%
St Kilda predicted to win by 37 points
Predicted total: 137 · Line: -37.3
Player Work Effort
Per-minute effort vs effectiveness (vs personal average)Team Effort
-0.34
Team Effectiveness
-0.03
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.