AFLW
Performance

How our tipping heuristics are performing.

Current Season 2026

13 / 16 rounds completed

How profit is calculated: each tip carries a simulated $10 stake. Games with bookmaker odds (The Odds API) settle at the real decimal price for the tipped team; games without an odds snapshot settle at a representative $1.90; drawn games refund the stake. Odds coverage shows the share of tips settled at real prices.

Best Bet

Current Season
Year-to-Date Profit $286.00
Projected Annual Profit $352.00
Projections are based on early season performance and may change as the season progresses.
Accuracy66.1%
Rounds Played13
Avg Profit/Round $22.00
Odds Coverage0%

Weighted Tip

Current Season
Year-to-Date Profit $248.00
Projected Annual Profit $305.23
Projections are based on early season performance and may change as the season progresses.
Accuracy64.3%
Rounds Played13
Avg Profit/Round $19.08
Odds Coverage0%

Boosted Tip

Current Season
Year-to-Date Profit $666.00
Projected Annual Profit $819.69
Projections are based on early season performance and may change as the season progresses.
Accuracy83.9%
Rounds Played13
Avg Profit/Round $51.23
Odds Coverage0%
Individual Model Accuracy
Form★
74.8%
Accuracy
$433
Profit
Value
68.8%
Accuracy
$343
Profit
Elo Rating
67.0%
Accuracy
$305
Profit
Matchup
50.0%
Accuracy
$-1
Profit
Home Advantage
48.6%
Accuracy
$-83
Profit

Weighted Tip Model

v81
Trained: Tue, 10 Nov, 08:00 amTraining rows: 111Intercept: 2.34R²: 0.3319MAE: 20.4

The Weighted Tip model combines all 5 ML model predictions using a linear regression trained on 111 historical games. Each model contributes a margin weight (influence on score margin) and a confidence weight (influence on confidence). The current model (v81) has R² = 0.332 with intercept 2.34. Most influential models: elo rating diff, form wins diff, home advantage home constant. The model is retrained weekly with updated coefficients.

Model Equation
predicted_margin =2.34+0.000·elo rating diffm+0.000·form wins diffm+0.000·home advantage home constantm+0.000·matchup h2h wins diffm+0.000·value win rate diffm

Each model contributes a margin weight (× its predicted margin toward home) and a confidence weight. Models with larger absolute weights have more influence on the final tip.

Margin Weights

Active Boosted Model (XGBoost)

v67
Trained: Tue, 10 Nov, 08:00 amTraining rows: 111R²: 0.6800MAE: 12.5SHAP base value: 2.95

The Boosted Tip model is a gradient-boosted tree ensemble (XGBoost) trained on 111 historical games to predict the home-team-signed margin from the same model predictions the Weighted Tip model uses. The current model (v67) reaches R² = 0.680 with MAE = 12.5 points and is retrained weekly. Feature importances below are mean |SHAP| values — how much each model's margin and confidence signal moves the prediction, with elo rating diff, value win rate diff, form wins diff the most influential.

SHAP Feature Importance