SANFL
Performance

How our tipping heuristics are performing.

Current Season 2026

23 / 23 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 $209.00
Projected Annual Profit $209.00
Projections are based on early season performance and may change as the season progresses.
Accuracy63.5%
Rounds Played23
Avg Profit/Round $9.09
Odds Coverage0%

Weighted Tip

Current Season
Year-to-Date Profit $209.00
Projected Annual Profit $209.00
Projections are based on early season performance and may change as the season progresses.
Accuracy63.5%
Rounds Played23
Avg Profit/Round $9.09
Odds Coverage0%

Boosted Tip

Current Season
Year-to-Date Profit $608.00
Projected Annual Profit $608.00
Projections are based on early season performance and may change as the season progresses.
Accuracy85.4%
Rounds Played23
Avg Profit/Round $26.43
Odds Coverage0%
Individual Model Accuracy
Value★
70.5%
Accuracy
$323
Profit
Form
70.0%
Accuracy
$297
Profit
Elo Rating
65.3%
Accuracy
$228
Profit
Matchup
62.0%
Accuracy
$89
Profit
Home Advantage
48.9%
Accuracy
$-65
Profit

Weighted Tip Model

v73
Trained: Tue, 10 Nov, 08:00 amTraining rows: 96Intercept: 1.87R²: 0.3180MAE: 27.2

The Weighted Tip model combines all 5 ML model predictions using a linear regression trained on 96 historical games. Each model contributes a margin weight (influence on score margin) and a confidence weight (influence on confidence). The current model (v73) has R² = 0.318 with intercept 1.87. 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 =1.87+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)

v59
Trained: Tue, 10 Nov, 08:00 amTraining rows: 96R²: 0.8607MAE: 12.1SHAP base value: 2.93

The Boosted Tip model is a gradient-boosted tree ensemble (XGBoost) trained on 96 historical games to predict the home-team-signed margin from the same model predictions the Weighted Tip model uses. The current model (v59) reaches R² = 0.861 with MAE = 12.1 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, form wins diff, value win rate diff the most influential.

SHAP Feature Importance