NRLW
Performance

How our tipping heuristics are performing.

Current Season 2026

14 / 14 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 $202.00
Projected Annual Profit $202.00
Projections are based on early season performance and may change as the season progresses.
Accuracy67.6%
Rounds Played14
Avg Profit/Round $14.43
Odds Coverage0%

Weighted Tip

Current Season
Year-to-Date Profit $240.00
Projected Annual Profit $240.00
Projections are based on early season performance and may change as the season progresses.
Accuracy70.4%
Rounds Played14
Avg Profit/Round $17.14
Odds Coverage0%

Boosted Tip

Current Season
Year-to-Date Profit $449.00
Projected Annual Profit $449.00
Projections are based on early season performance and may change as the season progresses.
Accuracy85.9%
Rounds Played14
Avg Profit/Round $32.07
Odds Coverage0%
Individual Model Accuracy
Matchup★
80.0%
Accuracy
$26
Profit
Elo Rating
69.0%
Accuracy
$221
Profit
Value
66.2%
Accuracy
$183
Profit
Form
64.6%
Accuracy
$148
Profit
Home Advantage
50.0%
Accuracy
$-34
Profit

Weighted Tip Model

v80
Trained: Tue, 10 Nov, 08:00 amTraining rows: 71Intercept: 1.13R²: 0.3413MAE: 16.2

The Weighted Tip model combines all 5 ML model predictions using a linear regression trained on 71 historical games. Each model contributes a margin weight (influence on score margin) and a confidence weight (influence on confidence). The current model (v80) has R² = 0.341 with intercept 1.13. 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 =1.13+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)

v66
Trained: Tue, 10 Nov, 08:00 amTraining rows: 71R²: 0.7822MAE: 7.6SHAP base value: 0.52

The Boosted Tip model is a gradient-boosted tree ensemble (XGBoost) trained on 71 historical games to predict the home-team-signed margin from the same model predictions the Weighted Tip model uses. The current model (v66) reaches R² = 0.782 with MAE = 7.6 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