Pitch GradesMovement ProfilesArsenal SynergyDeceptionProjectionsHow Models WorkMethodologyResearchAI ProcessChangelog
Heads up: All models on this page are in their early stages and should be considered placeholders. The underlying methodology is still being refined — take the specific numbers with a grain of salt.
How Models Work
Boosted Trees
Why XGBoost powers the pitch grades
XGBoost builds hundreds of tiny decision trees that learn from each other's mistakes. Early stopping prevents the model from memorizing noise when the real signal runs out — which happens fast on noisy per-pitch data.