NRFI/YRFI Prediction Engine

How the model works

The engine uses a Poisson scoring model: for each half-inning, expected runs (λ) are derived from the pitcher's historical first-inning NRFI rate via λ = −ln(NRFI Rate), then adjusted multiplicatively for the opposing lineup's first-inning offensive factor, park factor, and weather.

P(NRFI) = P(home scores 0) × P(away scores 0) = e^−λ_home × e^−λ_away

Value bets are identified when the model's implied probability exceeds the bookmaker's by ≥3%. Kelly Criterion (25% fractional) sizes the recommended wager.