Pitcher Greeks: First Principles, Stuff Models, and Derivatives
Aug 1, 2026·
·
0 min read
Aidan Resnick
Abstract
Stuff models grade a pitch from its physical characteristics alone —
velocity, induced movement, and approach angles. This paper builds a
continuous, differentiable stuff index per pitch type and borrows the
language of options pricing: each pitch gets “greeks,” the local
sensitivities of expected run value to its physical inputs, evaluated on
the manifold of pitches that actually get thrown. (TODO: replace with the
paper’s real abstract.)
Type
Authors
Quantitative Trader · Baseball Researcher
I’m a quantitative trader at Chicago Trading Company and a baseball
researcher in my free time. My recent work develops “pitcher greeks”:
continuous, differentiable stuff models whose sensitivities show how run
value responds to changes in a pitch’s velocity, movement, and approach
angles.