bottoms-up model
A predictive model built from the most granular events, such as individual pitches or batted-ball physics, and aggregated upward.
As defined in Making Decisions with Data
Where it comes up · 1
- Making Decisions with Data2 claims
Most important claims · 2 of 2Search all claims for “bottoms-up model” →
- For a long time sports data was poor because it captured what was easy to record, which describes what happened in the game rather than what best predicts outcomes; player tracking and computer vision now provide data built for prediction.Making Decisions with Data
- A single in baseball can be a weak ground ball or a rocket that barely misses a home run, so modern cameras that capture launch angle, spin rate, velocity and exit velocity are needed to build bottoms-up models that predict outcomes.Making Decisions with Data