November 4, 2015
Supported Intelligence’s Lead Developer, Neal Anderson, recently joined the hosts of the M2 TechCast to discuss SmartPitcher, a pitch recommendation model created for the 2015 World Series.
“Our model is designed to maximize out probability and minimize on-base probability over the course of the entire at-bat,” says Anderson.
SmartPitcher provides data-driven pitch advice for the 2015 World Series. SmartPitcher uses data on over one million pitches from the last three MLB seasons to determine the likelihood of a called ball, a strike, the batter reaching a base, or the batter being called out. SmartPitcher feeds those likelihoods into a recursive model, which determines the best pitch choice to maximize the chance of an out during that at-bat.
You may listen to the full episode of the podcast here.
You may also read a breakdown of SmartPitcher’s analysis of the pitch that led to Alcides Escobar’s inside-the-park home run to begin Game 1 here.
SmartPitcher is on Twitter: @SmartPitcher.