EAST LANSING – Supported Intelligence unveiled SmartPitcher, a data-driven pitch selection model, during game one of the 2015 World Series Tuesday night. Mets pitcher Matt Harvey threw a fastball low and in to Royals leadoff hitter Alcides Escobar to begin the bottom of the 1st. A good choice – but not the best, says SmartPitcher.
Escobar rifled the first pitch into left field and scored on an inside-the-park home run, only the 12th in World Series history. Could the thrilling start to the fall classic have been avoided? We can’t say for sure, but SmartPitcher thinks the risk could certainly have been reduced.
SmartPitcher recommended a fastball high in the strike zone instead of low and in. According the SmartPitcher model, Escobar was less likely to produce a hit on a high fastball than a low one.
SmartPitcher recommendations for Harvey pitching to Escobar, 0-0 count Although Harvey’s chosen pitch was more likely to draw a strike, SmartPitcher considered the low hit probability more important.
“SmartPitcher is designed to maximize out probability and minimize on-base probability over the course of the entire at-bat,” says Supported Intelligence Lead Developer Neal Anderson. “This led SmartPitcher to value the high fastball more than the fastball low and away.”
Follow SmartPitcher on Twitter (@smartpitcher) for live pitch recommendations throughout the Series. Stay tuned for more pitch analysis throughout the week from SmartPitcher and Supported Intelligence.
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.
Supported Intelligence provides software and analytical services to help people make better decisions. We are dedicated to harnessing recent advances in technology and analytical methods to improve decision making across multiple departments and industries. Our patent pending Rapid Recursive method is a true breakthrough in decision analytics and is at the core of many of our product and service offerings.
