The Quality of Pitches in Major League Baseball. Issue 2 (3rd April 2017)

• Record Type: Journal Article
• Authors: Swartz, Philippa; Grosskopf, Mike; Bingham, Derek; Swartz, Tim B.
• Is Part Of: American statistician. Volume 71:Issue 2(2017)
• Page Start: 148
• Page End: 154
• Publication Date: 2017-04-03
• Subjects: Machine learning -- PITCHf/x data -- Random forests; Statistics -- Periodicals; 001.42205
• DOI: 10.1080/00031305.2016.1264313
• Languages: English
• ISSNs: 0003-1305

Abstract

ABSTRACT: This article considers the quality of pitches in Major League Baseball (MLB). Based on approximately 2.2 million pitches taken from the 2013, 2014, and 2015 MLB seasons, the quality of a particular pitch is evaluated as the expected number of bases conceded. Quality is expressed as a function of various covariates including pitch count, pitch location, pitch type, and pitch speed. The estimation of the pitch quality is obtained through the use of random forest methodology to accommodate the inherent complexity of the relationship between pitch quality and the associated covariates. With the fitted model, various applications are considered which provide new insights on pitching and batting.