Skip to main content

Trouble With The Curve: Improving MLB Pitch Classification

Publication ,  Journal Article
Pane, MA; Ventura, SL; Steorts, RC; Thomas, AC
April 5, 2013

The PITCHf/x database has allowed the statistical analysis of of Major League Baseball (MLB) to flourish since its introduction in late 2006. Using PITCHf/x, pitches have been classified by hand, requiring considerable effort, or using neural network clustering and classification, which is often difficult to interpret. To address these issues, we use model-based clustering with a multivariate Gaussian mixture model and an appropriate adjustment factor as an alternative to current methods. Furthermore, we describe a new pitch classification algorithm based on our clustering approach to address the problems of pitch misclassification. We illustrate our methods for various pitchers from the PITCHf/x database that covers a wide variety of pitch types.

Duke Scholars

Publication Date

April 5, 2013
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Pane, M. A., Ventura, S. L., Steorts, R. C., & Thomas, A. C. (2013). Trouble With The Curve: Improving MLB Pitch Classification.
Pane, Michael A., Samuel L. Ventura, Rebecca C. Steorts, and A. C. Thomas. “Trouble With The Curve: Improving MLB Pitch Classification,” April 5, 2013.
Pane MA, Ventura SL, Steorts RC, Thomas AC. Trouble With The Curve: Improving MLB Pitch Classification. 2013 Apr 5;
Pane MA, Ventura SL, Steorts RC, Thomas AC. Trouble With The Curve: Improving MLB Pitch Classification. 2013 Apr 5;

Publication Date

April 5, 2013