Abstract Details
Activity Number:
|
107
|
Type:
|
Invited
|
Date/Time:
|
Monday, August 5, 2013 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistics in Sports
|
Abstract - #307411 |
Title:
|
Using Pattern Recognition to Classify Pitch Types from MLB PITCHf/x Data
|
Author(s):
|
Michael D. Schader*+
|
Companies:
|
George Mason University
|
Keywords:
|
baseball ;
pitchfx ;
pattern recognition ;
machine learning ;
classification
|
Abstract:
|
The volume of granular data available to baseball analysts today provides an opportunity to discover hidden relationships and non-obvious patterns. The field of Pattern Recognition supplies the tools to work with such data. In this effort, we use PITCHf/x trajectory parameters to train various types of classifiers to determine pitch type. We experiment with ways to improve accuracy by incorporating the context of each individual pitcher into the feature set, rather than resorting to building a specific classifier for every player. Our final results show excellent accuracy at duplicating the pitch classifications of the official MLB system, and could be applied to other taxonomies and other data sets.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.