What is it about?
In this research, we develop a system that makes predictions related to pitches in baseball. Unlike the previous researches for predicting pitch types only, we also predict pitch locations in addition to pitch types. Pitch location is the place where the pitched ball arrives among the imaginary grids drawn in front of the catcher. In the previous researches for predicting pitch types, the number of classes to predict was 2~7. However, in our research, since we also predict pitch locations, the number of classes to predict is 34.
Featured Image
Photo by Bill Stephan on Unsplash
Why is it important?
In order to win a baseball game, the batter must hit the ball and go on base. The reason we want to predict the pitch is to give information to the batter so that he can hit the ball. In order for the batter to hit the ball, he needs to know where the ball is coming in, i.e., pitch location. Prediction of pitch location has not been addressed in the previous researches. Therefore, pitch type predictions in the previous researches did not provide enough information that could be used practically in baseball games. The innovation of our research is to simultaneously predict pitch types and pitch locations.
Perspectives
Read the Original
This page is a summary of: Prediction of pitch type and location in baseball using ensemble model of deep neural networks, Journal of Sports Analytics, July 2022, IOS Press,
DOI: 10.3233/jsa-200559.
You can read the full text:
Contributors
The following have contributed to this page