What is it about?
Pitcher’s performance is the most important factor for winning or losing baseball games. We propose a novel model for analyzing the performance of starting pitchers, determining when they should be removed from the game and replaced by a reliever. Our approach is based on time series classification methods.
Featured Image
Why is it important?
Predicting the future performance of baseball players based on their historical records and statistics is a very active field of research today because of its numerous advantages for managerial and decision-making. One of the most complex decision problems that baseball managers have to handle during games consists in deciding when a fatigued, or faltering, pitcher should be removed from the game and replaced by a reliever. In this paper we present a predictive model for determining when a starting pitcher is about to falter using time series classification methods.
Perspectives
This paper shows that that the in-play performance of a starting pitcher is not a homogeneous process. We demonstrate that modeling and visualizing these non-homogeneous parts of the game as time series data, using some reasonable criterion of performance, could significantly improve our comprehensibility about pitching. Furthermore, we show that the application of time series classification methods could be a suitable tool for the particular problem of predicting the future performance of a baseball pitcher.
César Soto-Valero
Universidad Central Marta Abreu de las Villas
Read the Original
This page is a summary of: A predictive model for analysing the starting pitchers’ performance using time series classification methods, International Journal of Performance Analysis in Sport, July 2017, Taylor & Francis,
DOI: 10.1080/24748668.2017.1354544.
You can read the full text:
Contributors
The following have contributed to this page
