An optimization of baseball fielder positioning using SEAM

Alberts, Colin

Permalink

https://hdl.handle.net/2142/124170 Copy

Description

Title

An optimization of baseball fielder positioning using SEAM

Author(s)

Alberts, Colin

Issue Date

2024-05-01

Director of Research (if dissertation) or Advisor (if thesis)

Eck, Daniel J

Department of Study

Mathematics

Discipline

Applied Mathematics

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Sabermetrics
• Big data applications and visualizations
• Gradient descent
• Stochastic gradient descent
• Spatial optimization

Abstract

In the last decade, professional baseball has witnessed significant statistical and analytical advancements that have profoundly impacted on-field strategies. This study delves into diverse strategies for positioning defensive players by employing deterministic and stochastic gradient methods. These methods optimize fielder alignments based on a synthetic distribution estimating batted ball distributions across all Major League Baseball (MLB) batter-pitcher matchups in any MLB ballpark. The primary aim is to devise a fielder placement model that minimizes expected batting average for balls in play by maximizing the density coverage of each fielder. This research explores various optimization techniques to identify the most effective approach in terms of both optimality and implementation practicality. This methodology could be generalized to determine optimal fielder alignments for similar sports or applications such as softball, cricket, or region design. The code for this work can be found in this GitHub repository.

Graduation Semester

2024-05

Type of Resource

Thesis

Copyright and License Information

Copyright 2024 Colin Alberts

Owning Collections