The Price of Victory - A Machine Learning Analysis of How Salary Dispersion Influences Team Success in Major League Baseball

Aug 5, 2026

Upload by Aurelia

The Price of Victory examines how salary dispersion affects team success in Major League Baseball. Using data from 29 MLB teams across eight seasons (2012–2019), the study applies Ordinary Least Squares, panel data regressions, and Random Forest machine learning to test whether payroll inequality predicts winning percentage. Results show salary dispersion, measured by a Gini coefficient, is not a significant predictor. Instead, performance indicators such as ERA, runs scored, and fielding percentage consistently explain success. Findings support roster construction that prioritizes performance optimization over maximizing wage equity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Research objectives

Background and theory

Prior evidence and motivation

Methods and data

Modeling approaches (OLS, panel data, Random Forest)

Success and performance measures

Results and implications

Significance of salary dispersion vs. team metrics

Recommended roster-building focus

The Price of Victory: A Machine Learning Analysis of How Salary Dispersion Influences Team Success in Major League Baseball Joseph Belsanti Abstract This paper examines the effect of salary dispersion on team success in Major League Baseball (MLB). Using data from 29 MLB teams over eight seasons (2012-2019), this study uses multiple models, such as Ordinary Least Squares (OLS), panel data regressions, and Random Forest machine learning, to investigate the degree – if any – that inequalities in a team's payroll impacts success, measured by winning percentage. The study's results show that, contrary to prevailing theories, salary dispersion – measured by a Gini coefficient – is not a significant predictor of a team's winning percentage (team success). Instead, team performance metrics, such as Earned Run Average (ERA), Runs Scored, and Fielding Percentage, have consistently showed to be statistically significant predictors of team success. As the results indicate that a payroll with wage inequality does not necessarily negatively impact team success, the findings suggest that MLB teams should prioritize constructing a roster that optimizes performance metrics rather than optimizes equitable salary distribution. By applying both traditional economic models (OLS, panel data regressions) and machine learning techniques (Random Forest), this study adds to the comprehensive list of literature covering organizational efficiency and labor economics in professional sports. JEL Classification: J31, L83, C23, C55 Keywords: Salary dispersion, team performance, Major League Baseball (MLB), Ginicoefficient, panel data analysis, Random Forest, SHAP values, labor economics, sports economics. a Department of Economics, Bryant University, 1150 Douglas Pike, Smithfield, RI02917 . Phone: (978) 727-3932. Email: [j](jbelsanti@bryant.edu)[belsanti@bryant.edu](jbelsanti@bryant.edu) 1.0 INTRODUCTION Major League Baseball (MLB) has long allowed for a look into the complex relationship between salary structures and organizational outcomes and performance. The MLB, serving as"America's Pastime," has historically been a natural experiment involving labor dynamics, organizational economics, and sports economics. Baseball's unique characteristic of being a sport obsessed with statistics yields an environment where advanced analytics can help explain the dynamics between salary structure and team performance. These dynamics add to the complexities of team management and roster construction that teams and their leadership constantly deal with – especially in the case of allocating financial resources to optimize on-field performance. This study aims to enhance the understanding of how inequalities in the salary structure of sports teams, specifically Major League Baseball teams, influence team success. From a policy perspective, this analysis is important because of its potential to help in successful roster construction, influencing how teams decide to spend their scarce financial resources in hopes of leading to wins. The relevance of this study is that its findings are applicable to the current moment in the MLB, as teams are spending more money than ever before on players. Recently, MLB teams have substantially increased their spending on players. For example, the Los Angeles Dodgers signed star player Shohei Ohtani to a 10-year, $700 million contract during the 2024 offseason, with $680 million being deferred until his 10-year contract is complete. Additionally, star outfielder Juan Soto signed a 15-year contract worth $765 million with the New York Mets, marking the largest contract in MLB history. As teams continue to spend on talent, questions arise regarding how payroll increases should be distributed among team members. To maximize a team's chance of success, should ateam's payroll be evenly distributed across the entire team, or should it be concentrated among a few star players? With teams willing to sign players to contract

FAQs

How is salary dispersion measured, and what relationship is tested with team success?

Salary dispersion is measured using a Gini coefficient, and its relationship to team success is tested using winning percentage.

Which modeling methods are used to evaluate predictors of team success?

The study uses Ordinary Least Squares, panel data regressions, and Random Forest machine learning models.

What factors are found to be significant predictors of team success in the study?

Team performance metrics, including ERA, runs scored, and fielding percentage, are consistently identified as statistically significant predictors.

Aug 5, 2026

Upload by Aurelia