Data visualization and K-means clustering in MLB: uncovering performance trends, payroll impact, and strategic insights

This study uses data visualization and K-means clustering to analyze 23 years of Major League Baseball data from sources including Baseball Savant, Baseball Reference, and Spotrac Visualizations. Key trends examined include Launch Angle, Exit Velocity, League Slash Line, and Three True Outcomes. Analyses identified the top 30 hitters by OPS, Launch Angle, and Strikeout Percentage, the top defensive players by Outs Above Average (OAA) for 2023 and a positive correlation between Exit Velocity and Slugging Percentage. The relationship between team payrolls and Wins Above Replacement (WAR) was explored, uncovering insights into financial investment and performance. K-means clustering assessed individual player values to reach the overall aim of this work, which is to contribute machine learning tactics to aid in team construction, decision making, and further the world of baseball analytics.