Santa Barbara, California, United States
Developed a machine learning-based Swing Decision Model in Python to assess the expected run value impact of swinging or taking a pitch, enhancing decision-making analytics for player and game strategies.
Performed extensive data cleaning and preprocessing to ensure high-quality inputs for the model, employing techniques to handle missing values, outliers, and feature engineering.
Managed and analyzed large datasets using SQL to extract, transform, and load data efficiently, optimizing database queries for performance.
Utilized scikit-learn and other machine learning libraries to build and tune regression models, implementing strategies to evaluate model performance
Applied statistical analysis and visualization tools to interpret and communicate model results, collaborating with the analytics team to drive insights for game strategy and player development
Maintained well-documented code and presented findings to coaches and faculty, emphasizing data-driven recommendations