I'm a Statistics and Data Science student at UCLA interested in baseball analytics, sports data, and applied statistical modeling.
Currently, I'm building projects in R focused on player evaluation, simulation, and reproducible sports analytics workflows.
Monte Carlo simulation model for evaluating baseball batting orders using hitter event probabilities.
This project builds hitter profiles from plate appearance outcomes, applies sample-size shrinkage, simulates full 9-inning games, and ranks candidate batting orders by projected run production. It also compares a custom lineup against the model’s recommended lineup to show how simulation can support baseball decision-making.
Explainable Stuff+ style model for evaluating pitch quality from TrackMan-style data.
This project scores pitches using physical pitch traits such as velocity, movement, spin rate, extension, and fastball separation. The model converts pitch-level scores to a plus scale, summarizes results by pitcher and pitch type, and creates arsenal-level grades for player evaluation and development.
Reproducible workflow for creating player-specific hitter and pitcher exports from pitch-level baseball data.
This project turns a combined TrackMan-style dataset into organized player folders with cleaned pitch-by-pitch files, hitter summaries, pitcher summaries, pitch-type breakdowns, batting-against reports, and batch export logs. The public version uses synthetic data to demonstrate the workflow structure without including private team files.
R, SQL, Power BI, Tableau, Excel, C++
Baseball analytics, player evaluation, simulation modeling, sports strategy, and data visualization.