Australian Team Pursuit Race Modeling
Spring 2025
Race Power Modeling
Analysis & Results
PCA-Based Season Clustering
Used principal component analysis to reduce season-level scoring data to 9 components, then clustered NFL seasons based on similarities in team scoring patterns. The resulting 5 clusters did not reveal clear, chronologically distinct eras.
Rider Energy Utilization
Modeled rider-specific energy expenditure to evaluate how effectively a simulated race strategy utilized each athlete’s available capacity.
Modeled rider-specific power demands throughout the team pursuit to evaluate how different race strategies distribute effort across the team.
Led development of a physics-based modeling and optimization framework for AusCycling to evaluate race strategies for the 4,000 m team pursuit. I led the technical development and integration of the model, incorporating race dynamics and rider-specific performance constraints to simulate team performance and compare potential strategies. The project combined engineering modeling, optimization, and data analysis to support data-driven race planning for the Australian national team.
— Modeling · Optimization · Sports Engineering —
Least-Squares Modeling of League Trends
Developed a least-squares model relating team scoring to rushing, passing, and defensive performance, then tracked the fitted coefficients over time to investigate changes in league-wide play.
Teams Performance Over Time
Visualized the passing coefficient from the least-squares model across teams and seasons, revealing periods of sustained passing performance that align with several prominent quarterback tenures.