Chart point construction, rally shape, and player tendencies across match contexts.
Tennis analytics
Tennis
Match strategy, player development, and scouting work across three configurable programs.
Workstreams
What this team studies
Connect serve placement and next-shot advantage to tactical match planning.
Package match data into scouting notes, player profiles, and role-specific workflows.
Featured work
Machine Learning Based Playstyle Classification for NCAA Tennis Players
A transfer-learning tennis playstyle classifier that turns point-by-point match charting into player archetype scores, using professional data to label styles and UCLA match data to generate radar-plot profiles.
Problem
Coaches and scouts lack a systematic way to categorize player playstyles from match statistics, relying instead on subjective observation.
Approach
The team trains classification models on match-level features to assign players to playstyle archetypes such as baseliner, serve-and-volleyer, and counter-puncher.
Result
Read paper The framework produces interpretable playstyle labels validated against expert ratings and surfaces dominant archetypes across the NCAA landscape.
Tennis roles
Role-based programs
Scouting - role
Projects, dashboards, lead contacts, and archived work for this tennis role area.
Open roleTagging - role
Projects, dashboards, lead contacts, and archived work for this tennis role area.
Open roleStrategy - role
Projects, dashboards, lead contacts, and archived work for this tennis role area.
Open roleActive projects
Research
Current work
ResearchMachine Learning Based Playstyle Classification for NCAA Tennis Players
January 3, 2026Tennis · 2025-26
A transfer-learning tennis playstyle classifier that turns point-by-point match charting into player archetype scores, using professional data to label styles and UCLA match data to generate radar-plot profiles.
PythonGMMRandom Forest
Archive
Past work
Past work will appear here as the archive is filled out.
