Overview
The Wharton Sports Analytics and Business Initiative runs this competition with Wharton Global Youth, and it has become one of the more substantive data science experiences a high schooler can take on without leaving their kitchen table. The data closely resembles what professional teams actually work with, the judging panel includes Wharton statistics faculty and industry data scientists, and the whole thing costs nothing to enter.
Each year centers on a different sport, and the dataset is fully synthetic — meaning your child is testing their analytical skills, not their ability to Google real-world stats. Past competitions have featured a fictional women's pro soccer league, a basketball season, and an ice hockey tournament. A new sport is announced ahead of each registration window.
How the Competition Works
Teams receive a complete regular season of simulated league data and answer a layered prompt: rank the teams heading into a tournament, predict matchup outcomes, surface the performance stats that matter, and visualize what they find. The competition unfolds in three phases over roughly ten weeks.
- Phase 1 — Performance Predictions: Teams submit power rankings, tournament predictions, key performance stats, and visualizations. Auto-scored and graded against a rubric.
- Phase 2 — Semifinals Slide Presentation: Advancing teams build a 7-slide deck explaining their methodology. Judged on clarity, methodological rigor, visualization, and creativity.
- Phase 3 — Virtual Finals: The top 5 teams present live over Zoom to a panel of judges who name 1st, 2nd, and 3rd place.
Who It's For
A genuinely strong fit for the kid who likes sports and wonders why certain teams overperform their record — or who has started noticing that the most interesting questions don't have clean answers. Algebra 1 is the recommended starting point, meaning your child does not need to be a coding prodigy to participate. What they do need is curiosity about how data tells a story, and the patience to wrestle with a messy problem alongside teammates.
Judges & Mentorship
The judging panel is what sets this apart. Past judges have included Wharton statistics faculty, sports analytics professors from other universities, and Google data scientists. Throughout the competition, teams get access to online learning modules to support their work.
What Makes This Different
Most high school data competitions hand you a clean dataset and a single question. This one hands your child a messy, real-shaped problem with multiple deliverables — rankings, predictions, stats, visualizations — and asks them to defend their methodology to faculty who actually do this for a living. Top finishers earn publication in a special edition of the Wharton Sports Analytics Journal, a credential that carries real weight on a college application.
Application & Eligibility
- Open to high school students worldwide ages 14–18
- Teams of 3–5 students from the same high school, plus one Advisor employed by the school or district
- Home-schooled students may form their own team or join a school-based team — written approval from competition staff is required in advance
- A designated Student Team Leader, age 16 or older, is required for privacy compliance
- Algebra 1 recommended
Cost & Information
- Registration: Free
- Typical timeline: Registration opens in early December and closes in late January. Data is released in early February. Phase 1 submissions due in early March. Semifinal slide decks due late March. Finals held in mid-April.