Wharton High School Data Science Competition:
Soccer Playoff Predictions

Building Data Science Skills Through the Lens of Sports

The Wharton Sports Analytics and Business Initiative and Wharton Global Youth Program are excited to host the first Wharton High School Data Science Competition: Soccer Playoff Predictions. It’s a team-based opportunity for high school students to build their skills in data science through the lens of sports.

Using comprehensive data from a simulated professional soccer league, teams of high school students will crunch the numbers and make win-loss predictions about the league’s playoffs. Participants will be provided with a complete regular season of game-level results that include various summary game statistics. Based on the regular season team performance, they will predict the results of playoff games in both the Group Stage and the Knockout Stage. Teams will then make predictions of match outcomes during the playoffs. Success in the competition will be based on the accuracy of the predictions, the soundness of the methods used, creativity, and how well the teams’ methods and findings are described and communicated.

The competition will take part in 3 phases
that begin once registration is closed

Phase 1

February 2 – March 4
Soccer Playoff Game Predictions, submitted via online platform

Phase 2

March 5 – March 22
Semifinals – Description & Slide Presentation, submitted via online platform

Phase 3

April 3
Final Presentation, virtual presentation to a panel of judges

Welcome to the North American Soccer League

In order to keep the competition as realistic as possible, the Wharton Sports Analytics and Business Initiative has created a fictional 28-team league – the North American Soccer League (NSL) – complete with comprehensive stats for each club. The story of our league is as follows.

The NSL just hired a new, forward-thinking Commissioner, and she’s looking to position the NSL for long-term success by fully embracing data analytics.

The NSL needs help to make informed, analytics-backed predictions about two rounds of the NSL playoffs, using data the league captured for each of its 28 teams.

In addition to predictions, the League is also looking for a brief writeup that describes each team’s approach and methodology. Think you and your fellow students have what it takes?


1st Place Team

1st place trophy + opportunity to attend the Moneyball Academy: Training Camp, Moneyball Academy: Training Camp FLEX online program (Summer), or enrollment in a Global Youth Program Online Course: Future of the Business World, Essentials of Leadership free of charge + 1st place certificates + swag

2nd Place Team

2nd place trophy + virtual access to a Moneyball Academy guest speaker session + 2nd place certificates + swag

3rd Place Team

3rd place trophy + 3rd place certificates + swag

All Top-5 Teams