Data Challenge

Overview

Women’s soccer is historically underrepresented in media and data. CSAS, SkillCorner, and U.S. Soccer are committed to expanding data access and adding visibility to analysis of the women’s game. Additionally, we want to expand the visibility of tracking data and its applications in soccer as a whole. In accordance with these two goals, this data challenge will provide rich, frame-by-frame and event data for students to explore.

This Data Challenge focuses on pressing using data from the National Women’s Soccer League (NWSL) and Women’s Super League (FAWSL).

Questions to Consider

The concept of applying pressure as a team or a player is important for defensive evaluation and can be enhanced with tracking data. We are asking participants to evaluate how well or intelligently teams and players press using the provided datasets. Some questions to consider are:

• Pressing risk-reward: What is the value of pressing considering the disruption caused versus the space allowed?
  • Which teams/players make the most intelligent pressing decisions?
• How disruptive are teams/players when pressing?
• How often do teams/players press?
• Which teams have the most effective and coordinated press?

This is not an exhaustive set. Feel free to explore any aspect of pressing that is valuable and interesting to you.

Student Deliverables Could Include

• Pressing risk-reward metric
• Spatial press-coordination model/visualizations
• Pressing value model
• Team-specific strategy recommendations (based on frequency and efficiency of pressing)
• Player and team rankings according to pressing effectiveness and frequency

Available Data

SkillCorner is providing tracking and dynamic event data for the National Women’s Soccer League (NWSL) in 2025 and the Women’s Super League (FAWSL) in 2024/25. Tracking data is provided at 10 Hz (frames per second). The dynamic event data includes 4 datasets (off-ball-running, on-ball-engagement, player possession, and passing options) that join together as specified in SkillCorner’s Dynamic Event CSV Specifications.

Registered participants will receive instructions for accessing the data through the SkillCorner API, along with the required credentials. Documentation is available with those credentials. The following resources may also be helpful:

• Knowledge Base
  • Quick way to see a glossary of definitions, watch video examples, and get quick answers to questions
  • Tracking data helper links:
    • API: Access Our Tracking Data
    • SkillCorner Tracking Data
• Swagger API Documentation
  • A way to see API endpoints
• Python Client
  • A Pythonic method to call the API
• GitHub
  • SkillCorner’s open-source data offering with tools to visualize and work with their data

Use the data only for the CSAS 2027 Data Challenge. Keep the data and API credentials secure, and do not share or publish the data or any extracts. Reports, presentations, and other outputs must not reveal or allow reconstruction of the data. Any use or communication beyond CSAS 2027 requires SkillCorner’s prior written approval.

Data Challenge Registration

Given the challenge's popularity, we would like to know the number of participating teams to adequately prepare and recruit the necessary judges. Please register for the data challenge by December 15, 2026, at:

Data Challenge Registration Form

This registration is for the data challenge only. Registration for the conference will be available at a later date.

Submission

• Data Challenge Submission Form
• Deadline: January 15, 2027, 11:59 p.m. ET

Students must submit a zip file containing:

• A PDF report describing their results (max 3000 words). Please do not put the author names on the first page (or any page) of the report, just the title. The project will be linked to the name/email address that you used to submit your report. The judges won't see that, only the organizers, so that the judging will be anonymized.
• A folder containing:
  • Documented code files
  • A README file describing what each file does.
  • (Optional) If you used publicly available data that wasn't provided by the data challenge, please include it along with the code you used to obtain it. If those additional data files are too large to be uploaded here, you can upload them into a shared drive (e.g. Google Drive, OneDrive, Dropbox, Box, GitHub LFS), use a link for the shared file in your code, and make note of this in the README file. In other words, include whatever is necessary to make sure that your work is reproducible. Please do not include the data provided in the data challenge. We have that data already!
  • (Optional) Students can include other files (e.g. Shiny app code or other supporting work) as well. Any code or apps included need to be self-contained and able to run on judges' computers without modification. Include these files in your .zip file submission if you have them.

Eligibility

The CSAS Data Challenge is open to students only. You must be enrolled as a high school, undergraduate, or graduate student at some point during the current academic year. Participants must register using their school email address.

Teams must enter one of the following two tracks:

• High School / Undergraduate Track
• Graduate Track

To be eligible for the High School / Undergraduate track, all team members must be high school and/or undergraduate students. Each team can have up to 3 members. The team captain, if 18 years old or older, should fill out the registration form for the entire team using their school email addresses. If all team members are under 18, a faculty advisor needs to be the point of contact and register for the team.

For each team, a team member who is at least 18 years old or the team’s faculty advisor must sign the SkillCorner Data Usage Agreement Addendum on behalf of the team.

Judging Criteria

A panel of judges from across academia and the sports industry will judge your submissions based on the following:

• How original is the analysis?
• How applicable is the analysis?
• How appropriate were the methods used?
• How well did you communicate your findings? This includes both written text and visualizations. How did the use of facts, data-supported narratives, anecdotes, etc. enhance your storytelling?

Papers not chosen as finalists can still be submitted to the poster session.

Prizes

TBD

Data Challenge Information Webinar

Tuesday, November 3, 2026, at 7:00 p.m. ET. The meeting link will be sent to data challenge registrants.

Important Dates

• October 19, 2026: Data challenge released.
• November 3, 2026, 7:00 p.m. ET: Data challenge information webinar. The meeting link will be sent to data challenge registrants.
• December 15, 2026: Data challenge participation registration deadline.
• January 15, 2027: Data challenge submission deadline.
• February 15, 2027: Data challenge finalists notified.
• March 7, 2027: Early-bird conference registration deadline.
• March 22, 2027: Poster abstract submission deadline.
• April 7, 2027: Conference registration deadline.
• April 10, 2027: Data challenge awards and poster awards announcement.