The seventh Ottawa Hockey Analytics Conference (#OTTHAC 2022) running March 25 and 26, 2022 kicked off the second iteration of the Big Data Cup, #BDC2022.  BDC2022 is powered by Stathletes and sponsored by CANSSI, Stathletes, Rotman School at the University of Toronto, Carleton University, and St. Lawrence University. It is a datathon focusing on hockey data. The focus this year will be on analyses of Special Teams play.

The data sets available for use have been crafted specifically for the Big Data Cup. They are not in original format but are intended to be a small portion of Stathletes’ data that is translated for public consumption. They focus on two key areas of the game that have grown in prominence over the past year:

1. Women’s hockey play by play: (2018 and 2022 Women’s Hockey Tournament sample and NCAA games)  Interest in women’s sports has increased during the pandemic. By providing access to data about the game played at its highest level, we hope participants work with this robust data set from international tournaments.
2. Tracking Data: (2022 Women’s Hockey Tournament sample)  Player tracking is being introduced across many professional sports leagues. Tracking data generated from the broadcast camera is an easy way to develop advanced statistics for leagues that may have fewer resources.

Access the data here.

NOTE: As noted on the legal agreement, this data cannot be resold and is intended to be used for research purposes only.

Up for grabs is $10K in prize money and swag from NHL teams. There will be two categories for participants:

1. High school/college/undergraduate—all participants must provide proof of enrollment at high school, college, or undergraduate level.
2. Open—This category includes graduate students and anyone interested in hockey research.

Teams can be 1–4 participants. To enter this datathon you must REGISTER.

2022 Timeline and Key Dates

Participation in Big Data Cup 2022 competition is open to any individual regardless of background, experience, previous analysis, or public work. You must REGISTER for the datathon.

• March—Data is released: GitHub link
• April/May—Open office hours

We want to foster each participant’s ability to both evaluate data from a process and a technical perspective. To assist with this, we will be scheduling office hours for the Big Data Cup (specific times to be announced in April). Subject matter experts in both sport and analysis will be available to answer your questions and provide feedback. Check https://www.stathletes.com/big-data-cup/ for further details and updates and follow @meghanchayka on Twitter for details on ways to sign up. Anyone interested is encouraged to apply and data will be provided publicly to advance hockey research.

• May 15—Big Data Cup submissions due
• Week of May 30—Finalists announced
• Weekend of June 11/12—Winners in each category announced (Two winners per category) at BDC2022
  • Women’s hockey
  • High school/college/undergraduate
  • Open

Finalists will be selected* the week of May 30 and will have the opportunity to present their findings to our panel of NHL executives. Prizes will be awarded to top qualifiers.

*Evaluation criteria includes but is not limited to the following: a demonstrated ability to creating actionable insights for a general manager or head coach working in hockey and not just research; generating creative ideas, which may mean borrowing and applying ideas from other sports, leveraging domain knowledge, and/or filling gaps created by limitations of public data; a performative understanding of how to work with large data sets.