Skip to main content
WiDS News | January 12, 2020

The WiDS Datathon 2020 is Now Live, Encouraging Women Worldwide to Hone Their Data Science Skills

The 3rd Annual Women in Data Science (WiDS) Datathon competition is now open on Kaggle, and the competition has begun!

The dataset
The WiDS Datathon 2020 challenge is to create a model that uses data from the first 24 hours of intensive care to predict patient survival. MIT’s GOSSIS community initiative, with privacy certification from the Harvard Privacy Lab, has provided a dataset of more than 130,000 hospital Intensive Care Unit (ICU) visits from patients, spanning a one-year timeframe. This data is part of a growing global effort and consortium spanning Argentina, Australia, New Zealand, Sri Lanka, Brazil, and more than 200 hospitals in the United States.

The datathon winners will be announced at the Women in Data Science (WiDS) conference at Stanford University on March 2, 2020.

Dr. Marzyeh Ghassemi, an assistant professor at the University of Toronto who works with MIT’s GOSSIS team, collaborated with us to provide this year’s dataset. She addresses important topics in machine learning for health, including how algorithms could be used to audit and eradicate bias in healthcare data, on a recent installment of the WiDS Podcast. This topic inspired this year’s datathon, which uses global healthcare data.


“WiDS brings together some of the best and most creative data scientists in the world,” said Karen Matthys, Stanford ICME Executive Director, External Partners and Co-Director of the WiDS Conference. “This year the datathon participants are seeking patterns and insights in ICU data to find ways to reduce ICU deaths. There are approximately 500,000 ICU deaths annually in the U.S. alone. Our data scientists will race each other and the clock to find the biggest insights and solutions.”

You can read more about this year’s dataset on Kaggle.

Worldwide datathon participation
The WiDS Datathon, which requires that teams are comprised of at least 50% women, brings people together teams across borders and backgrounds to successfully submit their results. Worldwide participation in the datathon is encouraged, with participants from previous competitions coming from dozens of countries across six continents. WiDS Datathon 2019 participants included a mother-daughter team, which also spanned the UK & Spain; a team with members in Sweden and Nigeria; and teams from LaPaz, Bolivia who met weekly to create new submissions.

The WiDS Datathon focuses on encouraging women to hone their data science skills through a predictive analytics challenge focused on social impact. Kaggle, the leading platform for data science competitions, reports that more than 80 percent of its participants are men, based upon user survey results. Given the open and global nature of the platform, Kaggle is the perfect platform for inclusive participation.

“The WiDS Datathon always focuses on topics with significant social benefit,” said Matthys. “We have a lot of optimism that machine learning can help reduce ICU deaths. New predictive models for ICU deaths have been published recently, giving us hope that we can capitalize on recent successes.”

We invite anyone, from those new to data science to veterans of the field, to participate. Tutorials will be available for people who are new to data science and machine learning, and workshops will be hosted by select WiDS ambassadors worldwide.

To begin competing in the WiDS Datathon 2020:

1. If you haven’t yet, please register now for the datathon. At the end of your registration you will be provided a link to the competition on Kaggle

2. Create your account on and read through the datathon details and FAQ

3. Form a team with new collaborators! Connect with potential teammates on the Kaggle forums, at an in-person team formation or datathon-focused event hosted by WiDS Ambassadors, and through social media with #WiDSDatathon.

4. Join the WiDS Datathon mailing list to make sure you receive news, announcements, and datathon tutorials.

We look forward to seeing your entries!