WiDS Cambridge Datathon 2020


The WiDS Cambridge Datathon Workshop is an annual workshop preceding the WiDS Cambridge Conference. The workshop aims to provide mentorship and training for those interested in participating in the WiDS Datathon Challenge, and, more generally, anyone with a strong interest in data science.

View the Project on GitHub onefishy/wids_datathon_2020

General Information

Who is organizing the workshop?

This year’s workshop is organized by:

  1. Weiwei Pan (Harvard IACS)
  2. Karren Dai Yang (MIT IDSS)

What will you do at the workshop?

The WiDS Datathon workshop consists of a data science/machine learning tutorial followed by a team-based practical session focused on a single data science task. In this workshop:

  1. you will be introduced to data science/machine learning concepts and methods (especially relevant to the WiDS Datathon Challenge)
  2. you will be able to form teams during the workshop and get hands-on experience implementing machine learning models and working with the WiDS Datathon dataset
  3. you will receive mentoring from data scientists and machine learning researchers from universities and tech companies in the Boston area.

Who should sign up for the workshop?

We invite all participants with a strong interest in data science!

Programming experience as well as some previous training in probability, statistics and mathematics is helpful. But we welcome participants from all backgrounds!

Where is the workshop located?

The workshop will be held at:

      1 Memorial Drive
      Floor M
      Cambridge, MA 02142

How do I get there?

Parking information: The One Memorial Drive parking garage is in the NERD Center building and is open to the public. This garage is privately owned, and Microsoft is unable to validate parking. The daily maximum rate is $37.00. ​ Public Transportation: The NERD Center is a .3 mile walk from the Kendall/MIT red line stop and a .4 mile walk from several bus lines.

What should you bring to the workshop?

You will need to bring a laptop.

You must bring a government or school issued ID and check-in at the Microsoft front desk at the main entrance. You will then be directed to floor M.

Workshop Schedule

08:00am - 9:00am Breakfast & Check-in
09:00am - 9:10am Welcome
09:10am - 10:30am Introduction to Data Exploration & Classification
10:30am - 10:40am Coffee Break
10:40am - 12:00pm Introduction to Neural Network Models & Ensemble Methods
12:00pm - 01:00pm Lunch & Team-formation
01:00pm - 04:30pm Datathon
04:30pm - 05:00pm Report from Teams

Preparing for the Workshop

Create a Kaggle Account

  1. Navigate to www.kaggle.com
  2. Follow instructions to create an account

Familiarize Yourself with colab and python

  1. Open the Basic Features Overview Notebook in colab.
  2. Read about the two different types of cells (code and text) in a colab notebook.
  3. Make sure you know how to ‘run’ or ‘render’ a cell.
  4. Find quick primers on python here.

The WiDS Cambridge Datathon Workshop is generously sponsored by Microsoft NERD.

msft logo