WiDS Datathon Resources

Tutorials, sample code, and other resources will be posted here throughout the competition

Medical history prediction: Predicting diabetes from ICU admission data

WiDS Datathon webinar fireside chat
We will examine a baseline classification model for diabetes prediction created from the datathon dataset using AutoML that chose SparseNormalizer, XGBoostClassifier (and Monte Carlo cross validation) and consult with a physician and endocrinologist on how to improve the model.
Watch the recording

A beginner's guide to the WiDS Datathon 2021 challenge

by Sharada Kalanidhi, is Co-Chair of the WiDS Datathon Committee
This year’s WiDS Datathon challenge focuses on predicting a type of diabetes, Diabetes Mellitus, based on data collected during the first 24 hours of admission to an intensive care unit. We will try to model this very real medical problem using the best machine learning tools we have at our disposal.  I will help you with the basic steps of data set preparation and model fitting.
Read the tutorial

Getting Started with Kaggle - WiDS 2021 Datathon Videos

by Usha Rengaraju, Kaggle 2x Grandmaster
Video 1: Getting Started with Kaggle - an introduction on how to get started with Kaggle and how to navigate WiDS Datathon 2021 competition page
Video 2: Diabetes Prediction for ICU Patients - a baseline notebook walkthrough of WiDS Datathon 2021 challenge

MATLAB Benchmark Code for WiDS Datathon 2021

by Neha Goel, Technical Lead for AI/Data Science competitions at Mathworks
This dataset presents an opportunity to learn about the data modeling and processing challenges a real-world data problem brings. In this blog, I will talk about some basic methods to handle data challenges. To learn some more methods you can go through this Data Science Tutorial video series.
Read the tutorial

Deep Dive Discussion: A Data Scientist's Perspective on the WiDS Datathon

by Sharada Kalanidhi, WiDS Datathon Co-Chair
This dataset presents an opportunity to learn about interesting and real-world modeling challenges, and is different from other curated datasets in textbooks and classic machine learning exercises.  For that reason, I discuss some of the challenges you may experience around missing data, multicollinearity and linear/ nonlinear approaches. I will also provide resources to help you on these topics.
​Read the discussion