DrivenData blog

Explore the latest in our mission to build a better world using data science and AI.

Content list

insights

A brief introduction to machine learning and 3 ways to make it useful for social impact organizations

When social sector organizations think about data, the conversation often begins and ends with measuring impact. Here are some ways that social impact organizations can move beyond thinking about measuring impact and start using machine learning to transform how they operate.

winners

Meet the winners of the N+1 Fish, N+2 Fish challenge

See how DrivenData's top modelers managed to predict length, species, and count from videos of fish captured on fishing vessels.

tutorial

Benchmark for Pover-T Test - Predicting Poverty

We're launching a new competition to predict poverty. In this post, we'll show you how to get started!

community

Bridging the AI application gap

The focus of the Concept to Clinic challenge is to make AI advances useful — not just for data scientists interested in cutting-edge methods, but for clinicians working on the front lines of lung cancer detection and the patients they serve.

community

Interview with Concept to Clinic panelist Dr. Jason Hostetter

We interview Concept to Clinic panelist Dr. Jason Hostetter

community

Interview with Concept to Clinic contributor Serhiy Shekhovtsov (@Serhiy-Shekhovtsov)

We interview Concept to Clinic challenge contributor Serhiy Shekhovtsov (@Serhiy-Shekhovtsov)

competition

Hidden Signals Challenge: can you help identify biothreats in real time?

Can you help identify biothreats in real time? Submit a concept by 12/4/17!

tutorial

Pri-matrix Factorization - Benchmark

How about some deep learning to identify wild animals in camera traps? Here's a benchmark post to get contributors started in our newest challenge.

tools

How the Concept to Clinic challenge uses Docker for reproducibility and orchestration

Ensuring easy setup of the application stack and efficient segmentation of the various components of the Concept to Clinic challenge is precisely where Docker excels, especially when used with Docker Compose, its tool for declaring and orchestrating multiple services. In this post, we'll dive into some background on Docker and explain how we're using it in the Concept to Clinic challenge.

community

Interview with Concept to Clinic contributor Willi Gierke (@WGierke)

We had an e-chat to learn more about prolific Concept to Clinic challenge contributor Willi Gierke (@WGierke)

winners

Random walk of the penguins

The goal of this data science competition was to reach out to the data science community to build a model that predicts penguin populations.

competition

Now live: a new kind of data challenge

Just this week we launched a new $100,000 challenge where competition-tested algorithms are just the beginning.

tutorial

Random Walk of the Penguins - Benchmark

Penguins are so adorable! Here's our first pass at predicting penguin populations in Antarctica.

tutorial

DengAI: Predicting Disease Spread - Benchmark

We're launching a new competition to forecast the spread of dengue.

insights

Why Elections Are a Terrible Showcase for Data Science

The 2016 election was a bad showcase for the powers of data science.

winners

Trying to Get It Right when Everyone was Wrong

The best we can do with the polls.

tutorial

America's Next Top (Statistical) Model - Benchmark

We're launching a new competition for forecasting the 2016 presidential election.

winners

Meet the winners of the safe aging challenge

See how DrivenData's Top Modelers managed to predict activities from sensor data

media

SciPy 2016: "Data Science is Software" tutorial

Video footage of Peter and Isaac from their pilgrimage to SciPy 2016

winners

Visualizing a Future for Fog Nets

Meet the folks who used their data visualization and modeling skills to help Dar Si Hamd!

tutorial

There's no place like $HOME

We're launching a new competition for safe aging at home generously sponsored by AARP Foundation

winners

Building the best naïve bees classifier!

These are the people who were best able to distinguish honeybees from bumblebees and how they did it.

Stay updated

Join our newsletter or follow us for the latest on our social impact projects, data science competitions and open source work.

There was a problem. Please try again.
Subscribe successful!
Protected by reCAPTCHA. The Google Privacy Policy and Terms of Service apply.

Work with us to build a better world

Learn more about how our team is bringing the transformative power of data science and AI to organizations tackling the world's biggest challenges.