Blog

From raw Yelp reviews to a model of hygiene violations (in 3 easy steps)

We were so excited about our new civic innovation competition we couldn't help but get started ourselves! The goal for this competition is to use data from Yelp restaurant reviews to narrow the search for health code violations in Boston. Competitors will have access to historical hygiene violation records from the City of Boston — a leader in open government data — and Yelp's consumer reviews. The challenge: Figure out the words, phrases, ratings, and patterns that predict violations, and help public health inspectors do their job better.

Read More →

Help cities keep it fresh

Can you use the patterns, words, and phrases in Yelp reviews of restaurants to predict the number of hygeine violations that city health inspectors uncover?

Read More →

The Countable Care competition heats up

We're now about 2 weeks into the "Countable Care: Modeling Women's Health Care Decisions" competition, and things are heating up!

Read More →

An interview with "Box Plots for Education" winner Quoc Le

We recently got a chance to pick the brain of Quoc Le, our Box-Plots for Education 1st place finisher. He answered some of our questions about himself, the competition, and data science in general.

Read More →

Press coverage of "Box-Plots" results

The Boston tech press covers the successful completion of the ERS "Box-Plots for Education" challenge. Check out the article!

Read More →

Announcing beta testing of our new user forum

We're excited to announce the beta testing launch of our shiny new user forum!

Read More →

DrivenData in the news!

It's an exciting time for DrivenData. We've partnered with Education Resource Strategies to launch our first competition with a cash prize. We also got some nice press coverage. Check out the article in BostInno!

Read More →

Getting started with the Millennium Development Goals challenge

People have been a little reticent to start digging in to the Millenium Development Goals challenge. We thought a little sample code might help get things started. Here's an IPython notebook that should get get you from zero to submission in a few minutes.

Read More →

Introducing DrivenData

As we begin launching our first competitions, we thought it would be a good idea to lay out what exactly we're trying to do and why.

If your goal is to change the future, it helps to have really good predictions about what that future looks like.

And there are a lot of people interested in changing the future. Amazon wants to increase the number of goods you order through their site, so they predict which ones you might want to buy next and when. Twitter wants to boost your use of their platform, so they predict which tweets you will ignore and which you will engage with. Facebook and Google want to increase the number of ads you click …

Read More →

Beta launch!

Today we're excited to launch our beta testing phase, thanks for visiting us as we sand some rough edges in preparation for big things to come.

We're happy to present the first friendly competition, a really interesting data science problem based on data from the World Bank.

Feel free to sign up for an account and dig in!

Read More →