Keeping it Fresh: Predict Restaurant Inspections

Flag public health risks at restaurants by combining Yelp reviews with open city data on past inspections. An algorithmic approach discovers more violations with the same number of inspections. #civic

$5,000 in prizes
aug 2015
604 joined

DrivenDatistas - Here are the datasets used in this competition, for your practice and enjoyment! For more details on the results of the competition, check out our blog post.

Unfortunately we can't field questions about the data, but we wanted to release it openly so that people everywhere could use it. If you have a question, feel free to run it by the community on the forum. Enjoy!

Data for download

All Historical Violations: All of the historical violations for Boston (includes Test + Train from Phase I and more recent violations).

Restaurant ID Mapping: Matches restaurant_id in the violations data to business_id in the Yelp data.

Yelp Restaurant Reviews: This dataset is maintained by Yelp, released at its discretion, and is subject to its data use agreement. At this link, you can download restaurant reviews from Yelp.