Predicting E. Coli levels in Chicago beaches

« back to Projects & successes

Predicting E. Coli levels in Chicago beaches

Chicago has three-dozen beaches that, sometimes, have high E. Coli levels. When do we need to warn the 9 million annual visitors of potentially high E. Coli levels? In 2016, members of Chi Hack Night built an improved statistical model to predict the E. coli levels at Chicago’s beaches.

Built entirely by a team of volunteers from Chicago’s civic tech community, this predictive model was officially adopted by the City of Chicago in May 2016 to help the Park District know when they should issue warnings to swimmers of potentially high levels of bacteria.

This project is followed the successful launch of Is There Sewage in the Chicago River, another Chi Hack Night project.

Rebecca Jones, gave a lightning talk at Chi Hack Night after the project was completed. Watch her talk, Predicting E. Coli Exceedances on Chicago Beaches:

Interview with a project leader

Tom Schenk

Project leader
Tom Schenk
Chief Data Officer for Chicago

How did you come up with the idea for this project?

Members of the public brought-up the seemly low performance of a federal/academic model to predict E. Coli levels. After some preliminary analysis , this turned-out to be true, but was also clear there was opportunity for improvement. Since the data was public, volunteer data scientists could tackle this project to help the city and visitors to Chicago’s beaches.

How did Chi Hack Night help?

Volunteers at Chi Hack Night tackled this project on a weekly basis. From November 2015 through May 2016, a half-dozen to a dozen volunteers worked on the project during Hack Night, nights, and weekends. The project’s weekly meeting notes show the dedicated work from the team.

What was the impact of your project?

Volunteers were able to develop a new analytical model that outperformed the existing model. As a result, during the summer of 2017, the new analytical model will be used to determine which beaches may have elevated E. Coli levels.

As part of the project, my team developed a small application to collect E. Coli test results, which is now available on the open data portal. This product provides the impetus of developing a better way to provide lab data to the public.

What did you learn from this project?

E. Coli is really hard to predict.

More on this project

Taking Predictive Analytics to the Beach, Sean Thornton

Lightning Talk: Predicting E. Coli Exceedances on Chicago Beaches, Rebecca Jones (video)

Tags Predictive modeling
City partnership
Creators Tom Schenk
Kevin Rose
Rebecca Jones
Matt Sweeney
Chris Prokop
Melissa McNeill
And many more
GitHub https://github.com/Chicago/e-coli-beach-predictions
Launched May 2016