Archana Kumar
Luis Daniel Palacios Morton

De-anonymizing Stop And Frisk Data

Using the stop and frisk data set, this project attempts to de-anonymize the data to find individuals that have been stopped/frisked multiple times and tell their story.

Data Representation,Data Without Borders: Data Science in the Service of Humanity

Back in the mid-90\'s, Latanya Sweeney was able to find and send, then Governor of Massachusetts, WIlliam Weld\'s medical records to his home address by de-anonymizing publicly available medical records. Sweeney showed that 87% of Americans could be identified by only knowing their zip code, DOB, and sex. The stop and frisk data released by the NYPD (thanks to the NYCLU) not only contains location, DOB, and sex, but also race, eye color, hair color, height, weight, and build. This projects attempts to find the people who have been stopped and/or frisked multiple times and tries to tell their story. Where they arrested? Where they frisked every time? Did the stops occur over the course of 2011 or in a single month? Are they really bad apples and need to be constantly stopped and frisked? The goal is not to identify people and give them a name, but to bring their real-life stories to light in the form of a comic.