Creating Safer Streets Through Data Science

Datakind: “Tens of thousands of people are killed or injured in traffic collisions each year. To improve road safety and combat life-threatening crashes, over 25 U.S. cities have adopted Vision Zero, an initiative born in Sweden in the 1990’s that aims to reduce traffic-related deaths and serious injuries to zero. Vision Zero is built upon the belief that crashes are predictable and preventable, though determining what kind of engineering, enforcement and educational interventions are effective can be difficult and costly for cities with limited resources.

While many cities have access to data about where and why serious crashes occur to help pinpoint streets and intersections that are trouble spots, the use of predictive algorithms and advanced statistical methods to determine the effectiveness of different safety initiatives is less widespread. Seeing the potential for data and technology to advance the Vision Zero movement in the U.S., DataKind and Microsoft wondered: How might we support cities to apply data science to reduce traffic fatalities and injuries to zero?
What Happened?Three U.S. cities – New York, Seattle and New Orleans – partnered with DataKind, in the first and largest multi-city, data-driven collaboration of its kind, to support Vision Zero efforts within the U.S. Each city had specific questions that they wished to address related to better understanding the factors contributing to crashes and what types of engineering treatments or enforcement interventions may be most effective in helping each of their local efforts and increase traffic safety for all.

To help the cities answer these questions, DataKind launched its first ever Labs project, led by DataKind data scientists Erin Akred, Michael Dowd, Jackie Weiser and Sina Kashuk. A DataDive was held in Seattle to help support the project. Dozens of volunteers participated in the event and helped fuel the work that was achieved, including volunteers from Microsoft and the University of Washington’s E-Science Institute, as well as many other Seattle data scientists.

The DataKind team also worked closely with local city officials and transportation experts to gain valuable insight and feedback on the project, and access a wide variety of datasets, such as information on past crashes, roadway attributes (e.g. lanes, traffic signals, and sidewalks), land use, demographic data, commuting patterns, parking violations, and existing safety intervention placements.

The cities provided information about their priority issues, expertise on their local environments, access to their data, and feedback on the models and analytic insights.  Microsoft enabled the overall collaboration by providing resources, including expertise in support of the collaborative model, technical approaches, and project goals.

Below are detailed descriptions of the specific local traffic safety questions each city asked, the data science approach and outputs the DataKind team developed, and the outcomes and impacts these analyses are providing each city….(More)”