Photograph by Anna Kuperberg
Join DataKind and Microsoft May 12-13 to help make Seattle’s streets safer!
While Seattle has seen a 30 percent decline in traffic fatalities over the last decade, traffic collisions are still a leading cause of death for Seattle residents age 5-24. DataKind is supporting the City of Seattle’s commitment to Vision Zero by conducting an in-depth pedestrian and bicyclist safety study to inform the Department of Transportation’s efforts to reduce traffic fatalities to zero. To lay the groundwork for this study, we’re rallying data scientists to help do data exploration and modeling that will serve as the foundation for our analysis going forward.
- Flex your data skills and apply by May 8th to join us!
Space is limited so we’ll let you know if you've been selected.
Questions? Check out FAQs below or reach out to us at firstname.lastname@example.org.
What You'll Work On
This DataDive will focus on the Seattle’s Vision Zero traffic safety program. Using Seattle’s collision, roadway and traffic data, participants will conduct exploratory data analyses to kick-off an in-depth pedestrian and bicyclist safety study for the City’s Department of Transportation. Specifically, our objectives for this Seattle Vision Zero DataDive are:
To better understand the relative safety of specific locations in the city for pedestrians and cyclists, we must understand the relationship between crashes and the total volumes of automobiles, pedestrians and bicycles present at specific locations (i.e. exposure). While automobile volumes are the most commonly collected data of this type, coverage is still not complete. Furthermore, bicycle and pedestrian counts are much less common and cover a much smaller number of city streets.
- Your mission? Develop separate estimates of automobile, pedestrian and cyclists volumes with the count data available for each group, coupled with information on the built environment, demographics, road network characteristics and other data for these streets.
Modeling Crash Probability
Understanding what streets and locations are most prone to collisions, and what is the probability of a crash, and what is the probability of a crash at such locations can provide policy makers and engineers with actionable information for developing and implementing interventions. Pedestrian and cyclist crashes at specific locations can be characterized as rare events. Therefore, developing models that can provide the probability of crash, even at locations where a crash has yet to occur, is extremely valuable. This analysis can also provide insights into the locations that are the safest and highlight potential characteristics of these locations that contribute to overall safety.
- Your mission? Use the collision data set, available exposure data (traffic, bike, pedestrian counts), road network characteristics, built environment characteristics, and other datasets to develop models.
Traditional approaches to this problem include Negative Binomial, Poisson, Bayesian and Linear Regression models - participants are encouraged to apply these, and/or other statistical/ML approaches for addressing this problem.
Modeling Influencing Factors for Specific Crash Types
There are different categories of crashes for both pedestrians and cyclists based on how the collisions occurred. Examples of such types include: Right turn, left turn, head on, and rear end collisions. Understanding the contributing factors and predictive variables associated with these specific crash types can elucidate specific interventions that could be implemented to reduce the number of such collisions. Furthermore, similar to the objective above, this work can highlight specific locations where specific crash types are more prevalent.
- Your mission? Using the collision data set, available exposure data (traffic, bike, pedestrian counts), road network characteristics, built environment characteristics, and other datasets to develop models.
What's a DataDive?
DataDives are marathon-style events where teams of volunteer data scientists help organizations do initial data analysis, exploration, and prototyping.
Who would I get to work with?
For this DataDive, you will get to work with a selected group of socially conscious quantitative experts from Microsoft, University of Washington and DataKind Labs that will prep the data, scope the work, and make sure each team crosses the finish line.
Ready? Set? Go! What’s the agenda?
- Thursday 5/12 6pm - 8pm: discuss goals for the DataDive and dive into the data!
- Friday 5/13 8am - 8pm: three rounds of data exploration and a modeling session
Who is DataKind? How is Microsoft involved?
We are a nonprofit dedicated to harnessing the power of data science in the service of humanity. Since August, we’ve been working with Microsoft and its Tech & Civic Engagement Group to support the Vision Zero movement in the U.S., reducing traffic-related deaths and severe injuries to zero in Vision Zero Cities nationwide. After kicking off a long-term data science project with the city of New York, we recently expanded our work to three new cities - San José, New Orleans, and Seattle. This DataDive officially kicks off our work in Seattle so you are helping to pave the way (yes pun intended) for our future efforts.