Subscribe to DSC Newsletter

Contributed by David Richard Steinmetz. He enrolled in the NYC Data Science Academy 12-week full time Data Science Bootcamp program taking place between July 5th to September 23rd, 2016. This post is based on their second project - R Shiny, due on 4th week of the program. The original article can be found here.

Automated driving is coming, and it will affect you

Google, Tesla, and other automakers such as BMW, Daimler-Mercedes, and General Motors are all presenting visions of a future where most or all of the responsibilities and tasks of driving are no longer yours. A big benefit of automated driving will be an anticipated reduction in fatal motor vehicle accidents. On the other side of the coin, the millions of people who work in transportation-related industries could be affected by the shift to autonomous driving. The Shiny app discussed in this article will help you explore how automated driving could affect you. The data is from 2014 and comes from the NHTSA and BLS. It can be found here and here.

How a reduction in fatal accidents would affect you is dependent on where you live

Death due to unintentional injuries, a subset of which is motor vehicle accidents, is among the leading causes of death in the United States. The distribution amongst states is unequal, with the most by far occurring in Texas and California, with Florida not far behind. This might not be surprising given the populations of those three states, but if the absolute number of accidents were lowered by autonomous driving, these states have the potential to feel the greatest relief. The 'Number of Accidents' tab in the app allows you to explore the absolute number of fatal accidents per state.

A high number of accidents does not necessarily mean a high accident rate per resident

When the absolute number of accidents from the previous section is adjusted for population, it becomes apparent that low absolute number of accidents is a good thing, but do not mean a low rate of accidents per resident. It is particularly interesting to see that California has a high absolute number of accidents to is on the low end of the rate of accidents per 100,000 people. This contrasts starkly to Wyoming, which had far fewer numbers of fatal accidents, but has the highest accident rate. Of interest is New Jersey, which has a low number of fatal accidents and low accident rate, while having the highest population density in the nation.

Streets such as Colfax Ave. in Denver show a trend of fatal accidents

By using the app to explore your area, you may uncover places or streets with quite a few fatal accidents. One such road is Colfax Ave. in Denver, Colorado. It is depicted in the image above and had ten fatal accidents along it in 2014 alone. Other such locales of interest are Eisenhower Expressway in Chicago and the Long Beach Freeway in Los Angeles. Use the interactive map on the 'Accident Locations' tab to investigate these locales and the area near you.

Go out early, but not too early! And best while everyone is working

When viewing a bar chart of the number of fatal accidents by time of day, one thing becomes clear: go out early! But not too early. The number of accidents declines from midnight to 4am, increases during the morning rush hour until another local minimum at 9am, and then increases throughout the day until the dinnertime lull at 6pm. So avoid rush hour if you can, and get your shopping done when the stores open in the morning. A bar chart for the number of accidents by days of the week shows a similar trend: fewer fatal accidents occur during Monday to Thursday. The number 1 on the graph represents Sunday.

States with a high percentage of transportation jobs per resident but not a high rate of accidents might lose out

States like North Dakota, which have a relatively low fatal accident rate but has a high rate of transportation-related jobs might benefit least from a shift to automated driving. The number of transportation jobs and jobs per 100 people per state can be viewed in 'Transportation Data' tab of the app.

Transportation and warehousing is the top transportation-related job category in many states

One particular fact that jumps out of the transportation jobs data is that the category of 'Transportation and Warehousing' is at the top of the list of transportation jobs for many states, including those shown here. California and Texas alone have over 3M jobs in this sector which could be affected not only by autonomous driving but by the automation of warehouses, storage facilities, and industrial production. These kinds of numbers will demand action from society as a whole, which is why even if you don't drive, automated driving will still affect you.

Takeaway

Automated driving is likely to affect you or those you know either through a reduction in fatal traffic accidents or a shift in jobs in the transportation industry. A Shiny app helps you to explore how these factors might affect the areas where you live and work and find answers for yourself.

You can find the code for the app on Github

Click here to see the code.  

Views: 266

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Antonis Hontzeas on January 14, 2018 at 10:25am

Very nice article. Of course if something goes wrong we may be dealing with accidents of catastrophic proportions. Regardless, I wouldn't invest in downtown parking lots in the long term.

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service