Desirable Streets: Using Deviations in Pedestrian Trajectories to Measure the Value of the Built Environment.

The experience of walking through a city is infuenced by amenities such as parks and restaurants, as well as the visual qualities of its built environment, such as the beauty of architecture and the liveliness of streets.

In this paper, we use thousands of pedestrian trajectories obtained from GPS signals to construct a desirability index for streets in Boston. We create the index by comparing the actual paths taken by pedestrians with the shortest path between any origin-destination pairs. The index captures the willingness of pedestrians to deviate from their shortest path and provides a scalable measure of the scenic and experience value provided by different parts of the city. This index can be used by scholars and practitioners to identify areas in the city with high potential to attract pedestrians. Conversely, it can also be used to pinpoint areas that have low desirability, but that would be suitable candidates for street improvements. We then use computer vision techniques combined with georeferenced data to measure a diverse set of built environment characteristics that have been shown to affect the pedestrian experience. We show that desirable streets are heterogeneous in terms of geography and are characterized by having better access to parks and sidewalks, more business establishments, and a higher presence of urban furniture. These results further our understanding of the value that the built environment brings to pedestrians, which in turn enhances our capacity to design more lively and desirable environments.



Joint with Zhuangyuan Fan, Fabio Duarte, and Carlo Ratti. Download Working Paper