A big data approach to understanding pedestrian route choice preferences: Evidence from San Francisco

•Some of the key innovations presented in the paper include (a) gathering and mapping route attribute information by computationally processing a large set of Google Street View images, (b) using a novel technique for generating alternative paths for route choice estimation;•and (c) estimating how a range of specific route attributes affect pedestrian route choice from a large number of actual trajectories (i.e., revealed preference) that do not focus on a particular destination type (e.g. walking to transit), but include a wide diversity of destinations and geographies, thereby describing typical pedestrians’ preferences in San Francisco as a whole.•We also show how the findings can be operationalized to describe pedestrian accessibility to different destinations using ‘perceived distance’ as opposed to traversed distance.