Big Data Brings Bespoke Cities

This start-up uses an AI to comb through Google Street View images, matching users with cities that fit their "lifestyle preferences."
February 12, 2017, 9am PST | Philip Rojc | @PhilipRojc
Share Tweet LinkedIn Email Comments
Scanrail1

Big data and machine learning have a tendency to serve up the awesome and the unsettling on a single platter. Here, Dave Gershgorn writes about Teleport, a big data startup with a means "to automatically look around cities and see if people will like them based on their lifestyle preferences."

The process goes like this: "First, [Teleport] plots 10,000 randomized points throughout a city, and grabs images taken by Google Street View. Then those images are run through computer-vision algorithms that identify objects, people, and buildings, and describes them in a short sentence. Words are a lot easier to search than images, and the final step is calculating which phrases or words are most common."

The tool takes its inspiration from MIT's StreetScore, which uses Street View to gauge street safety.

Full Story:
Published on Wednesday, February 8, 2017 in Quartz
Share Tweet LinkedIn Email