Solving Cities

MIT scientifically defines 'curb appeal' using Google Street View

MIT scientifically defines 'curb appeal' using Google Street View

Posting in Cities

The Place Pulse project uses big data, massive number crunching and the power of 100,000 snap human judgements to figure out what, exactly, makes a place appealing

Place Pulse is a project from the MIT Media Lab that is trying to quantify, through artificial intelligence and massive data crunching, what it is about the look of a particular neighborhood that makes it appear to be safe, unique or "upper class."

The site shows visitors two images from Google Street view, then asks them to make a pairwise comparison between them. Later, artificial intelligence helps identify what's common to the images that appear to be more or less safe, unique or classy.

Ultimately, the results of this study could be used to help city planners, real estate agents, architects and homeowners figure out what makes a place appealing. The technology is also designed to be extended to answer almost any question that could be asked about a streetscape.

From the Place Pulse homepage:

Inside your mind, subconscious judgements about your surroundings are made in real time. Do you feel safe? Does the area you are in seem unique? Does it appear wealthy, clean or even energetic? You may not think about, let alone understand, what goes into making these anecdotal determinations, but when elicited, your opinions can be understood as part of a more substantial collective and used in powerful ways.

Share this

Christopher Mims

Contributing Editor

Contributing Editor Christopher Mims has written for Scientific American, WIRED, Popular Science, Fast Company, Good, Discover, Slate, Technology Review, Nature and the Nicholas Institute for Environmental Policy Solutions at Duke University. Formerly, he was an editor at Scientific American, Grist and Seed. He is based in Washington, D.C. Follow him on Twitter. Disclosure