Technology That Tracks What You Buy, or Steal

Егемен Қазақстан
28.09.2018 83


Cayce Clifford for The New York Times.Standard Market has cameras that watch shoppers and the items they choose to buy.

SAN FRANCISCO — One recent afternoon, the city’s newest grocery market was trying to figure out whether I would buy, steal or leave behind a bag of white Cheddar popcorn — and so was I.

On its side: 27 cameras and behavioral data. On my side: crippling indecision.

Last month, San Francisco got its first automated cashierless store, Standard Market. Shoppers who have downloaded the store’s app can go into the 176-square-meter space, grab items and leave. There is no check-in gate, and there is no checkout swipe. Cameras identify the shopper and the items, and determine when those items leave with that shopper. Or, that’s the idea.

The start-up behind this is Standard Cognition, begun in 2017. The goal is to add the tech in 100 stores a day by 2020.

Five of the seven founders came from the United States Securities and Exchange Commission, where they built artificial intelligence software to detect fraud and trade violations. Now these experts are working to discern something equally complicated: whether I am stealing a snack.

In January, Amazon opened its first cashierless Go market in Seattle; it has since opened more. In China, experiments in cashierless stores abound.

Standard Cognition’s approach is different. It relies exclusively on the ceiling cameras and artificial intelligence software. It knows if I slowed down, grabbed a chocolate bar and put it back. It knows if my body is facing the dried mangoes but my face is set on the popcorn. And it knows (or is trying to know) when I am planning to steal.

“We learn behaviors of what it looks like to leave,” said Michael Suswal, a founder. “If they’re going to steal, their gait is larger, and they’re looking at the door.” Once the system decides it has detected potential theft behavior, a store attendant will get a text and walk over for “a polite conversation,” Mr. Suswal said.

Predicting theft requires a lot of data about shoppers, much of which does not exist yet. So a few days before Standard Market opened, Standard Cognition hired 100 actors to shop there for four hours. In Japan, the team has worked with a convenience store chain, whose name it has not disclosed, in a data collection effort. Standard Cognition said it did not collect biometric information, a possibility that has troubled privacy experts.

On a recent Friday, I opened my phone, which flashed blue, letting the store know I had entered. I wandered, throwing items into my tote. Then I left.

Outside I found Mr. Suswal. A notification popped up on my phone: one white Cheddar popcorn and one roll of toilet paper for a total of $1.19.

In fact, I had left with two bags of popcorn. I had toyed with the second bag, debated buying it, put it back and finally took it with an impulsive grab. The system missed it.

“That shouldn’t happen,” Mr. Suswal said. And yet it did. He shrugged and said I had won it. So I left with it.

Standard Cognition and others will probably get better at detecting where that snack went. But for now it’s not quite good enough. And I’m covered in crumbs.

Behavioral data and 27 cameras in a cashierless store.

© 2018 New York Times News Service

To read more articles from The New York Times, click here