Sign up for our newsletter and get the latest big data news and analysis.

Amazon Go – Deep Learning Conquers Retail

Deep learning driven Amazon Go store in downtown Seattle

Seattle is one of my favorite tech-friendly cities and I always look forward to heading out to the Pacific Northwest for a conference. Sometimes I take off on foot from my favorite downtown hotel to take in the feel of the city. Yes, Seattle is that cool. This time, I stumbled upon a real gem – the new Amazon Go store located at 2131 7th Ave., just a few blocks from my hotel. I soon found out this experimental retail outlet is a bold new move to transform retail that’s powered by deep learning technology, specifically image recognition algorithms.

You immediately get a sense for its uniqueness – there are no cashiers or registers anywhere! There’s no need for any. You enter the store through a row of gates resembling a BART station in San Francisco. Only shoppers with the store’s smartphone app are allowed in. Inside, the complement of products are like those of a small bodega. The store itself is only 1,800 square feet.

The shopping experience is simple, you just browse around, place items into a bag and then just walk out. It sort of feels like you’re shoplifting (more on that later). But in reality, your Amazon account automatically gets charged for what you take out the door. The checkout process is completely automated. Every time you take a product from a shelf, one of hundreds of small cameras located in the ceiling recognizes the item and places it in your virtual shopping cart. If you change your mind, no problem, you’re still being watched and the system will remove it from your cart once you put it back on the shelf. The deep learning technology is able to recognize every item in the store without any special tags like RFID chips.

Camera technology on the ceiling of the Amazon Go store

Although just a prototype, this store and accompanying technology is poised to disrupt the retail industry. The Bureau of Labor Statistics reports 3,555,500 cashiers working in the U.S. in 2016. Many of these jobs will be in jeopardy if Amazon’s technology takes hold, although the company plays this down by saying the roles of such employees will simply change. Change or not, once we start to see more deep learning stores like Amazon Go, the discussion of job loss due to AI will ramp up just like what we’re seeing with self-driving vehicles. Pure and simple, AI and deep learning is destined for global disruption of many industries, including retail. Of course, other companies are working on similar problem domains, like Planorama that leverages AI to help its clients boost their retail execution and merchandising. Their solutions incorporate deep learning algorithms that can instantly analyze and recognize millions of product items based on shelf pictures from any source.

And if you think Amazon Go-like stores will be easy to rip off, think again. The company is very aware of the risk for shoplifting in stores with few employees on the floor. One experiment involved a shopper trying to obscure a product with a bag and then slipping it under an arm while walking out the door. Nope! The system still charged the appropriate Amazon account for the item.

It’s unclear how far Amazon intends to take this technology. I’ve visited an Amazon Bookstore in my hometown of Los Angeles, and that seems like a very likely destination for complete automation. Another candidate would be Amazon’s Whole Foods stores. Beyond that, the company could make a killing licensing the technology to other retailers using a cloud business model like AWS. As a data science practitioner myself, I’m continually impressed with all the new applications of AI technology coming out because I know how complex these systems are under the hood. I can just hear all the GPUs humming along while training Amazon’s convolutional neural networks!

Contributed by Daniel D. Gutierrez, Managing Editor and Resident Data Scientist of insideBIGDATA. In addition to being a tech journalist, Daniel also is a practicing data scientist, author, educator and sits on a number of advisory boards for various start-up companies. 

 

Sign up for the free insideBIGDATA newsletter.

Leave a Comment

*

Resource Links: