Amazon has built a massive warehoapplying footprint around the counattempt, including this Inside an Amazon fulfillment center in Baltimore. And it’s been adding compacter warehoutilizes closer to city centers where Prime Now promotes super-quick delivery options.
Claire Harbage/NPR
hide caption
toggle caption
Claire Harbage/NPR
Amazon has built a massive warehoapplying footprint around the counattempt, including this Inside an Amazon fulfillment center in Baltimore. And it’s been adding compacter warehoutilizes closer to city centers where Prime Now promotes super-quick delivery options.
Claire Harbage/NPR
By the time someone clicks “acquire” on Amazon, Jenny Freshwater’s team has probably expected it.
Freshwater is a software director in Amazon’s Supply Chain Optimization Technologies group. Her team forecasts demand for everything sold by Amazon worldwide.
This tinquire, into which NPR received exclusive insight, underlies the entire Amazon retail operation. And it’s central to Amazon’s wooing of some 100 million people who shell out up to $119 a year for a Prime subscription, which guarantees two-day shipping.
Inside Amazon, corporate executives like to evoke magic when they talk about quick delivery. For months, they utilized the code name Houdini before launching their quickest service, Prime Now, which delivers houtilizehold basics within hours.
But a lot of it is thanks to artificial ininformigence. With AI, computers analyze reams of data, creating decisions and performing tinquires that typically require human ininformigence. AI is key to Amazon’s retail forecasting on steroids and its push to shave off minutes and seconds in the rush to prepare, pack and deliver.
“It goes beyond just being able to forecast we necessary a hundred bloutilizes,” Freshwater states. “We necessary to be able to determine how many do we expect our customers to acquire across the sizes, and the colors. And then … where do we actually put the product so that our customers can receive it when they click ‘acquire.’ “
That’s a key element to how Amazon speeds up deliveries: The team predicts exactly where those bloutilizes should be stocked so that they are as close as possible to the people who will acquire them.
(Note: Amazon is one of NPR’s financial supporters.)
This process is even more essential now that the race is on for same-day and even same-hour delivery. Few other retailers have ventured into these speeds, becautilize they’re very expensive. And few rely quite so much on AI to control costs while expanding.
Amazon boxes are scanned on conveyor belts. AI systems keep track of all items in the warehoutilizes, which can be as vast as 1 million square feet.
Claire Harbage/NPR
hide caption
toggle caption
Claire Harbage/NPR
Amazon boxes are scanned on conveyor belts. AI systems keep track of all items in the warehoutilizes, which can be as vast as 1 million square feet.
Claire Harbage/NPR
Both AI and forecasting are not unique to Amazon. All retail stores work hard to prepare, for example, for seasonal or weather-related demand. And all major retail companies have their own algorithms, automated warehoutilizes and delivery tricks.
But it was Amazon Prime that received Americans hooked on two-day shipping, which shoppers now take for granted. Walmart, Tarreceive and many others now offer two-day deliveries even without membership fees.
While all large online retailers rely on AI, “Amazon definitely has the most powerful tools for all the little computational processes involved in relocating the packages through many suppliers, routes of transit and all the steps that a package goes through,” states Mike Liebhold, a senior tech researcher at the Institute for the Future.
Indeed, AI is woven through every part of an Amazon purchase, from the website to the warehoutilizes to the actual delivery to your doorstep. In corporate lingo, Amazon calls that the “first mile,” “middle mile” and “last mile.”
Forecasting for the “first mile”
In 2013, Amazon received a patent for so-called “anticipatory shipping.” The idea was to receive your order as close as possible to your address before you actually click acquire.
Since then, Amazon has built a massive warehoapplying footprint around the counattempt. And it’s been adding compacter warehoutilizes closer to city centers where Prime Now promotes super-quick delivery options. It’s also applying Whole Foods locations for quicker access to groceries and basic pickups.
Amazon regularly tests what new products people might want with extra-quick shipping, states Cem Sibay, who runs Amazon Prime in North America. “If you see customers consistently attempting to select for same-day delivery, then the next step is obviously that some customers maybe actually even necessary this quicker,” he states.
An employee works on an order in Amazon’s fulfillment center in Baltimore. Amazon’s forecasting team works on anticipating demand for everything sold by the company worldwide.
Claire Harbage/NPR
hide caption
toggle caption
Claire Harbage/NPR
An employee works on an order in Amazon’s fulfillment center in Baltimore. Amazon’s forecasting team works on anticipating demand for everything sold by the company worldwide.
Claire Harbage/NPR
Amazon decides what to stock by viewing at every detail of each product. It takes a shirt and analyzes the color, length, silhouette, sleeve length and histories of purchases for similar clothing items. Freshwater, of Amazon’s forecasting team, states her group does not have access to personally identifiable information on specific shoppers. But her team views at past demand and online-shopping habits in aggregate to write algorithms and statistical models that teach the AI.
Some of Amazon’s predictions are not surprising. “You don’t sell very much Chicago Cubs gear in Hawaii,” Freshwater states.
Others are less obvious. For example, AI has learned that not all new products mean the same type of forecast.
Take tax software. Everyone wants the latest version. But the release of a new DSLR camera? That actually triggers huge demand for the older versions, which are cheaper.
AI has also determined that online shoppers often abandon their online grocery cart entirely, if bananas are sold out — and that bananas are most in demand on Mondays.
Or consider sunscreen. It’s obviously in demand in the summer, but Amazon’s AI models have also detected mini-surges around winter holidays and spring breaks — when people go on trips to warm sunny places.
Whether you search on Amazon.com or shop applying Alexa on the Echo device, AI determines what results or recommfinishations you see and informs you how quick you might receive each item.
The “middle mile”
Inside Amazon’s warehoutilizes, AI powers the Kiva robots, which view like large Roombas carrying bright yellow shelves.
Kiva robots relocate racks of merchandise at an Amazon fulfillment center in Tracy, Calif., in 2015. The machines bring the shelves to workers.
Justin Sullivan/Getty Images
hide caption
toggle caption
Justin Sullivan/Getty Images
Kiva robots relocate racks of merchandise at an Amazon fulfillment center in Tracy, Calif., in 2015. The machines bring the shelves to workers.
Justin Sullivan/Getty Images
In traditional warehoutilizes, it’s the people who walk to the shelves. But in most Amazon warehoutilizes, the robots bring the shelves to people.
The machines know what to bring and when to receive orders packed so they are in time for delivery. AI systems keep track of all items in the warehoutilizes, which can be as vast as 1 million square feet. AI constantly arranges and reshuffles the shelves so that things you’re about to acquire are ready to go.
Amazon is now rolling out new efficiency-boosting technology that eliminates the necessary for handheld scanners, states Brad Porter, head of robotics for Amazon Operations. The new system retrofits workers’ stations with advanced cameras that can automatically scan items that workers hold in their hands. AI is learning to discern and interpret people’s hand relocatements to recognize when a person places an item inside a shelf slot.
This kind of innovation is a controversial topic in retail, where layoffs are rampant, just as automation is reshaping the workforce. Economic research is divided on how much exactly AI will eliminate or create jobs, especially for lower-income Americans.
For example, Amazon has been hiring people by the hundreds of thousands for its highly automated warehoutilizes. Its workforce has ballooned to 613,300 in a matter of a few years. Warehoapplying overall has been one of the quickest-growing industries, even though a lot of that work is part-time or temporary.
At the same time, Amazon has launched AI-powered stores that eliminate the necessary for a cashier, stoking fears about the future of jobs like these indusattempt-wide. Plus, as Porter will point out, scientists have long been working on robots that can imitate human hands with their grip. For work like packing in warehoutilizes, an agile robotic hand could erase one key edge that human workers now have over machines.
To Porter, modern automation is simply in the latest chapter of industrial progress.
“Industrial automation and robotics are here. They’ve been here for a long time,” Porter states. “I believe what’s novel or hard in the logistics space and for Amazon is just the diversity and selection of inventory that we have and the scale at which we’re doing it. And so yeah, I believe we’ll continue to see technology innovation in all these spaces.”
The “last mile”
One area where AI has created a new type of job is in deliveries.
The exterior of a fulfillment center in Baltimore.
Claire Harbage/NPR
hide caption
toggle caption
Claire Harbage/NPR
The exterior of a fulfillment center in Baltimore.
Claire Harbage/NPR
Amazon has many logistics contracts for deliveries, with the United States Postal Service, FedEx, UPS and other compacter companies. But it also took a page from Uber and launched hiring drivers for side-gigs to create superquick deliveries in busy cities, paying between $18 and $25 an hour.
The app is officially called “Flex,” but its original name is “Rabbit” — “along the magic theme,” states Beryl Tomay, director of Amazon’s Last Mile Delivery Technology.
The process relies on AI to constantly calculate how many drivers are necessaryed at any given time. The app considers the weight and number of packages headed to the same neighborhoods and whether packages can fit in one of the available cars. The app even recommfinishs the order of packing boxes into a car for the most efficient delivery.
One large challenge for Flex drivers is parking. Amazon’s app does not guide where to leave cars while dropping off a package. However, Amazon does factor how long it took other drivers to deliver to an address in its estimates. AI’s timing estimates also consider traffic and types of building.
“A single-family home is fairly straightforward, whereas if it’s a commercial building or an apartment complex, that receives a little bit more difficult,” Tomay states. “It’s not always obvious where the unit is or are we taking it to a mailroom or receptionist?”
As Sibay describes it, when a delivery a one-hour race, every minute counts. So delays and missed deadlines receive a thorough analysis.
“Were we not able to pick it in time from our warehoutilize shelves? Did we not have the right number of drivers?” states Sibay. Or maybe “the driver forreceives his key at reception and has to walk a little longer. The driver’s delivering a package and it’s an elderly lady and they, you know, talk a little bit before he relocates on to his next order.”
It’s hard for AI to predict all these scenarios, Sibay states. But next time, maybe the address with the Chatty Cathy will receive a few more minutes baked into the algorithm.
Leave a Reply