How AI Is Helping Amazon Save Half A Million Tons Of Packaging Per Year

Amazon ships 20 million packages a day in 19 countries, requiring an astronomical amount of paper, cardboard and plastic packaging. Figuring out how to pack all those items efficiently is good for the environment and for its own profits.

So in 2019, Amazon
AMZN
launched its own proprietary AI model to reduce packaging waste. The result: five years later, it’s helping to save at least 500,000 tons of packaging a year, according to company data. That’s roughly equivalent to the weight of 7,750 Boeing 737 airplanes.

“This allows us to make these decisions at scale,” Kayla Fenton, a senior manager on Amazon’s packaging innovation team, told Forbes. “It’s definitely an example where sustainability and business can be nicely aligned.”

To handle the volume, Amazon researchers built the AI model, which it calls the Package Decision Engine, to predict the most efficient packaging choice – making sure that a set of dinner plates gets a sturdy box, say, while a blanket does without.

The model uses natural language processing and text-based data about each item from its online store, including basics like the product’s name and description. It also collects feedback from returns and product reviews, incorporating information about products that arrived damaged. It combines all that data with photos taken when items arrive at an Amazon warehouse using a special computer vision tunnel. Those photos give the company details on each object’s exact dimensions and capture images from multiple angles, helping it determine the best way to pack.

Over time, the model has added more nuance in identifying specific items so that, for example, personal items like adult diapers won’t be shipped without packaging in order to save on materials, and products that have strong magnets get enough protection so that they don’t get stuck on conveyors.

In a 2021 paper, Amazon researchers Prasanth Meiyappan, an applied scientist with a PhD in atmospheric sciences from the University of Illinois Urbana-Champaign, and Matthew Bales, a physicist in charge of machine learning in Amazon’s customer experience team, wrote that combining data from both visuals and text improved the model’s performance by as much as 30%.

Using AI to make packaging decisions is unusual, said Euihark Lee, an assistant professor at Michigan State University’s School of Packaging. “I think Amazon is in the forefront of this AI implementation on the packaging side because they have a lot of data,” he said. “Other companies don’t have that amount of data.”

Fenton said that Amazon, which has $575 billion in sales, currently uses the AI model throughout North America and Europe, and is working to roll it out in India, Australia and Japan. She declined to give a date for when the international rollout would be complete, but noted that it would require the AI model to learn new languages and incorporate products specific to those markets.

Amazon said that its packaging model helped it to cut more than 2 million tons of packaging between 2015 and 2022. That’s an increase of 500,000 tons since the last time the retail giant announced its packaging reduction in 2021, when it reported saving more than 1.5 million tons since 2015. Amazon does not disclose how many tons of packaging material it uses each year, making it tough to know how significantly the AI model has reduced its total packaging use.

Experts told Forbes that any reductions are positive. “I think it is substantial,” said David Feber, a McKinsey senior partner focused on packaging. Rafael Auras, a professor of packaging sustainability at Michigan State University’s School of Packaging, said that it was an impressive amount for one company to reduce, but the problem is so widespread that this hardly makes a dent. “There is a large opportunity not only for Amazon but for the whole industry to use AI to reduce packaging waste,” he said.

Amazon’s use of AI in packaging isn’t just about waste or sustainability, of course, but also about cost. In its most recent annual report, the company details how it seeks “to reduce our variable costs per unit,” including by picking the right packaging.

Plastic packaging is a particular sticking point for Amazon. Plastic is tough to recycle, and a recent report by CalPIRG found that plastic waste from Amazon that was dropped off at store bins (as required for all those blue-and-white plastic mailers) rarely made it to recycling centers.

Amazon announced in October that its warehouse in Euclid, Ohio would replace plastic packaging with recyclable paper and cardboard materials as part of a multiyear effort to wean its distribution network off plastics. The AI model helped it to make that switch by determining which items could safely go into paper bags—a new packaging type that is 90% lighter than rigid, cardboard boxes of the same size—and which still needed sturdier options, Fenton said.

She said that the switch to paper and cardboard packaging is now complete in the Ohio distribution center, but declined to give a target date for when Amazon’s other U.S. warehouses would give up plastics. In Europe, where new legislation will soon ban single-use plastic packaging, Amazon has replaced its plastic delivery bags and air pillows with paper and cardboard materials.

Amazon has said that its goal is to reach net-zero in carbon emissions by 2040. In its most recent sustainability report, for 2022, the company said that it had reduced carbon emissions by 0.4%, while sales increased by 9%, in part by delivering 145 million packages globally with its fleet of more than 9,000 electric vehicles. Packaging choices can also indirectly impact delivery emissions (and cost) because the smaller packages are, the more that can fit into any one vehicle. “The impact of reduced packaging is felt in the packaging itself and in the transportation of smaller sized and more right-sized packages to customers,” Fenton said.

But to fully reduce the impact of all those packages being shipped to consumers, cutting waste is just one piece. Another, perhaps harder, challenge will be to get the paper mills that supply it with boxes and bags to produce them in a sustainable way.

New regulation and legislation on packaging sustainability may provide a push. McKinsey’s Feber said that more than 700 regulations in 59 countries target packaging sustainability, including between 50 and 100 at the state and local levels in the United States. “The true breakthroughs in sustainability and cost,” he said, “are going to come when all the supply chain works together.”