Amazon ships 20 million packages to 19 countries every day, requiring a lot of paper, cardboard and plastic packaging, and figuring out how to package all of these items efficiently is good for the environment and its own bottom line.
So in 2019, Amazon launched its own proprietary artificial intelligence model to reduce packaging waste. According to company data, after five years, it helped save at least 500,000 tons of packaging per year, which is roughly equivalent to the weight of 7,750 Boeing 737 aircraft. .
To handle the volume of packages, Amazon researchers built an artificial intelligence model called the Packaging Decision Engine to predict the most efficient packaging choices, such as ensuring a set of dinner plates gets a sturdy box and a blanket unnecessary.
The model uses natural language processing and text-based data on each item in the online store, including basic information such as product name and description. It also collects feedback from returns and product reviews, and integrates information about receiving damaged products. All that data is combined with photos taken when items arrive at Amazon warehouses using a special computer vision channel, which gives the company details on the exact dimensions of each object and captures images from multiple angles, helping it determine the best packaging. Way.
Over time, the model added more nuances in identifying specific items; for example, personal items such as adult diapers would not be shipped without packaging to save material, while products with strong magnets would be adequately protection so that they can be shipped without packaging.
In a 2021 paper, Amazon researchers Prasanth Meiyappan and Matthew Bales wrote that combining visual and textual data could improve model performance by as much as 30%.
Euihark Lee, assistant professor at the School of Packaging at Michigan State University, said that using artificial intelligence to make packaging decisions is unusual. "I think Amazon is at the forefront of artificial intelligence applications in packaging because they have a lot of data," he said. "Other companies don't have that much data," said.
Amazon said its packaging model helped it reduce more than 2 million tons of packaging between 2015 and 2022, which was an increase of 500,000 tons from the retail giant in 2021 when it announced its packaging reductions since 2015. While it has saved more than 1.5 million tons since then, Amazon does not disclose how many tons of packaging material it uses each year, making it difficult to determine how much of an impact the AI model has had on its overall reduction in packaging use.
Experts told Forbes that any reduction is a positive, "I think it's important!" said David Feber, a senior partner at McKinsey who focuses on packaging. The reductions are impressive for one company, but the problem is so widespread that it has little impact, said Rafael Auras, professor of packaging sustainability at MSU's College of Packaging. "Using artificial intelligence to reduce packaging waste is a huge opportunity not only for Amazon but for the entire industry," he said.
Source: Forbes (2024.4.16) How AI Is Helping Amazon Save Half A Million Tons Of Packaging Per Year
