Package Decision Engine is designed to ensure that the customer orders are delivered in the most efficient packaging, while preventing damage and streamlining delivery processes
Amazon uses AI model Package Decision Engine to lower packaging waste. (Credit: Amazon.com, Inc.)
Amazon has revealed the development and deployment of an artificial intelligence (AI)-based model called Package Decision Engine to optimise the packaging efficiency of customer purchases.
Package Decision Engine is designed to ensure that customer orders are delivered in the most efficient packaging while preventing damage and streamlining delivery processes.
Using the Amazon Web Services (AWS) cloud, the AI model determines suitable packaging for each item by combining deep machine learning, natural language processing, and computer vision.
The process helps lower the number of cardboard envelopes and boxes, paper dunnage, tape, and paper bags used in order delivery.
The multimodal AI model can predict whether a product needs protective packaging or a sturdier box, the e-commerce major claimed. It also continuously learns about the company’s changing packaging options.
The Package Decision Engine gathers details about each item through several steps. When an item arrives at an Amazon centre, it’s photographed in a special tunnel that measures its size, checks for flaws and takes multiple pictures.
The model also reads text data about each item, like its name, description, price, and package size. It gets feedback from customers through Amazon’s Online Returns Center, product reviews, and other channels in almost real-time.
Based on these data, the model gives a score suggesting the best type of packaging to use. It remembers this choice for future reference, helping to improve packaging decisions over time.
Amazon packaging innovation team technology products senior manager Kayla Fenton said: “We wanted the ability to quickly identify the most efficient packaging option for each item, while also predicting how safely each product would ship.
“The use of AI through the Package Decision Engine has allowed us to advance our packaging efficiency work at scale quickly, and it has worked so well that we’re implementing this technology across Amazon’s broader global footprint.”
The AI application aligns with the sustainability goals of the e-commerce major, contributing to a significant reduction of over two million tonnes of packaging material globally since 2015.
Amazon’s packaging innovation team is planning to use the AI model all over the world. It is being trained to understand various languages, different types of packaging, and products sold in various countries.