Amazon has embedded sustainability into its core strategy, looking to be net-zero carbon by 2040 as part of its Climate Pledge. To do so, the company has accelerated efforts by leveraging artificial intelligence and machine learning.
The company’s vice president and head of worldwide sustainability, Kara Hurst, recently detailed these initiatives in a blog post, stating that “artificial intelligence and machine learning can help us meet our climate goals at the speed, scale, and urgency our planet requires.”
One of the primary areas of business seeing a notable increase in sustainable-forward initiatives is packaging.
The company is using an AI model called the Packaging Decision Engine, launched in 2019, to determine the most efficient packaging options, taking into account an item’s shape and durability as well as customer feedback from fulfilled orders.
The model is continuously learning, said Hurst, and has so far eliminated over two million tons of packaging material worldwide since 2015, in combination with other packaging innovations.
Reducing Returns and Waste
Additionally, Amazon is tackling waste - both related to returns and food. Using AI across its fulfillment processes, the company has been able to increase its detection of damaged goods in order to reduce the amount of damaged items being sent out and then returned.
“The AI is three times more effective at identifying damaged goods than human beings and has been trained by analyzing millions of photos of undamaged and damaged items,” said Hurst. “If a product can’t be shipped directly to a customer due to imperfections, the item is flagged to an Amazon associate, who assesses the product and reroutes it to be resold at a reduced price, donated, or otherwise reused.”
To reduce returns related to fit-related issues, Amazon has added capabilities such as personalized size and recommendations using AI and ML, along with a Fit Insights tool, in order to more accurately meet the needs of consumers.
When it comes to food, Amazon has been able to automate store shelf monitoring for fruits and vegetables by using machine learning. The AI-powered tech looks at crate images to determine if there are any visual imperfections like cracks, cut, and pressure damage on fruits.
“To ensure the defective produce is recycled whenever possible, Amazon Fresh resells the usable produce to local contractors who further resell the produce at reduced prices for use cases like feeding to livestock, ensuring less food goes to waste,” said Hurst.
The Power of Data to Move Sustainability Forward
In order to continue innovating and ensure that sustainability efforts move forward, the company leans on many different data points.
For example, Amazon’s AI-based algorithm named Flamingo uses natural language processing to match text descriptions for Environmental Impact Factors (EIF) to calculate the carbon impact of an item. Hurst said that one experiment that used this algorithm resulted in scientists spending less time mapping 15,000 Amazon products - down from a month to several hours.
Other efforts include real-time monitoring to prevent deforestation and supporting the company’s IT infrastructure with chips that are more energy efficient.
“As the most transformational technology of our time, Amazon expects AI to be an increasingly important part of our work to build a more sustainable business, and we’re excited to share what’s coming next for our company and customers,” said Hurst.