How we use AI to deliver customer orders with less packaging
If you sell with FBA, the boxes or mailers that your products are sent to customers in are likely selected by artificial intelligence (AI).
We're working hard to reduce packaging waste, but choosing the optimal packaging that both reduces waste and protects products can be challenging.
Our AI model, the Package Decision Engine, uses a combination of deep machine learning, natural language processing, and computer vision to determine the most efficient packaging for each product. For example, it can predict when a more durable product like a blanket doesn't need protective packaging, or when a potentially fragile item like a set of dinner plates might need a studier box.
The model helps to reduce the number of cardboard boxes, air pillows, tape, and mailers used to send purchases to customers, and along with other packaging innovations has helped avoid more than 2 million tons of packaging material worldwide since 2015.
Prior to the use of AI, Amazon associates used physical testing on individual products to determine how to optimize packaging, but that work was impossible to scale through human efforts alone. The Package Decision Engine has helped automate portions of this work, allowing Amazon associates to focus on addressing other sustainability challenges.
To find out more about how it works, read the full story in About Amazon
How we use AI to deliver customer orders with less packaging
If you sell with FBA, the boxes or mailers that your products are sent to customers in are likely selected by artificial intelligence (AI).
We're working hard to reduce packaging waste, but choosing the optimal packaging that both reduces waste and protects products can be challenging.
Our AI model, the Package Decision Engine, uses a combination of deep machine learning, natural language processing, and computer vision to determine the most efficient packaging for each product. For example, it can predict when a more durable product like a blanket doesn't need protective packaging, or when a potentially fragile item like a set of dinner plates might need a studier box.
The model helps to reduce the number of cardboard boxes, air pillows, tape, and mailers used to send purchases to customers, and along with other packaging innovations has helped avoid more than 2 million tons of packaging material worldwide since 2015.
Prior to the use of AI, Amazon associates used physical testing on individual products to determine how to optimize packaging, but that work was impossible to scale through human efforts alone. The Package Decision Engine has helped automate portions of this work, allowing Amazon associates to focus on addressing other sustainability challenges.
To find out more about how it works, read the full story in About Amazon
26 respuestas
Seller_7qyIBLnwn8Wlz
More often than not we get our automated returns sent back in massive Amazon boxes that are far too large for the products being sent back. Our products will literally slide from side to side and hits the box inside enough times in transit it starts to or actually breaks through the box. I think the Package Decision Engine might need more tweaking...
Seller_LAhuiXJ4eMubd
What an absolute joke - every time we get a removal from FBA, it's always a tiny little product in a massively oversized box. If we're lucky, whoever packed the order will throw a scrap of packing paper in the box for good measure, as if that's going to do anything.
The scary part about this? Amazon is considered to be a leader in AI, and as anybody who has been selling on Amazon for a while knows, their AI makes absolutely horrible decisions.
Seller_zFh2yK8Fq5oqa
Maybe you should contract with another AI provider. Your AI is pathetic. We get returns from FBA that are a DVD in a box larger than a shoebox. Your AI bots flag listings like sex in the city DVDs as adult toys, or books about healthy eating as unapproved supplements. And your AI cannot seem to stop Chinese listing jackers from changing brand names on existing products to a bunch of nonsense letters.
Seller_Ggt6s7zXEwLbA
Cool - when will lower FBA fees from the cost savings become effective?
Seller_OChH0VD9utdxq
Can your AI fix the website so when I search for a product and "USA" its stops giving me all the knockoffs and junk from China?
Or when I search my own company name, would it stop offering all of the fakes and knockoffs of our product under "recommended"?
Seller_wnc1pjYEF5ZqF
AI is needed to figure that out? How about a human with common sense?
Not to mention there's some faulty logic here, as a blanket in a polymailer (Amazon's standard unprotected packaging) could easily rip and damage a fabric item like that. Seems like this is a case of the blind leading the blind.
Seller_NxPuqak8YNJEF
A.I. short for Artificial Incompetence?
Seller_G53rrrmDqxLLo
I once bought expensive Bone China Teacups, Sold and Shipped by AMAZON ,the order was $1200 and came in a Bubble Mailer! And this was done BEFORE AI was making decisions . Needless to say the entire order was totally destroyed and Amazon did not have replacements to send, so I got a refund. If I could have left feedback for Amazon it would have been NEGATIVE, but only OUTSIDE sellers are subjected to the USELESS FEEDBACK SYSTEM!
Seller_2srXkS44rN39i
I love the "Amazon is helping the environment by using thinner boxes".
Yep... more stuff getting damaged in transit is helping the environment more than using standard 32 ECT cardboard on your order.
Seller_79Jmvk9Q9E9wC
I am not sure when this began but if it is recently, I hope it is better than what it has been. We get sometimes a way too large of a box for an item with a splash of packing paper. Makes no sense.
Furthermore, if AI makes this better, will the savings be passed to the sellers. Because right now it is hard for sellers to make money, it basically all goes to Amazon.
