After recently turning to generative AI to reinforce its product reviews, e-commerce giant Amazon today shared the way it’s now using AI technology to assist customers shop for attire online. The corporate explains it’s now using large language models, generative AI and machine learning to power 4 AI-powered features that may help customers find clothing that matches — an ongoing challenge when shopping online and the leading cause for attire returns.

Based on a study by Coresight Research, the typical return rate for clothing ordered online is 24.4%, which is eight percentage points higher than the general online return rate. As well as, retailers and types said online returns had grown over the past two years. Often, that’s partly because today’s consumers will buy an item in multiple sizes or colours after which return people who don’t work out, because the strategy of home try-ons and shipping items back has turn into easier.

To deal with this challenge, Amazon has introduced AI into the net shopping experience in 4 ways: in personalized size recommendations, a “Fit Insights” tool for sellers, AI-powered highlights from fit reviews left by other customers and reimagined size charts.

With the personalized size recommendations, Amazon Fashion used AI to develop a deep learning algorithm that may help customers find their best-fitting size across a wide range of styles.

This technique works by considering the dimensions relationship between brands’ size systems, the product’s reviews and the client’s own fit preferences. The data is combined in real-time to make suggestions of the best-fitting size for a customer and adapts as the client’s size needs change. The corporate also uses AI to assist them discover the styles that fit them best. Nevertheless, this feature may be imperfect if a member of the family frequently shops for an additional (like their son or daughter) online, because it confuses the system as to what size the client is versus the kid.

One other latest feature, “Fit Review Highlights,” could help combat that problem, nevertheless. This feature is an extension of the newly added AI-generated Customer Review Highlights introduced in August 2023, which give a brief paragraph summary that details the client sentiment and product features, in addition to provides key product attributes as clickable buttons.

Image Credits: Amazon

With the Fit Review Highlights, Amazon extracts information concerning the apparel’s fit from the client reviews, including things like size accuracy, garment fit on specific body areas and fabric stretch. Large language models extract details from the client reviews after which AI summarizes the findings into an easy-to-read highlight personalized to the user, Amazon explains. This might help save users time as they wouldn’t must read through lots of of reviews to get a way of the item’s fit.

The retailer can be now leveraging AI to enhance size charts across the location. With large language models, Amazon Fashion is extracting and cleansing product size charts from multiple sources after which transforming the information into standardized sizes. This process will remove duplicate information and auto-correct missing or incorrect measurements, resulting in more accurate charts — and subsequently, fit.

Image Credits: Amazon

Sellers, too, will gain access to AI-powered insights. With a Fit Insights Tool from Amazon Fashion, sellers are supplied with an understanding of a customer’s fit needs so that they can improve how they impart sizing to customers — e.g. “true to size,” or if an item runs smaller or larger, as an example.

This information will also be used to guide their future manufacturing efforts, Amazon notes. On this case, large language models are used to extract and aggregate customer feedback on fit, style and fabric along with returns, size chart analyses and customer reviews. Machine learning can be used to discover errors within the brand’s size charts, if any.

Image Credits: Amazon

These features are only a handful of AI advances that Amazon has employed AI to enhance the shopping experience on its site in recent months. Beyond the client review highlights, Amazon also debuted generative AI tools to assist sellers write their product descriptions and enhance their product images. The latter could boost click-through rates by 40%, the retailer estimated on the time. Outside of Amazon Web Services, the corporate also brought AI to other consumer products, including Alexa and Fire TV.