How Amazon Fashion is using AI to help you find the perfect fit

Amazon wants customers to shop with confidence. This includes developing features that help customers find great-fitting fashion items from the comfort of their homes. Valuable insights unlocked by artificial intelligence (AI) have been helping us improve the customer experience and address the size and fit challenges that are part of shopping for fashion online.

Following are a few recent AI-enabled features that empower customers to confidently shop our stores for the fashion and styles they love.

AI-driven size recommendations personalized to each customer

Not sure what size to order? Nobody wants to spend time cross-referencing reviews, size charts, product images, and detailed product descriptions. That’s why we use AI and machine learning models to recommend a size that’s just for you on each product’s detail page.

We developed a deep learning-based algorithm to help each customer find their best-fitting size in any style. It considers the sizing relationships between brands and their size systems, a product’s reviews and other details, and a customer’s own fit preferences. The feature then recommends in real-time the best-fitting size for a customer.

From Alexa to ‘Thursday Night Football,’ Amazon is using generative AI as a powerful tool to innovate.

Here’s how it works: The algorithm anonymously clusters together customers with similar size and fit preferences, and products with a similar fit. From there, the algorithm learns from millions of product details, such as style, size chart, and customer reviews, and billions of anonymized customer purchases. It also takes into account sizes bought and kept by similar customers for the same product, or for similar-fitting products.

We know that sizes may change over time. We built the algorithm so it’s continuously learning and self-adapting to changes in customers’ size needs. For example, if you bought child pants in a certain size this month, the algorithm will consider that you might need a bigger size in the coming months.

We also know that shoppers love to evaluate their options. We use AI to help them discover alternative best-fitting styles based on their preferences. Our AI-powered recommendation extracts product data such as style, color, price, size, rate of return, and customer reviews across our vast product catalog to recommend other flattering styles as a customer shops.

We’ve learned that customers are more likely to purchase and keep an item when a size is recommended for them. The size recommendation system analyzes millions of data points every day and generates billions of size recommendations each month for hundreds of millions of customers across 19 locales around the world.

Fit Review Highlights offer relevant customer feedback

Another feature that helps our customers find the right fit is AI-generated Fit Review Highlights. We create a review highlight for each customer based on their recommended size using common themes across reviews. The goal is to make it easier for our diverse customer base to get personalized size guidance so they can determine how a style will fit on them.

The feature tells a customer whether to size up or down in a particular style based on reviews from customers who have purchased the item in the same size. We use the latest and most advanced forms of AI, like large language models (LLMs), to extract details from customer reviews, such as size accuracy, garment fit on specific body areas, and fabric stretch. We then use AI to summarize these details in an easy-to-read review highlight. The highlight guides each customer to the most relevant information, so they don’t have to manually parse through hundreds of reviews for each item.

Reimagining size charts with AI-powered data that you can trust

We also want to make size charts more accurate and useful for customers. AI helps us improve accuracy of size charts while showing customers relevant information in a more visually engaging way. By leveraging LLMs, we automatically extract and clean product size chart data from multiple sources. We then transform the data into standardized sizes, remove duplicate information, and auto-correct missing or incorrect measurements, resulting in a more accurate and consistent size chart.

We are also making size charts easier to understand. Rather than showing a full table of measurements in a chart format, we are experimenting with new ways to bring forward the most relevant size and measurement details for each customer—such as grouping measurements for their recommended size, so that their size is easy to find.

Brands can now improve their product offerings with our AI-backed Fit Insights Tool

Brands and selling partners can benefit from all of this innovation, too. Understanding why customers returned an item can be a mystery, but with our new Fit Insights Tool, Amazon can do the heavy lifting for brands and offer insights into the fit of various products.

The Fit Insights Tool uses an LLM model to extract and aggregate customer feedback on fit, style, and fabric. It contextualizes returns and size chart analyses with customer reviews, using machine learning to identify defects in size charts. By leveraging this data, brands can better understand customer fit issues, improve how they communicate sizing to customers, and even incorporate the feedback into future designs and manufacturing. This helps brands reduce fit-related returns and more accurately list their items for customers.

Whether you’re looking to step up your beauty game, or stock up on everyday essentials—here are some of our favorites.

Find the perfect fit with AI and Amazon Fashion

Our vision is to make Amazon Fashion for everyone. It’s why we will continue to bring new, exciting selection to our stores, and why we’re continually innovating the shopping experience to meet the needs of every customer—regardless of their size, budget, or style preference.

Discover new styles and see personalized fit and size recommendations at Amazon Fashion.

Next, get an inside look at Amazon’s return process and how products get a second life.