Amazon enhances fashion shopping with AI
Amazon is deploying artificial intelligence (AI) to help ensure proper fit and customer satisfaction for its online fashion shoppers.
In a corporate blog post, Apoorv Chaudhri, director of computer vision and machine learning at Amazon Fashion, highlighted a few recent AI-enabled features the e-tail giant has rolled out to assist fashion shoppers and sellers.
AI-driven size recommendations personalized to each customer
Amazon uses AI and machine learning (ML) models to recommend a size that’s just for you on each product’s detail page. The retailer developed a deep learning-based algorithm to help each customer find their best-fitting size in any style.
The algorithm considers the sizing relationships between brands and their size systems, a product’s reviews and other details, and a customer’s fit preferences. The feature then recommends in real-time the best-fitting size for a customer.
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.
Amazon says it built the algorithm so it’s continuously learning and self-adapting to changes in customers’ size needs. For example, if a customer bought child pants in a certain size, the algorithm will consider that they might need a bigger size in the coming months.
In addition, Amazon’s AI-based recommendations extract product data such as style, color, price, size, rate of return and customer reviews across its product catalog to recommend other individually selected styles as a customer shops.
Fit review highlights offer relevant customer feedback
Another feature designed to help fashion shoppers find the right fit is AI-generated fit review highlights. Amazon creates a review highlight for each customer based on their recommended size using common themes across reviews.
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. Amazon applies AI tools like large language models (LLMs) to extract details from customer reviews, such as size accuracy, garment fit on specific body areas, and fabric stretch.
The retailer then uses AI to summarize these details in a review highlight. The highlight guides each customer to the most relevant information, with the goal of allowing them to avoid manually reading through hundreds of reviews for each item.
Applying AI-based fit data to size charts
Leveraging LLMs, Amazon automatically extracts and cleans product size chart data from multiple sources. The retailer utilizes that data to create standardized sizes, remove duplicate information, and auto-correct missing or incorrect measurements, with the goal of creating a more accurate and consistent size chart.
Rather than showing a full table of measurements in a chart format, Amazon is experimenting with new ways to surface the most relevant size and measurement details for each customer, such as grouping measurements for their recommended size.
AI-backed fashion fit insights tool
The fit insights tool uses for fashion brands and sellers 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 ML to help identify defects in size charts.
Leveraging this data, fashion brands can try to better understand customer fit issues, improve how they communicate sizing to customers, and incorporate feedback into future designs and manufacturing.
[Read more: Study: AI will have a $580 billion impact on Amazon and Walmart]
“Our vision is to make Amazon Fashion for everyone,” Chaudri said in the blog post. “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.”