The news: Fanatics worked with OpenAI to build “Shop the Look,” a feature that recommends in-stock merchandise that matches shoppers’ favorite teams and personal style from a catalog of more than 1.5 million SKUs across Fanatics.com, along with its sports league and team ecommerce sites.

The tool addresses a key challenge: Fanatics’ massive, fast-changing assortment makes it difficult for shoppers to find products that fit their tastes. With thousands of new items added regularly, traditional merchandising methods like curated photoshoots strained to keep pace, leaving shoppers to navigate the growing catalog on their own and contributing to lengthy shopping sessions, per CNBC.

The details: The tool’s model draws on enriched product data, inventory, and team information, with daily updates to reflect catalog changes. Merchandising rules help ensure recommendations are relevant and complementary.

Fanatics tested the experience on 50 products in less than a day, then refined it with OpenAI over several days before approving the initial version that same week. Built to scale across thousands of products, the feature drove 10% higher engagement than the previous version in testing across roughly 30,000 MLB products.

Implications for retail: While much of the AI buzz centers on potentially game-changing tools like agentic commerce and dedicated apps within ChatGPT, AI’s near-term retail impact may be less flashy. Fanatics’ Shop the Look shows how AI can help retailers make recommendation engines more responsive to changing assortments and more effective at connecting shoppers with relevant products, simplifying personalization at scale.

This content is part of EMARKETER’s subscription Briefings, where we pair daily updates with data and analysis from forecasts and research reports. Our Briefings prepare you to start your day informed, to provide critical insights in an important meeting, and to understand the context of what’s happening in your industry. Non-clients can click here to get a demo of our full platform and coverage.