Fanatics launches OpenAI-powered Shop the Look to complete fans' game-day outfits
Fanatics has launched an OpenAI-powered version of Shop the Look, a feature that recommends coordinated merchandise so fans can complete their game-day outfits. According to OpenAI, the new experience achieved 10% higher engagement than the previous one in tests across roughly 30,000 MLB products.
- Fanatics launched an OpenAI-powered Shop the Look that recommends coordinated merchandise for game-day outfits.
- It is live across many Fanatics network sites, including Fanatics.com and the official NFL, NBA, MLB and NHL online stores.
- Looks use enriched product, team and inventory data, follow Fanatics' merchandising rules and are refreshed daily.
- A test on 50 products took less than a day, and the MVP was approved the same week.
- According to OpenAI, tests across roughly 30,000 MLB products showed 10% higher engagement than the previous experience.
Shop the Look goes live across the Fanatics network
Fanatics and OpenAI are collaborating to improve the fan experience, and Shop the Look is the first result described in the announcement. The feature is now live across many sites in the Fanatics network, including Fanatics.com and the official NFL, NBA, MLB and NHL online stores.
When a fan browses for a favorite team's jersey, Shop the Look suggests coordinated outfits on the product page. The suggestions use in-stock items that match the team and the intended style, so fans can more easily find merchandise to wear with the item they are looking at.
Fanatics is a global digital sports platform. According to OpenAI, the company uses ChatGPT Work and Codex across Fanatics Corporate, Commerce, Collectibles, and Betting and Gaming.
How the recommendations are built
OpenAI models draw on enriched product data, team information and inventory information to assemble the recommendations. Fanatics' merchandising rules keep the selections compatible and relevant, and the looks are refreshed daily as catalogs change.
The setup combines model-generated suggestions with the retailer's own rules. The models propose the outfits, while the merchandising rules act as a check on whether items fit together and suit the fan's chosen team and style.
The first 50 looks in under a day
Using Codex, OpenAI and the Fanatics engineering team quickly developed custom recommendation tools. These tools enrich product and catalog data, find compatible merchandise, evaluate recommendations, and generate looks for each product.
Testing the new approach on 50 products took less than a day to complete. Fanatics reviewed the looks and gave feedback directly to the builders. After a couple of days of iteration, the company approved the minimum viable product that same week.
According to OpenAI, it helped design the solution that let Fanatics implement the new Shop the Look experience in its production environment and scale the approach across thousands of products.
What the results suggest
The one performance figure in the announcement comes from testing across roughly 30,000 MLB products. In that test, the OpenAI-powered Shop the Look experience achieved 10% higher engagement than the previous experience, according to OpenAI. The announcement does not say how engagement was measured.
For shoppers on Fanatics sites, the change means outfit suggestions on product pages that are built from current inventory and refreshed each day. For retailers, the example shows a workflow in which a small test batch, direct feedback and quick iteration led to a approved prototype within a week, followed by a rollout across thousands of products.
OpenAI: How Fanatics and OpenAI streamline the fan experience