United StatesRetail and e-commerce2025 – ongoingFurniture.com
Find It AI image-based product discovery and automated catalog cleanup
Furniture.com shoppers who used its Find It AI search returned at 3.2 times the usual rate
Problem
Furniture.com sells from more than 60 retail partners and over 1.5 million SKUs. Partner data came with inconsistent image sizes, missing attributes and unstructured product details, and cleaning it by hand was not practical.
Approach
Furniture.com built Find It AI on Databricks. It uses generative AI to create an image from the shopper's query and matches that image against the catalog. Computer vision models standardize product images, and language models group related products into sets such as bedroom or dining collections.
Results
Takeaway
The same catalog automation that fed the search also let a merchandising team of four or five people handle new partners. The company estimated the team would otherwise need more than 10 people.
Categories
- Size
- Small business
- Industry
- Retail and e-commerce
- Business function
- Marketing and salesProduction and quality
- Innovation type
- Product and service innovation
- AI technology
- Generative AIComputer vision
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
Databricks describes how Furniture.com built the Find It AI search tool and automated cleanup of partner product data. It reports an 8x higher conversion rate and 3.2x more returning users for people who used Find It AI. Click-through was 23.5% for users who interacted with the tool, against a 3% average.
Full details are in the original sources.