Etsy
Fine-tuning

Shaping Product Understanding with Contrastive Reinforcement Learning

Our short summary of Etsy’s engineering write-up. The full story, with all the detail, is on their blog.

Read the full write-up on etsy.com (opens in a new tab)

Problem

Buyers often have vague tastes, making it hard to recommend the right handmade items.

Solution

Etsy trained a model with contrastive reinforcement learning to better capture subtle product details, improving search and recommendation relevance.

Research behind this, on AI Papers DailyFactorized MLLM Embeddings for Composed Image Retrieval

Want the architecture, code and numbers? They’re in the original post.

Read the full write-up on etsy.com (opens in a new tab)

More from Fine-tuning

All Fine-tuning write-ups