Making Ads Count: Using MMoE and Auxiliary Tasks to Better Connect Buyers & Sellers

· Etsy, Inc. · March 20, 2026, 7:02 p.m.
e-commerce Machine Learning Advertising Technology Data Science
Summary
This blog post discusses Etsy's advancements in their Ads Search ranking model, focused on enhancing buyer engagement through a multitask learning framework that incorporates the Multigate Mixture of Experts (MMoE) architecture and additional auxiliary signals such as 'add-to-cart'. It highlights improvements in predicting purchase intent and optimizing ad visibility for sellers, aimed at better connecting buyers with relevant listings.
Read full post on www.etsy.com →
AUTHOR
Sponsored
Zulip logo Zulip
Organized team chat for people who take work seriously. Topic-based threading keeps conversations focused.
Try Zulip
Become a sponsor →