Presented By O'Reilly and Cloudera
Make Data Work
March 13–14, 2017: Training
March 14–16, 2017: Tutorials & Conference
San Jose, CA

New user recommendations at scale: Identifying compelling content for low-signal users using a hybrid-curation approach

Maura Lynch (Pinterest)
2:30pm3:00pm Tuesday, March 14, 2017
DCS, Strata Business Summit
Location: LL20 A
Average rating: ***..
(3.50, 4 ratings)

New users are the most delicate for any service. Nailing their first experience with your product is essential to growing your user base. Maura Lynch offers an overview of Pinterest’s hybrid-curation approach to creating compelling content streams for users when there is very little signal as to their preferences. Maura also discusses how Pinterest identifies high-quality topical content at scale and shares the challenges Pinterest has faced along the way.

Topics include:

  • A high-level exploration of how new user recommendations work
  • How Pinterest creates a lightweight signal
  • How to leverage hybrid curation
  • Challenges: Localization, first impressions (home feed experience for first-time users), and evolution (finding the right trends while avoiding brand-inappropriate content)
Photo of Maura Lynch

Maura Lynch


Maura Lynch is a product manager at Pinterest. Before joining product, she worked in analytics both at Pinterest and in gaming for several years. Maura started her career in research in physics at Duke and in economics at the Federal Reserve.