Presented By O'Reilly and Cloudera
Make Data Work
22–23 May 2017: Training
23–25 May 2017: Tutorials & Conference
London, UK

The mystery of the vanishing pins: Building a sustainable content ecosystem at Pinterest

Grace Huang (Pinterest)
14:5515:35 Thursday, 25 May 2017
Location: Capital Suite 15/16
Average rating: *****
(5.00, 1 rating)

What you'll learn

  • Learn how Pinterest maintains a healthy ecosystem around machine-learning products

Description

As Pinterest undergoes explosive growth in its user base, the content corpus that users contribute to is also rapidly expanding. The content and the machine-learning algorithms exist in a feedback cycle where content signals power the algorithms and algorithms influence the content that populates the ecosystem. A major algorithm change can significantly impact how content is exposed. Without proactive monitoring in place, the makeup of the exposed content can drift over time, in a direction that may not be the most beneficial to users in the long term.

Grace Huang offers a glimpse into the unique challenges of maintaining a healthy ecosystem around machine-learning products at Pinterest. Grace explores the suite of tools Pinterest built to make sense of machine-learning experiment results and the panel of metrics it developed to help gauge the health of the content ecosystem and shares the story of a cross-functional effort to ensure that quality content can thrive in the the ecosystem and make its way to pinners who will find it relevant and engaging.

Photo of Grace Huang

Grace Huang

Pinterest

Grace Huang is the data science lead for discovery at Pinterest, where discovery products like recommendations and personalization are developed. She is passionate about building data science products around machine-learning algorithms to drive better experience for Pinterest users and build a sustainable ecosystem.