Pinterest’s mission is to help you discover and do what you love—whether that’s finding the perfect recipe for your family dinner or pulling together an outfit. To achieve this level of personalization, and with 200M+ active users and billions of recommendations every day, we live on machine learning. From object detection and classification to ads auction model tuning, Machine learning is used in numerous components of our system. With limited resources as a medium-sized company, but fast growing demand from passionate users, we have to balance cutting edge technology advancement with practical system implementation that can be put in place within a short amount of time. In this talk, I will review Pinterest’s approach of a careful balance between simplicity and functionality, and how we reached our current stage of system design.

Grace Huang currently heads a data science team at Pinterest where she leads the data science efforts around key machine learning products in order to power a visual discovery engine. Prior to Pinterest, Grace has worked on a wide range of data science projects spanning recommendation systems, search relevance, growth, and algorithm developments in genome sequencing/cancer diagnostics. She holds a PhD in Computational Genomics from the Joint CMU-Pitt Program in Computational Biology.