How Pinterest Uses Crystal
7 engineering articles about Crystal from Pinterest's engineering team
Other Pinterest Technologies
Other Companies Using Crystal
Articles
Filter:
The article discusses Non-Engagement Signals, which are essential for platforms like Pinterest to avoid optimizing for low-quality content driven by user engagement.
Pinterest Engineering
9 min read
Has Summary
--
The article discusses how Pinterest developed its Trust & Safety team to combat spam and unsafe content.
This article discusses the transition from a single-output deep neural network to a multi-task learning (MTL) framework for home feed ranking at Pinterest.
Pinterest Engineering
12 min read
Has Summary
--
This article discusses how Pinterest utilizes AutoML, Multi-task Learning, and Multi-tower models to enhance its Ads marketplace.
The article discusses the development of a real-time user signal service at Pinterest that enhances feature engineering for personalized content delivery.
Pinterest Engineering
8 min read
Has Summary
--
The article discusses the improvements made to the Related Pins feature on Pinterest, focusing on addressing the cold start problem to enhance the freshness and relevance of recommendations.
Pinterest Engineering
5 min read
Has Summary
--
The article discusses how Pinterest utilized machine learning to enhance user engagement globally, particularly through improvements in the home feed experience.
Pinterest Engineering
7 min read
Has Summary
--
You've reached the end! All 7 articles loaded.