apply() is an event series for machine learning and data teams to discuss the practical data engineering challenges faced when building operational machine learning systems. Participants learn from industry experts and share best practices with the community.
apply(recsys) focuses on the specific challenges of building recommender systems. Join us to discuss best practice development patterns, tools of choice, and emerging architectures to successfully build and manage production RecSys applications.
Slack, as a product, presents many opportunities for recommendation, where we can make suggestions to simplify the user experience and make it more delightful. Each one seems like a terrific use case for machine learning, but it isn’t realistic for us to create a bespoke solution for each.
In the talk, we’ll dive into the Recommend API, a unified framework the team built over the years that allows us to quickly bootstrap new recommendation use cases. Behind the scenes, these recommenders reuse a common set of infrastructure for every part of the recommendation engine, such as data processing, model training, candidate generation, and monitoring. This has allowed us to deliver a number of different recommendation models across the product, driving improved customer experience in a variety of contexts.
Intermission between the increadible talks. While we hang out and rest our minds Demetrios will be cracking jokes and giving out some Swaaaaag!
We’ll provide an introduction to Monolith, a system tailored for online training. Our design has been driven by observations of our application workloads and production environment that reflects a marked departure from other recommendations systems. Our contributions are manifold: first, we crafted a collisionless embedding table with optimizations such as expirable embeddings and frequency filtering to reduce its memory footprint; second, we provide an production-ready online training architecture with high fault-tolerance; finally, we proved that system reliability could be traded-off for real-time learning. Monolith has successfully landed in the BytePlus Recommend product.
You suggest the lyrics and Demetrios will sing about whatever you desire!
Meet others who are at the event!