As practitioners, data scientists, engineers, and researchers building effective modern recommendation systems, we understand that simple collaborative filtering models are not enough to accelerate recommender workloads. There is a gap between a few simple models and a production system that serves up relevant recommendations at any scale, including workloads that have the potential to surpass the biggest large language models in use today. Our daily work includes addressing the gap and its challenges. While adjacent domains are under spotlight for end-user accountability for their outputs or retrieved responses on a massive corpus of data, we already know as recommender system builders, how relevant recommendations engage with a person multiple times a day and have business impact on companies within media, retail, finance, and more. Our work on recommender systems continues to drive the digital economy.

Join us online with fellow data scientists, engineers, and researchers to learn, discuss, and iterate on best practices, methods, and techniques to build effective modern recommendation systems at any scale.

• best practices from experts, and proven techniques and methods within industry

• learnings on leveraging session-based recommenders on a multilingual ecommerce dataset

• accelerate performance on massive datasets and recommender workloads

Content

content goes here