Industrial recommender systems (RecSys) are made up of complex pipelines requiring multiple steps including data preprocessing and feature engineering, building and training recommender models and deploying them into production. Data Scientists and ML engineers might focus on different stages of recommender systems, however they share a common desire to reduce the time and effort searching for and combining boilerplate code coming from different sources or writing custom code from scratch to create their own RecSys pipelines.
In this workshop, we will review the theory of deep learning recommender systems and introduce the challenges. Furthermore, we will introduce the NVIDIA Merlin framework that consists of a set of libraries and tools to build models and pipelines more easily and efficiently. We will demonstrate how to train popular deep learning recommender architectures and how to deploy an ensemble in two live-coding sessions.
In this presentation, participants will learn: (i) a short introduction into recommender systems and deep learning recommender systems, (ii) how to easily implement common recommender system techniques, and (iii) deploying recommender systems with NVIDIA Merlin.
