Building Session-Based Recommendation Models with NVIDIA Merlin

Session-based recommendation (SBR) has been an important task in online services like ecommerce and news portals, where users may have very distinct interests in different sessions. SBR models have been proposed to model the sequence of interactions within the current user session. They have gained popularity due to their ability to capture short-term or contextual user preferences toward items, and to provide promising model accuracy results. Learn (1) the main concepts and algorithms for SBR; (2) how to process the data and create sequential features; (3) how to create an SBR model with a simple MLP architecture first, then with an RNN-based architecture, and finally with a Transformer-based one using NVIDIA Merlin; and (4) how to train/evaluate the models on GPU. You're expected to have intermediate-level understanding of machine learning/deep learning pipelines, and must have basic knowledge of recommender systems, TensorFlow, and Python programming. 

Prerequisite(s):  

• The target audience for this training lab are practitioners from data science, machine learning (ML) and/or AI communities with intermediate-level understanding of ML and Deep Learning (DL) concepts and pipelines. 
• Basic knowledge of Recommender Systems, TensorFlow framework and Python programming is required. 

Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session. Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.