A free course on building a real-time personalized recommender system for H&M articles using a four-stage architecture, two-tower model design, and Hopsworks AI Lakehouse. This lesson covers the feature pipeline crucial for creating and managing features required for machine learning models, integrating the H&M dataset, and engineering features for both retrieval and ranking models. It highlights the importance of Hopsworks Feature Groups in managing and reusing features efficiently.
Table of contents
1 — The H&M dataset1 — The H&M datasetTables Relationships2 — Feature engineering3 — Creating Feature Groups in HopsworksThe importance of Hopsworks Feature Groups4 — Next Steps: Implementing a streaming data pipeline5 — Running the feature pipelineConclusionEnjoyed this course?1 Comment
Sort: