Search relevance improves when ranking reflects how users actually interact with results. OpenSearch provides three plugins that work together to enable this: User Behavior Insights (UBI) collects click and query data, Search Relevance Workbench (SRW) evaluates ranking quality, and Learning to Rank (LTR) applies machine-learned models to reorder results. This session walks through the full workflow: collecting user behavior data with UBI, training an XGBoost-based ranking model, and deploying customized search rankings using the LTR plugin.
