Elasticsearch Optimizations at LyftPhoto by LyftBy Stefan Zier and Vinay Kakade IntroductionAt Lyft, we use an in-house Feature Service to store batch and streaming features used by ML models, making them accessible in both offline mode (for training) and online mode (for inference). The service replicates these features in Elasticsearch to enable advanced queries. For Growth products, we use Elasticsearch to power internal tools l
