Features on Time: Lyft's Store for ETA and Marketplace Models
Why Lyft invested in a feature store so training-time signals for ETAs and dispatch match what the production models see in the request path.
3 min read
Engineering at scale
3 articles · 9 min of reading
Why Lyft invested in a feature store so training-time signals for ETAs and dispatch match what the production models see in the request path.
How Lyft balances dynamic pricing, dispatch, and ETA so a two-sided marketplace clears without leaving riders waiting or drivers idle in the wrong place.
Why Lyft replaced a tangle of client libraries with Envoy, a C++ L7 proxy that became the data plane for service mesh everywhere else.