Lyft Engineering

OpenStreetMap proven to be a highly accurate map in top US cities

Mark Huberty & Clare Corthell, Lyft Mapping

Flyte: A Cloud Native Machine Learning and Data Processing Platform

Today Lyft is excited to announce the open sourcing of Flyte, a structured programming and distributed processing platform for highly…

Solving a linear optimization problem on incentive allocation

At Lyft, scientists solve all kinds of optimization problems. While solvers can come in handy, there are times when complicated or…

Beyond L2 Loss – How We Experiment with Loss Functions

Estimating expected time of arrival (ETA) is crucial to what we do at Lyft. Estimates go directly to riders and drivers using our apps, as…

Creating Hyper-Accurate Maps from Open-Source Maps and Real-Time Data

Amundsen – Lyft’s data discovery and metadata engine

In order to increase productivity of data scientists and research scientists at Lyft, we developed a data discovery application built on…