[CW Paper-Club] DeepETA: How Uber Predicts Arrival Times Using Deep Learning

Welcome to CloudWalk's weekly paper-club session, where our R&D team presents interesting research papers.

In this week's session, Lars Klingen will be presenting the blogpost "DeepETA: How Uber Predicts Arrival Times Using Deep Learning" by Uber in 2022. Uber later (after this video was recorded) released a paper named "DeeprETA: An ETA Post-processing System at Scale" by Hu et al, which expands on the blogpost's concepts.

Uber uses machine learning models to refine accurate arrival time predictions. They switched to deep learning with the development of DeepETA (later renamed DeeprETA), a low-latency deep neural network architecture that meets the challenges of latency, accuracy, and generality.

If you're interested in joining our team at CloudWalk, please check out our job openings on LinkedIn. Don't forget to check out the blogpost and paper, which are available at the links provided below.

Recording Date: March 11, 2022