Improving Driver Communication through One-Click Chat, Uber’s Smart Reply System

One-click chat, the Uber driver app's smart reply system, leverages machine learning to make in-app messaging between driver-partners and riders more seamless.

Introducing Petastorm: Uber ATG’s Data Access Library for Deep Learning

Petastorm logo
Uber's Advanced Technologies Group introduces Petastorm, an open source data access library enabling training and evaluation of deep learning models directly from multi-terabyte datasets in Apache Parquet format.

From Financial Models to iOS Model View Controllers: Making a Career Move to Programming

Joe Zhou, the 7th iOS engineer on the Uber Eats team, offers advice for those considering taking the plunge into programming.

Marmaray: An Open Source Generic Data Ingestion and Dispersal Framework and Library for Apache Hadoop

Marmaray logo
Today we introduce Marmaray, an open source framework allowing data ingestion and dispersal for Apache Hadoop, realizing our vision of any-sync-to-any-source functionality, including data format validation.

Talking Safety with Uber Data Scientist Sunny Jeon

Sunny Jeon
In an interview for the Uber Eng blog, Data Scientist Sunny Jeon talks about how his team develops solutions in order to advance Uber's core value of safety.

Food Discovery with Uber Eats: Recommending for the Marketplace

Food Discovery with Uber Eats: Recommending for the Marketplace
Uber Eats engineers describe how they surface restaurant recommendations in the app using multi-objective optimization to give eaters the most satisfying experience while maintaining the health of the Uber Eats marketplace.

Forecasting at Uber: An Introduction

In this article, we provide a general overview of how our teams leverage forecasting to build better products and maintain the health of the Uber marketplace.

Under the Hood of Uber’s Experimentation Platform

Uber's experimentation platform empowers us to improve the customer experience by allowing teams to launch, debug, measure, and monitor product changes.

Scaling Uber’s Customer Support Ticket Assistant (COTA) System with Deep Learning

Uber built the next generation of COTA by leveraging deep learning models, thereby scaling the system to provide more accurate customer support ticket predictions.

Seeing Double: Meet Uber’s Identical Twin Data Scientists

Afshine and Shervine Amidi, identical twins, discuss their journeys to data science and how their work at Uber helps teams improve user experiences on our platform.

Maximizing Process Performance with Maze, Uber’s Funnel Visualization Platform

Uber developed Maze, our funnel visualization platform, to identify possible UX bottlenecks and provide insight into the various ways riders and drivers interact with our platform.

Out of the Classroom: A Snapshot of Uber’s Summer 2018 Interns

Summer 2018 Uber Eng Interns
A few of Uber's over 200 engineering interns from this year's summer program talk about the projects they worked on and what their experiences in the office were like.

M3: Uber’s Open Source, Large-scale Metrics Platform for Prometheus

M3, Uber's open source metrics platform for Prometheus, facilitates scalable and configurable multi-tenant storage for large-scale metrics.

Databook: Turning Big Data into Knowledge with Metadata at Uber

Databook, Uber's in-house platform for surfacing and exploring contextual metadata, makes dataset discovery and exploration easier for teams across the company.

Introducing Fusion.js: A Plugin-based Universal Web Framework

Fusion.js, Uber's new open source web framework, supports modern features and integrations that make it easy to build lightweight, high-performing apps for the web.

Herb: Multi-DC Replication Engine for Uber’s Schemaless Datastore

Facing the need for a resilient data structure over thousands of storage nodes to serve the 15 million rides per day that occur on our platform, Uber engineers developed Herb, our data replication solution. Herb ensures data availability and integrity across our data centers.

Building Automated Feature Rollouts on Robust Regression Analysis

This series of images shows staged rollouts of features at Uber
Building robust regression analysis not only helps ensure that new feature deployments work properly, but also lets Uber engineers automate deployments.

Enhancing the Quality of Uber’s Maps with Metrics Computation

Enhancing the Quality of Uber’s Maps with Metrics Computation - feature image
Maps make up the bedrock of Uber's transportation solutions. Find out how we ensure the quality of our map data through extensive metrics computation, maintaining fidelity to real world locations and pinpointing allowable pick up and drop off locations for riders.

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

As powerful and widespread as convolutional neural networks are in deep learning, AI Labs’ latest research reveals both an underappreciated failing and a simple fix.

Transforming Financial Forecasting with Data Science and Machine Learning at Uber

World map with stack of gold coins
Uber developed its own financial planning software, relying on data science and machine learning, to deliver on-demand forecasting and optimize strategic and operations decisions.

Popular Articles