Advanced Technologies for Detecting and Preventing Fraud at Uber

Diagram of fraud prevention workflow
To detect and prevent fraud, Uber brings to bear data science and machine learning, analyzing GPS traces and usage patterns to identify suspicious behavior.

Engineering for Compliance: Meet the Uber Engineering Team in Sofia, Bulgaria

Established in 2014 as one of Uber's first distributed engineering sites, Uber Sofia is home to our Tax & Compliance Engineering team, a group responsible for developing the technologies that power our key reporting and compliance services.

Food Discovery with Uber Eats: Building a Query Understanding Engine

Query understanding article feature image
Uber engineers share how we process search terms for our Uber Eats service, using query understanding and expansion to find restaurants and menu items that best match what our eaters want.

Going Global: Highlights from the Second Annual Uber Technology Day

On April 19, 2018, Uber's LadyEng group hosted Going Global: Uber Tech Day, our second annual event focused on showcasing the technical work of engineers, data scientists, and product managers from across the company.

Building a Multi-Modal Transportation Platform with JUMP Bikes

A JUMP bike rider at the Golden Gate Bridge
Making JUMP Bikes' semi-dockless electric bicycles available on Uber's platform not only added a popular new transportation type for Uber riders, but also marked an important step in how we can use our technology to broaden transportation options.

From Beautiful Maps to Actionable Insights: Introducing kepler.gl, Uber’s Open Source Geospatial Toolbox

Created by Uber's Visualization team, kepler.gl is an open source data agnostic, high-performance web-based application for large-scale geospatial visualizations.

Open Source at Uber: Meet Shan He, the Architect Behind kepler.gl

Shan He, the technical lead on Uber's kepler.gl framework, discusses her journey to data visualization and why she believes open source is such an important part of her team's work.

Growing the Data Visualization Community with deck.gl v5

deck.gl v5 incorporates simplified APIs, scripting support, and framework agnosticism, making the popular open source data visualization software more accessible than ever before.

Engineering a Job-based Forecasting Workflow for Observability Anomaly Detection

Uber’s Observability Applications team overhauled our anomaly detection platform’s workflow to enable the intuitive and performant backfilling of forecasts, paving the way for more intelligent alerting.

Customer-focused Engineering at Uber: A Q&A with Jörg Heilig, VP of Ridesharing and Eats Engineering

Jörg Heilig, Vice President of Engineering for Ridesharing and Eats
In this interview, Uber Vice President of Engineering for Ridesharing and Eats Jörg Heilig talks about taking a leadership role in a large engineering organization with a broad portfolio and the priorities being set for 2018.

Thank You for Your Feedback: Improving the Uber Engineering Workflow with uRate

uRate empowers both Uber employees and customers to provide quick and efficient feedback on tools and products, enabling engineers to build more responsive services.

Revealing Genius: Zach Singleton on Preparing Black Male CS Students for Tech Careers

The Hidden Genius Project - Career Prep Program
Product Manager Zach Singleton talks about how Uber partnered with The Hidden Genius Project to create the Career Prep Program, a one-year course that prepares black male computer science students for careers in tech.

Introducing Nanoscope: An Extremely Accurate Method Tracing Tool for Android

Uber's Mobile Engineering team open sources Nanoscope, a new method tracing tool for Android that enables developers to more accurately debug difficult performance issues.

Measuring the Intrinsic Dimension of Objective Landscapes

Curious about what it is like to traverse the high-dimensional loss landscapes of modern neural networks? Check out Uber AI Labs’ latest research on measuring intrinsic dimension to find out.

Accelerating Deep Neuroevolution: Train Atari in Hours on a Single Personal Computer

Evolution to running
Applying hardware acceleration to deep neuroevolution in what is now an open source project, Uber AI Labs was able to train a neural network to play Atari in just a few hours on a single personal computer, making this type of research accessible to a far greater number of people.

Rethinking GPS: Engineering Next-Gen Location at Uber

Uber’s Sensing, Inference, and Research team released a software upgrade for GPS on Android phones that significantly improves location accuracy in urban environments.

Mediation Modeling at Uber: Understanding Why Product Changes Work (and Don’t Work)

Uber Labs leverages mediation modeling to better understand the relationship between product updates and their outcomes, leading to improved customer experiences on our platform.

Scaling for Growth: A Q&A with Uber’s VP of Core Infrastructure, Matthew Mengerink

Matthew Mengerink, VP of Core Infra
Matthew Mengerink, Vice President of Engineering for Uber’s Core Infrastructure group, talks about how converging technologies and cloud computing contribute to stable and scalable growth.

Differentiable Plasticity: A New Method for Learning to Learn

Neuron image
Differentiable Plasticity is a new machine learning method for training neural networks to change their connection weights adaptively even after training is completed, allowing a form of learning inspired by the lifelong plasticity of biological brains.

Scaling Uber’s Apache Hadoop Distributed File System for Growth

Uber's Data Infrastructure team overhauled our approach to scaling our storage infrastructure by incorporating several new features and functionalities, including ViewFs, NameNode garbage collection tuning, and an HDFS load management service.

Popular Articles