In a selection of presentations delivered at a June 2019 Uber meetup, we discuss how to use H3, our open source hexagonal indexing system, to facilitate the granular mining of large geospatial data sets.
Uber's Marketplace simulation platform leverages ML to rapidly prototype and test new product features and hypotheses in a risk-free environment.
Uber Labs leverages causal inference, a statistical method for better understanding the cause of experiment results, to improve our products and operations analysis.
A key challenge faced by self-driving vehicles comes during interactions with pedestrians. In our development of self-driving vehicles, the Data Engineering and Data Science teams at Uber ATG (Advanced Technologies Group) contribute to the data processing and analysis that help make these interactions safe.
On May 3, 2019, Uber’s Applied Behavioral Science team hosted the Behavioral Science Track of the Second Uber Science Symposium, featuring a full day of presentations delivered by leading researchers in the field.
Learn how to use Kepler.gl for data visualization through our tutorial, where we show how easy it is to load multiple datasets into Kepler.gl to visualize traffic safety in Manhattan.
CatchMapError (CatchMe) is a system that automatically catches errors in Uber's map data with anonymized GPS traces from the driver app.
Performing updates of individual records in Uber's over 100 petabyte Apache Hadoop data lake required building Global Index, a component that manages data bookkeeping and lookups at scale.
How engineers and data scientists at Uber came together to come up with a means of partially replicating Vertica clusters to better scale our data volume.
DBEvents: A Standardized Framework for Efficiently Ingesting Data into Uber’s Apache Hadoop Data Lake
Uber engineers discuss the development of DBEvents, a change data capture system designed for high data quality and freshness that is capable of operating on a global scale.
In this article, we discuss Uber's journey toward a unified, multi-tenant, and scalable data workflow management system.
In this article, Uber’s Marianne Borzic Ducournau discusses why financial planning at Uber presents unique and challenging opportunities for data scientists.
AresDB, Uber's open source real-time analytics engine, leverages GPUs to enable real-time computation and data processing in parallel.
Uber Labs utilizes insights and methodologies from behavioral science to build programs and products that are intuitive and enjoyable for users on our platform.
Uber built Manifold, a model-agnostic visualization tool for ML performance diagnosis and model debugging, to facilitate a more informed and actionable model iteration process.
During an October 2018 meetup, members of our Women in Statistics, Data, Optimization, and Machine Learning (WiSDOM) group presented on their technical work at Uber.
Uber's Head of Urban Computing & Visualization reflects on his team's work visualizing data to better understand urban mobility in 2018—and beyond.
Uber's many data flows required modeling the data associated with a specific task, such as a rider trip, into a state machine. The state machine lets engineers focus on just the events needed to successfully accomplish a trip.
Quantile treatment effects (QTEs) enable our data scientists to capture the inherent heterogeneity in treatment effects when riders and drivers interact within the Uber marketplace.
Responsible for cleaning, storing, and serving over 100 petabytes of analytical data, Uber's Hadoop platform ensures data reliability, scalability, and ease-of-use with minimal latency.
Uber Visualization announces partnership with Mapbox to enhance our data visualization tools and grow our open source community.
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.
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.
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.
Uber's experimentation platform empowers us to improve the customer experience by allowing teams to launch, debug, measure, and monitor product changes.
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.
Databook, Uber's in-house platform for surfacing and exploring contextual metadata, makes dataset discovery and exploration easier for teams across the company.
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.
With a solid margin, Uber senior data scientist Slawek Smyl won the M4 Competition with his hybrid Exponential Smoothing-Recurrent Neural Networks (ES-RNN) forecasting method.
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.
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.
deck.gl v5 incorporates simplified APIs, scripting support, and framework agnosticism, making the popular open source data visualization software more accessible than ever before.
Uber Labs leverages mediation modeling to better understand the relationship between product updates and their outcomes, leading to improved customer experiences on our platform.
Written in Haskell, Queryparser is Uber Engineering's open source tool for parsing and analyzing SQL queries that makes it easy to identify foreign-key relationships in large data warehouses.
Uber Engineering extended our anomaly detection platform's ability to integrate new forecast models, allowing this critical on-call service to scale to meet more complex use cases.
By leveraging neuroevolution to train deep neural networks, Uber AI Labs is developing solutions to solve reinforcement learning problems.
Gleaning Insights from Uber’s Partner Activity Matrix with Genomic Biclustering and Machine Learning
Uber Engineering's partner activity matrix leverages biclustering and machine learning to better understand the diversity of user experiences on our driver app.
In this article, we highlight how Uber leverages machine learning and artificial intelligence to tackle engineering challenges at scale.
Uber Engineering's data science workbench (DSW) is an all-in-one toolbox that leverages aggregate data for interactive analytics and machine learning.
Uber Engineering introduces Horovod, an open source framework that makes it faster and easier to train deep learning models with TensorFlow.
The UberEATS Restaurant Manager gives restaurant partners insight into their business by measuring customer satisfaction, sales, and service quality.
Uber Engineering introduces a new Bayesian neural network architecture that more accurately forecasts time series predictions and uncertainty estimations.
Uber Engineering introduces Michelangelo, our machine learning-as-a-service system that enables teams to easily build, deploy, and operate ML solutions at scale.
Uber Engineering’s Data Visualization team uses their deck.gl and Voyager visualization platforms to map rider behavior during the August 21, 2017 solar eclipse.
Uber Engineering's Data Visualization Team and ATG built a new web-based platform that helps engineers and operators better understand information collected during testing of its self-driving vehicles.
Snap your fingers and presto! How Uber Engineering built a fast, efficient data analytics system with Presto and Parquet.
Recurrent neural networks equip Uber Engineering's new forecasting model to more accurately predict rider demand during extreme events.
Composed of a staged rollout and intelligent analytics tool, Uber Engineering's experimentation platform is capable of stably deploying new features at scale across our apps. In this article, we discuss the challenges and opportunities we faced when building this product.
Uber Engineering debuts deck.gl 4.0, the latest version of our open source data visualization framework featuring enhanced geospatial exploration, a re-architected codebase, and more comprehensive documentation.
The engineering behind how Uber's Driving Safety team is using telematics to raise awareness of driving patterns to our partners.