Skip to main content
Data / ML

Engineering More Reliable Transportation with Machine Learning and AI at Uber

November 10, 2017 / Global
Featured image for Engineering More Reliable Transportation with Machine Learning and AI at Uber
Image
Attendees listen to presentations during our Uber Machine Learning Meetup on September 12, 2017.
Figure 1: A visualization highlights trips originating from Uber’s HQ block in San Francisco.
Figure 2: Destination prediction ranking leverages various features and along with a gradient boosted decision tree to provide destination suggestions to riders.
Figure 3: A spatio-temporal stream-processing engine, along with custom models, powers the generation of billions of real-time forecasts every minute.
Figure 4: Dispatch matching leverages a thousands of features to generate thousands of predictions in sub-second timing.
Figure 5: Uber’s Marketplace organization industrializes machine learning by building  systems that learn with scale.
Figure 6: Our customizable NLP platform enables Data Scientists to rapidly build models for chatbots, sentiment analysis, and rapid response for support tickets.
Figure 7: Uber’s anomaly detection platform helps our engineering teams to maximize the actionable on-call alerts.
Figure 8: The anatomy of an Uber ATG self-driving car includes LiDAR sensors, cameras, antenna for GPS positioning, compute and storage, and radar.
Figure 9: Multiple inputs are used for training along with intermediate feedback loops to build learning for end-to-end self-driving.
Figure 10: Time-aggregated views create denser information and temporal features for algorithms focused on safety.
Chintan Turakhia

Chintan Turakhia

Chintan Turakhia is an engineering manager on Uber's Marketplace team.

Posted by Chintan Turakhia

Category: