From determining the most convenient rider pickup points to predicting the fastest routes, Uber uses machine learning and data-driven analytics to create seamless trip experiences. Inside Uber, big data and machine learning are used everywhere.
Uber’s analysts and engineers wanted to run real-time analytics with deep learning models. But copying data from one source to another is pretty expensive, and it’s challenging to support real-time analytics with deep learning.
Zhenxiao Luo explains how Uber supports real-time analytics with deep learning on the fly, without any data copying. He starts with the company’s big data and deep learning infrastructure, specifically TensorFlow, Hadoop, and Presto. He outlines how Uber uses TensorFlow as a deep learning engine and Presto as the interactive SQL engine, and then details how Uber built a Presto TensorFlow connector from scratch to support real-time analytics on deep learning. He concludes by sharing the company’s production experience and roadmap.
Zhenxiao Luo is leading Interactive Query Engines team at Twitter, where he focuses on Druid, Presto, Spark, and Hive. Before joining Twitter, Zhenxiao was running Interactive Analytics team at Uber. He has big data experience at Netflix, Facebook, Cloudera, and Vertica. Zhenxiao is PrestoDB committer. He holds a master’s degree from the University of Wisconsin-Madison and a bachelor’s degree from Fudan University.
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com