Personalization is a common theme in social networks and ecommerce businesses. Personalization at Uber involves an understanding of how each driver and rider is expected to behave on the platform. One way to quantify future behavior is to understand the number of trips a driver or rider will make.
Ankit Jain explains how Uber employs deep learning and its huge database to understand and predict the behavior of each and every user on the platform, focusing on training LSTMs for short-term trip predictions (4–6 weeks). Uber combines past engagement data of a particular driver with incentive budgets and uses a custom loss function (i.e., zero-inflated Poisson) to come up with accurate trip predictions using LSTMs. Join in to learn how predicting rider- and driver-level behaviors helps Uber find cohorts of high-performing drivers, run personalized offers to retain users, and understand deviations from trip forecasts.
Ankit Jain is a senior data scientist at Uber AI Labs, the machine learning research arm of Uber. His work primarily involves the application of deep learning methods to a variety of Uber’s problems, ranging from forecasting and food delivery to self-driving cars. Previously, he held a variety of data science roles at Bank of America, Facebook, and other startups. Ankit holds an MFE from UC Berkeley and a BS from IIT Bombay (India). Outside of his job, he likes to mentor students in data science, run marathons, and travel.
©2018, 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. • firstname.lastname@example.org