Uber is in over 600+ cities (250+ for Uber Eats), 65 countries, and has completed over 10 billion rides. At such a scale, Uber continues to explore new frontiers and provide access to safe and reliable transportation for 75 million monthly active riders with 15 million trips every day, providing  opportunity for millions of drivers. Outside of rideshare, we are also foraying into new territories, such as Uber Eats, Uber Freight, and personal mobility devices. Our massive scale and global presence bring unique and challenging data science problems, and with great problems comes the need for top talent, diverse perspectives and an appetite for challenging the status quo.

This event is about celebrating and sharing some of the work done by data scientists at Uber. Attendees will learn about how we apply convolutional neural networks, recommendation engines, and behavior modeling to solve challenging problems at Uber. In addition, the event will feature a panel discussion and Q&A that will give audience members a firsthand look at what it's like to work in one of the largest data science organizations in the world on some of the field’s most interesting challenges.

This event is organized by WiSDOM (Women in Statistics, Data, Optimization and Machine learning), a community of and for women working in data at Uber.

6:00PM - Doors Open 
6:45PM - Introduction
7:00PM - Food Discovery with Uber Eats: Recommending for the Marketplace, Yuyan Wang
7:15PM - Doors Close
7:20PM - An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution, Rosanne Liu
7:40PM - Mediation Modeling at Uber: Understanding Why Product Changes Work (And Don't Work), Bonnie Li
8:00PM - Panel + Q&A
8:25PM - Mix & Mingle
9:00PM - Event Ends

Mediation Modeling at Uber: Understanding Why Product Changes Work (And Don't Work)

By: Bonnie Li

At Uber, we apply mediation modeling, a statistical approach from academic research, to address user pain points. Mediation modeling goes beyond simple cause and effect relationships in an attempt to understand what underlying mechanisms lead to a given result. Using this type of analysis, we can fine-tune product changes and develop new ones that focus on the underlying mechanisms behind successful features on the Uber platform.

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

By: Rosanne Liu
Convolution is prevalent in deep learning.  However, recent work from Uber AI unfolds one of its generic inabilities in transforming spatial representations between different types of coordinate systems. Such a finding as well as a subsequently revealed solution in the form of the CoordConv layer have proved to bring about improvements in a wide range of domains, including object detection, generative models, and reinforcement learning.

Food Discovery with Uber Eats: Recommending for the Marketplace

By: Yuyan Wang
The Uber Eats marketplace consists of three sides: eaters, restaurant-partners and delivery-partners. Ranking and recommending restaurants on Uber Eats is therefore a unique challenge, as each each side has intrinsic and different values that we need to take into consideration when optimizing for the marketplace. In this talk, we will go through the journey of ranking restaurants on the Uber Eats app, and zoom into the multi-objective optimization framework for our three-sided marketplace.