Using AI in Marketing Analytics and Predictive Modeling

When it comes to moving people and making deliveries, few companies are more widely spread and more widely recognized than Uber. Uber is part of the logistics fabric of more than 700 cities around the world, and whether it's a ride, a sandwich, or a package, they use technology to give people what they want, when they want it.

Uber spends hundreds of millions of dollars in acquisition and retention and we are constantly optimizing the allocation of these budgets and performing experimentation.

We use AI in creative ways to:

- Improve the signal on AB experiments and have better reads and insights

- Advanced segmentation of customers by propensity to act, churn, open an email

- Cross sell predictions

- Models of resurrection and reactivation

- Natural Language to provide insights on content

- Loyalty programs

In this talk, I will discuss how predictive models are used across these areas:

- How to think and interpret predictive models

- What metrics we use to evaluate these models

- The tools and technologies we use

- Specific case studies in optimization, channel attribution

Speaker: Mario Vinasco, Uber Technologies