Optimization of digital spend using machine learning in PyTorch
Who is this presentation for?Data scientists or analysts
When it comes to moving people and making deliveries, few companies are more widely spread and 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, it uses technology to give people what they want, when they want it.
Uber spends hundreds of millions of dollars in acquisition and retention, and it’s constantly optimizing the allocation of these budgets and performing experimentation. It uses AI in creative ways to improve the signal on A\B experiments and have better reads and insights; advance the segmentation of customers by propensity to act, churn, or open an email; cross-sell predictions; model resurrection and reactivation; use natural language to provide insights on content; and try loyalty programs.
Mario Vinasco explains how predictive models are used across these areas and how to think and interpret predictive models, what metrics Uber uses to evaluate these models, the tools and technologies it uses, and specific case studies in optimization and channel attribution.
- Familiarity with ML and digital marketing
What you'll learn
- Learn how to develop the intuition to apply ML models in practical marketing situations
Mario A. Vinasco
Mario Vinasco is a data science and optimization lead at Uber, where he’s responsible for customer management, retention, and prediction. The team conducts advanced segmentation of customers by propensity to act, churn, and open email, and he’s set up sophisticated experiments to test and validate hypotheses. He has over 15 years of progressive experience in data-driven analytics with an emphasis in database programming and machine learning creatively applied to ecommerce, advertising, customer acquisition and retention, and marketing investment. Mario specializes in developing and applying leading-edge business analytics to complex business problems using big data and predictive modeling platforms. Previously, he was a data scientist in the Consumer Marketing Group at Facebook, where he was responsible for improving the effectiveness of its consumer-facing campaigns and key projects included ad-effectiveness measurement of Facebook’s brand marketing activities and product campaigns for key product priorities using advanced experimentation techniques; vice president of business intelligence in a digital textbook startup; people analytics manager at Google; and ecommerce senior manager at Symantec. He holds a master’s degree in engineering economics from Stanford University.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
Premier Diamond Sponsors
Premier Exhibitor Plus
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires