Uplift Modeling for Driving Incremental Revenue by Display Remarketing

Abstract: Traditional marketing campaigns target customers based on their response rate, and thus may not target people for whom the campaigns are most profitable. In contrast, uplift modeling predicts the causal effect of marketing campaigns by comparing the conversion rates of both treatment and control groups, and thus selects the most incremental customers to target. The Wayfair marketing data science team has been using uplift modeling to drive incremental revenue by optimizing our display remarketing to the right customers. The user-level prediction for incrementality, combined with click-through rate prediction, generates Wayfair’s real-time bidding algorithms to send our display remarketing Ads to the right people at the right time in the right place across Internet.

Bio: Jen Wang received her Ph.D. in Biophysical Chemistry from the University of Iowa, where she researched cancer-related drug development. Though a far cry from her work at Wayfair today, her work as a grad student and subsequently, a post-doc at Albert Einstein College of Medicine in New York, gave her the opportunity to cultivate a deep interest and expertise in the rich predictive capabilities of machine learning. In 2016, she joined Wayfair's data science team, where she now leads a team that supports display remarketing. In her session, she will discuss how data scientists at Wayfair take data-driven approaches and leverage uplift modeling to drive incremental revenue

Open Data Science Conference