Abstract: 

With the rapid advancement in technology within online advertising, marketers are required to turn to black-box algorithms to implement effective ad buying and targeting strategies. In this talk, I focus on how Data Science at Wayfair balances causal and predictive modeling techniques to build our display retargeting bidding AI. Using evidence from a large scale field experiment, we utilize a two-stage least squares regression to model the marginal impact of a single impression. Comparing the causal model to a simple predictive model, we demonstrate that merely maximizing the predictive power of an algorithm can potentially lead to undesirable results for the business.

Bio: 

Bradley is a Data Scientist at Wayfair, the largest online-only furniture retailer in the U.S., where he builds machine learning models to better understand how marketing can best solve consumer problems. Specifically, he’s working on the bidding and targeting algorithms which power Waystack, Wayfair’s internal ad-serving platform. He earned an MBA and is finishing his Ph.D. in Quantitative Marketing Strategy at Arizona State University.