For 10+ years, the online advertising industry has been heavily dependent on machine learning algorithms to optimize auction dynamics. Buyers and sellers have relied on complex analyses of petabytes of data to set prices, floors, and other rules that govern the billions of auctions per day that fuel programmatic advertising. The increasing need to optimize results has been in conflict with the need for transparency. Buyers and sellers are questioning the "black box" nature of machine learning.

Kershaw's talk at DataScience: Elevate explores the history of algorithmic optimization in advertising and how to look for a happy medium between complexity and simplicity, as well as between optimization and transparency.