Feedback Control-Based Publisher Revenue Maximization in Online Advertising

Online publishers often monetize traffic on their webpages by selling ad inventory to advertisers via real-time bidding in open exchanges. Typically they leverage a
Supply Side Platform
(SSP) to sell the ad inventory. An SSP is a technology platform that enables publishers to manage their advertising space inventory, fill it with ads, and receive revenue. A state-of-the-art SSP solves an optimization problem, which in this letter is defined as publisher revenue maximization subject to a lower bound on the SSP margin. The optimal bidding mechanism is derived and it is shown how the solution can be implemented as two separate subsystems, publisher control and bid shading optimization. Feedback control plays an important role to make the optimization scalable and adaptive. A proof of concept control system is designed and illustrated in simulations.