Spending Programmed Bidding: Privacy-friendly Bid Optimization with ROI Constraint in Online Advertising

Privacy policies have disrupted the multi-billion dollar online advertising market by making real-time and precise user data untraceable, which poses significant challenges to the optimization of Return-On-Investment (ROI) constrained products in the online advertising industry. Privacy protection strategies, including event aggregation and reporting delays, hinder access to detailed and instantaneous feedback data, thus incapacitating traditional identity-revealing attribution techniques. In this paper, we introduces a novel Spending Programmed Bidding (SPB) framework to navigate these challenges. SPB is a two-stage framework that separates long horizon delivery spend planning (the macro stage) and short horizon bidding execution (the micro stage). The macro stage models the target ROI to achieve maximum utility and derives the expected spend, whereas the micro stage optimizes the bid price given the expected spend. We further extend our framework to the cross-channel scenario where the agent bids in both privacy-constrained and identity-revealing attribution channels. We find that when privacy-constrained channels are present, SPB is superior to state-of-the-art bidding methods in both offline datasets and online experiments on a large ad platform.