Blacklisting the Blacklist in Online Advertising
Yeming Shi, Ori Stitelman, Claudia Perlich (Dstillery)
Every day, billions of online advertising slots are bought and sold through real time bidding (RTB). In RTB, publishers sometimes reject bids to deliver ads (impressions) for some brands, due to, for example, direct deals with other brands. Publishers rarely dis- close which brands they blacklist to ad buyers. Buyers bidding for a blacklisted brand waste computing resources in a low latency envi- ronment and lose an opportunity to show a good ad for a dierent brand. Here we describe a dynamic system developed at Dstillery that detects these (publisher, brand) combinations based on ad auc- tion win rates and limits bidding for them to the minimum. This system demonstrates 1) a signicant increase in the win rates of our bids, 2) a sizable reduction of system load, and 3) eectiveness in nding qualied non-blacklisted brands to replace blacklisted brands to show ads for. The system allows us to deliver more ad impressions while making fewer bids. In addition, we develop and demonstrate a methodology of choosing the optimal exploration- exploitation balance of the problem.