Abstract | ||
---|---|---|
We present the experiences from building a web-scale user modeling platform for optimizing display advertising targeting at Yahoo!. The platform described in this paper allows for per-campaign maximization of conversions representing purchase activities or transactions. Conversions directly translate to advertiser's revenue, and thus provide the most relevant metrics of return on advertising investment. We focus on two major challenges: how to efficiently process histories of billions of users on a daily basis, and how to build per-campaign conversion models given the extremely low conversion rates (compared to click rates in a traditional setting). We first present mechanisms for building web-scale user profiles in a daily incremental fashion. Second, we show how to reduce the latency through in-memory processing of billions of user records. Finally, we discuss a technique for scaling the number of handled campaigns/models by introducing an efficient labeling technique that allows for sharing negative training examples across multiple campaigns. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2187980.2187982 | WWW (Companion Volume) |
Keywords | Field | DocType |
per-campaign maximization,web-scale user profile,advertising investment,optimizing display advertising,daily incremental fashion,web-scale user modeling platform,user record,low conversion rate,web-scale user modeling,per-campaign conversion model,daily basis,user model,advertising,user modeling,behavioral targeting | Revenue,World Wide Web,Display advertising,Behavioral targeting,Computer science,Latency (engineering),User modeling,Maximization | Conference |
Citations | PageRank | References |
24 | 1.10 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohamed Aly | 1 | 139 | 6.47 |
Andrew Hatch | 2 | 24 | 1.10 |
Vanja Josifovski | 3 | 2265 | 148.84 |
Vijay K. Narayanan | 4 | 138 | 10.99 |