Two-stage Auction Design in Online Advertising
Modern online advertising systems often involve a substantial number of advertisers in each auction, which results in scalability issues. To address this challenge, two-stage auctions have been designed and implemented in practice. These auctions enable efficient allocation of ad slots among numerous candidate advertisers in a short response time. This approach employs a fast yet coarse model in the first stage to select a small subset of advertisers, followed by a slow, more refined model to determine the final winners. However, existing two-stage auction mechanisms primarily focus on optimizing welfare, overlooking other critical objectives of the platform, such as revenue.
Authors
- Weiran Shen (ORCID: https://orcid.org/0000-0003-4366-9276)
- Ruo-Yu Wang
- Qi Ye (ORCID: https://orcid.org/0009-0006-5907-5746)
- Lan Hu
- Zhikang Fan (ORCID: https://orcid.org/0000-0001-5026-2269)
- Zhongrui Ma (ORCID: https://orcid.org/0009-0002-5907-1607)
- Yue Wang (ORCID: https://orcid.org/0000-0003-4258-9856)
Institutions
- Huawei Technologies (China) (CN)
- Renmin University of China (CN)
Publication Details
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1145/3696410.3714735
- Citations
- 1
- Primary Topic
- Consumer Market Behavior and Pricing
- Type
- article
- Field-Weighted Citation Impact
- 2.07
Funders
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities