XiaoYu Wang
ABSTRACT
Guaranteed delivery (GD) and real-time bidding (RTB) constitute two parallel profit streams for the publisher. The diverse advertiser demands (brand or instant effect) result in different selling (in bulk or via auction) and pricing (fixed unit price or various bids) patterns, which naturally raises the fusion allocation issue of breaking the two markets' barrier and selling out at the global highest price boosting the total revenue. The fusion process complicates the competition between GD and RTB, and GD contracts with overlapping targeting. The non-stationary user traffic and bid landscape further worsen the situation, making the assignment unsupervised and hard to evaluate. Thus, a static policy or coarse-grained modeling from existing work is inferior to facing the above challenges.
This paper proposes CONFLUX, a fusion framework located at the confluence of the parallel GD and RTB markets. CONFLUX functions in a cascaded process: a paradigm is first forged via linear programming to supervise CONFLUX's training, then a cumbersome network distills such paradigm by precisely modeling the competition at a request level and further transfers the generalization ability to a lightweight student via knowledge distillation. Finally, fine-tuning is periodically executed at the online stage to remedy the student's degradation, and a temporal distillation loss between the current and the previous model serves as a regularizer to prevent over-fitting. The procedure is analogous to a cascade distillation and hence its name. CONFLUX has been deployed on the Tencent advertising system for over six months through extensive experiments. Online A/B tests present a lift of 3.29%, 1.77%, and 3.63% of ad income, overall click-through rate, and cost-per-mille, respectively, which jointly contribute a revenue increase by hundreds of thousands RMB per day. Our code is publicly available at https://github.com/zslomo/CONFLUX.
Supplemental Material
- Santiago R Balseiro, Jon Feldman, Vahab Mirrokni, and Shan Muthukrishnan. 2014. Yield Optimization of Display Advertising with Ad Exchange. Management Science 60, 12 (2014), 2886--2907.Google Scholar
Digital Library
- Vijay Bharadwaj, Peiji Chen, Wenjing Ma, Chandrashekhar Nagarajan, John Tomlin, Sergei Vassilvitskii, Erik Vee, and Jian Yang. 2012. SHALE: An Efficient Algorithm for Allocation of Guaranteed Display Advertising. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1195--1203.Google ScholarDigital Library
- Niv Buchbinder, Moran Feldman, Arpita Ghosh, and Joseph Naor. 2014. Frequency capping in online advertising. Journal of Scheduling 17, 4 (2014), 385--398.Google ScholarDigital Library
- Bowei Chen, Shuai Yuan, and Jun Wang. 2014. A Dynamic Pricing Model for Unifying Programmatic Guarantee and Real-time Bidding in Display Advertising. In Proceedings of the 8th International Workshop on Data Mining for Online Advertising. 1--9.Google ScholarDigital Library
- Peiji Chen, Wenjing Ma, Srinath Mandalapu, Chandrashekhar Nagarjan, Jayavel Shanmugasundaram, Sergei Vassilvitskii, Erik Vee, Manfai Yu, and Jason Zien. 2012. Ad Serving Using a Compact Allocation Plan. In Proceedings of the 13th ACM Conference on Electronic Commerce. 319--336.Google ScholarDigital Library
- Ye Chen, Pavel Berkhin, Bo Anderson, and Nikhil R Devanur. 2011. Real-time Bidding Algorithms for Performance-based Display Ad Allocation. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1307--1315.Google ScholarDigital Library
- Nikhil R Devanur and Thomas P Hayes. 2009. The Adwords Problem: Online Keyword Matching with Budgeted Bidders under Random Permutations. In Proceedings of the 10th ACM Conference on Electronic Commerce. 71--78.Google ScholarDigital Library
- Zhen Fang, Yang Li, Chuanren Liu, Wenxiang Zhu, Yu Zheng, and Wenjun Zhou. 2019. Large-Scale Personalized Delivery for Guaranteed Display Advertising with Real-Time Pacing. In IEEE International Conference on Data Mining (ICDM). 190--199.Google Scholar
- Arpita Ghosh, Preston McAfee, Kishore Papineni, and Sergei Vassilvitskii. 2009. Bidding for Representative Allocations for Display Advertising. In Internet and Network Economics, Stefano Leonardi (Ed.). Springer Berlin Heidelberg, Berlin, Heidelberg, 208--219.Google Scholar
- Yue He, Xiujun Chen, Di Wu, Junwei Pan, Qing Tan, Chuan Yu, Jian Xu, and Xiaoqiang Zhu. 2021. A Unified Solution to Constrained Bidding in Online Display Advertising. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2993--3001.Google ScholarDigital Library
- Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015).Google Scholar
- Ali Hojjat, John Turner, Suleyman Cetintas, and Jian Yang. 2014. Delivering guaranteed display ads under reach and frequency requirements. In Twenty- Eighth AAAI Conference on Artificial Intelligence.Google ScholarDigital Library
- Grégoire Jauvion and Nicolas Grislain. 2018. Optimal allocation of real-time-bidding and direct campaigns. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 416--424.Google ScholarDigital Library
- Zhizhong Li and Derek Hoiem. 2017. Learning Without Forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 12 (2017), 2935--2947.Google ScholarDigital Library
- Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, and Kun Gai. 2018. Entire Space Multi-task Model: An Effective Approach for Estimating Post-click Conversion Rate. In Proceedings of the 41st ACM International Conference on Research & Development in Information Retrieval. 1137--1140.Google ScholarDigital Library
- Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for Thin Deep Nets. arXiv preprint arXiv:1412.6550 (2014).Google Scholar
- Konstantin Salomatin, Tie-Yan Liu, and Yiming Yang. 2012. A Unified Optimization Framework for Auction and Guaranteed Delivery in Online Advertising. In Proceedings of the 21st ACM International Conference on Information and Knowledge Management. 2005--2009.Google ScholarDigital Library
- Frederick Tung and Greg Mori. 2019. Similarity-preserving Knowledge Distillation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1365--1374.Google ScholarCross Ref
- Erik Vee, Sergei Vassilvitskii, and Jayavel Shanmugasundaram. 2010. Optimal Online Assignment with Forecasts. In Proceedings of the 11th ACM Conference on Electronic Commerce. 109--118.Google ScholarDigital Library
- Ruoxi Wang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. 2021. DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems. In Proceedings of the Web Conference. 1785--1797.Google ScholarDigital Library
- Di Wu, Cheng Chen, Xiujun Chen, Junwei Pan, Xun Yang, Qing Tan, Jian Xu, and Kuang-Chih Lee. 2021. Impression Allocation and Policy Search in Display Advertising. In 2021 IEEE International Conference on Data Mining (ICDM). 749--756.Google Scholar
- Xun Yang, Yasong Li, Hao Wang, Di Wu, Qing Tan, Jian Xu, and Kun Gai. 2019. Bid Optimization by Multi-variable Control in Display Advertising. In Proceedings of the 25th ACM International Conference on Knowledge Discovery & Data Mining. 1966--1974.Google Scholar
- Jia Zhang, Zheng Wang, Qian Li, Jialin Zhang, Yanyan Lan, Qiang Li, and Xiaoming Sun. 2017. Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31.Google ScholarCross Ref
- Guorui Zhou, Ying Fan, Runpeng Cui, Weijie Bian, Xiaoqiang Zhu, and Kun Gai. 2018. Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
Index Terms
- CONFLUX: A Request-level Fusion Framework for Impression Allocation via Cascade Distillation
Recommendations
Pay-as-Bid: Selling Divisible Goods
EC '16: Proceedings of the 2016 ACM Conference on Economics and ComputationPay-as-bid auctions are frequently implemented when a single seller allocates multiple units of a homogeneous good, and are commonly used to sell treasury securities, allocate electricity generation, and distribute emissions credits. In this auction ...
Core-competitive Auctions
EC '15: Proceedings of the Sixteenth ACM Conference on Economics and ComputationOne of the major drawbacks of the celebrated VCG auction is its low (or zero) revenue even when the agents have high value for the goods and a competitive outcome would have generated a significant revenue. A competitive outcome is one for which it is ...
An empirical study of reserve price optimisation in real-time bidding
KDD '14: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data miningIn this paper, we report the first empirical study and live test of the reserve price optimisation problem in the context of Real-Time Bidding (RTB) display advertising from an operational environment. A reserve price is the minimum that the auctioneer ...
Comments