Volume 16, Issue 2 (Journal of Control, V.16, N.2 Summer 2022)                   JoC 2022, 16(2): 69-87 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Divsalar M, Babazadeh M, Nobakhti A. Statistical Modeling of Ad Campaigns in Online Advertising Systems. JoC 2022; 16 (2) :69-87
URL: http://joc.kntu.ac.ir/article-1-893-en.html
1- Sharif University of Technology
Abstract:   (1825 Views)
In this paper, statistical modeling of online advertising systems is addressed. The proposed model relies on the highest bidding price estimation in an auction network and the click-through rate estimation of the ad campaign. The estimation problem is faced with serious challenges due to the extremely time-varying and nonlinear behavior of users, the competitive behavior of the ad campaigns, and the variety of strategies incorporated by the demand-side platforms. Accordingly, estimation algorithms based on Kalman filtering may fail to provide reliable solutions in a real-time setting. In this paper, particle filtering is utilized to estimate the probability distribution of the highest bidding price. Advertisers observe the highest bidding price only if they win the auction. Otherwise, they do not have access to the highest bidding price. Thus, a biconditional update rule is proposed for the particles. The weighting scheme modifies the posterior distribution in case of winning or losing the auction. Next, the click-through rate of the ad campaign is introduced based on the Bayesian estimation. Since the user response is extremely variable over time, an adaptation rule is proposed to update the forgetting factor and the level of emphasis on the recent observations. Finally, by estimation of the highest bidding price and the click-through rate distributions, the input-output model of the ad campaign is developed. The input is the bidding signal or the control signal and the output is the total number of winning impressions for the campaign. The results are reported for a campaign with four individual segments and confirm that the proposed statistical approach can provide a reliable model for ad campaigns.
 
Full-Text [PDF 1311 kb]   (164 Downloads)    
Type of Article: Research paper | Subject: Special
Received: 2021/08/19 | Accepted: 2022/03/10 | ePublished ahead of print: 2022/04/13

References
1. [1] S. Yuan, J. Wang, X. Zhao, "Real-time Bidding for Online Advertising: Measurement and Analysis," in Proceedings of the Seventh International Workshop on Data Mining for Online Advertising, 2013. [DOI:10.1145/2501040.2501980]
2. [2] K Ren, W Zhang, Y Rong, H Zhang, Y Yu, J. Wang, "User response learning for directly optimizing campaign performance in display advertising," Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, p. 679-688, 2016. [DOI:10.1145/2983323.2983347]
3. [3] J. Xu, X. Shao, J. Ma, K. Lee, H. Qi, Q. Lu, "Lift-based bidding in ad selection," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1, 2016. [DOI:10.1609/aaai.v30i1.10025]
4. [4] N. Karlsson and J. Zhang,, "Applications of feedback control in online advertising," in American Control Conference, 2013. [DOI:10.1109/ACC.2013.6580779]
5. [5] J. Gittins, K. Glazebrook, and R. Weber, Multi-armed bandit allocation indices, John Wiley & Sons, 2011. [DOI:10.1002/9780470980033]
6. [6] N Karlsson, "Control problems in online advertising and benefits of randomized bidding strategies," European Journal of Control, vol 6, pp. 31-49, 2016. [DOI:10.1016/j.ejcon.2016.04.007]
7. [7] J. Guo, N. Karlsson, , "Model Reference Adaptive Control of Advertising Systems," American Control Conference, 2017. [DOI:10.23919/ACC.2017.7963807]
8. [8] Q. Sang, N. Karlsson, J. Guo,, "Feedback Control of Event Rate in Online Advertising Campaigns," Control Engineering Practice, vol 75, p. 126-136, 2018. [DOI:10.1016/j.conengprac.2018.03.010]
9. [9] N. Karlsson, "Adaptive estimation of small event rates," in 55th Conference on Decision and Control (CDC), 2016. [DOI:10.1109/CDC.2016.7798831]
10. [10] W. Zhang, Y. Rong, J. Wang, T. Zhu, X. Wang, "Feedback Control of Real-Time Display Advertising," in ACM International Conference on Web Search and Data Mining, 2016. [DOI:10.1145/2835776.2835843]
11. [11] X. Yang, Y. Li, H. Wang, D. Wu, Q. Tan, J. Xu, K. Gai, "Bid Optimization by Multivariable Control in Display Advertising," in ACM International Conference on Knowledge Discovery & Data Mining, 2019. [DOI:10.1145/3292500.3330681]
12. [12] N. Karlsson, "Feedback Control in Programmatic Advertising: The Frontier of Optimization in Real-Time Bidding," IEEE Control Systems Magazine, vol 40, no 5, pp. 40-77, 2020. [DOI:10.1109/MCS.2020.3005013]
13. [13] Z. Pooranian, M. Conti, H. Haddadi, R. Tafazolli, "Online Advertising Security: Issues, Taxonomy, and Future Directions," IEEE Communications Surveys & Tutorials, vol 23, no 4, pp. 2494-2524, 2021. [DOI:10.1109/COMST.2021.3118271]
14. [14] R. Myerson, "Optimal auction design," Mathematics of operations research, vol. 6, no. 1, pp. 58-73, 1981. [DOI:10.1287/moor.6.1.58]
15. [15] N. Karlsson and Q. Sang, "Adaptive Bid Shading Optimization of First-Price Ad Inventory," در American Control Conference, 2021. [DOI:10.23919/ACC50511.2021.9482665]
16. [16] T. Zhou, H. He, S. Pan, N. Karlsson, B. Shetty, B. Kitts, "Zhou, T., He, H., Pan, S., Karlsson, N., Shetty, B., Kitts, B., ... & Flores, A. (2021, August). An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions.," in In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data, 2021. [DOI:10.1145/3447548.3467167]
17. [17] N. Karlsson, "Plant gain estimation in online advertising processes," in IEEE 56th Annual Conference on Decision and Control (CDC), 2017. [DOI:10.1109/CDC.2017.8263968]
18. [18] V. Mardanlou, N. Karlsson, J. Guo, "Statistical Plant Modeling and Simulation in Online Advertising," in American Control Conference, 2017. [DOI:10.23919/ACC.2017.7963275]
19. [19] J. Jin, C. Song, H. Li, K. Gai, J. Wang, W. Zhang, "Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising," in ACM International Conference on Information and Knowledge Management, 2018. [DOI:10.1145/3269206.3272021]
20. [20] X. Zhao, C. Gu, H. Zhang, X. Yang, X. Liu, H. Liu, J. Tang, "DEAR: Deep Reinforcement Learning for Online Advertising Impression," in AAAI Conference on Artificial Intelligence, 2020. [DOI:10.1609/aaai.v35i1.16156]
21. [21] M. Bompaire, A. Gilotte, B. Heymann, "Causal models for real time bidding with repeated user interactions," in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021. [DOI:10.1145/3447548.3467280]
22. [22] S. Sluis, "Everything you need to know about bid shading," https://www.adexchanger.com/, 2019.
23. [23] N. Karlsson, "Adaptive control using heisenberg bidding," in American Control Conference, 2014. [DOI:10.1109/ACC.2014.6859107]
24. [24] J. Candy, Bayesian signal processing: classical, modern, and particle filtering methods, John Wiley & Sons, 2016. [DOI:10.1002/9781119125495]

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2023 CC BY-NC 4.0 | Journal of Control

Designed & Developed by : Yektaweb