Analysis, Modeling, and Implementation of Publisher-side Ad Request Filtering

Online advertising has been a great driving force for the Internet industry. To maintain a steady growth of advertising revenue, advertisement (ad) publishers have made great efforts to increase the impressions as well as the conversion rate. However, we notice that the results of these efforts are not as good as expected. In detail, to show more ads to the consumers, publishers have to waste a significant amount of server resources to process the ad requests that do not result in consumers’ clicks. On the other hand, the increasing ads are also impacting the browsing experience of the consumers.In this paper, we explore the opportunity to improve publishers’ overall utility by handling a selective number of requests on ad servers. Particularly, we propose a publisher-side proactive ad request filtration solution Win2. Upon receiving an ad request, Win2 estimates the probability that the consumer will click if serving it. The ad request will be served if the clicking probability is above a dynamic threshold. Otherwise, it will be filtered to reduce the publisher’s resource cost and improve consumer experience. We implement Win2 in a large-scale ad serving system and the evaluation results confirm its effectiveness.

[1]  Heng Yin,et al.  Measuring and Disrupting Anti-Adblockers Using Differential Execution Analysis , 2018, NDSS.

[2]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[3]  Bo Li,et al.  On arbitrating the power-performance tradeoff in SaaS clouds , 2013, 2013 Proceedings IEEE INFOCOM.

[4]  Foster J. Provost,et al.  Scalable hands-free transfer learning for online advertising , 2014, KDD.

[5]  Joaquin Quiñonero Candela,et al.  Web-Scale Bayesian Click-Through rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine , 2010, ICML.

[6]  Vasudeva Varma,et al.  Learning the click-through rate for rare/new ads from similar ads , 2010, SIGIR.

[7]  Nicholas Kushmerick,et al.  Learning to remove Internet advertisements , 1999, AGENTS '99.

[8]  Subodha Kumar.  Optimization Issues in Web and Mobile Advertising: Past and Future Trends , 2015 .

[9]  Dan Wang,et al.  Communication-Aware Container Placement and Reassignment in Large-Scale Internet Data Centers , 2019, IEEE Journal on Selected Areas in Communications.

[10]  John A. Davis.  Cost per Action , 2012 .

[11]  Tie-Yan Liu,et al.  Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks , 2014, AAAI.

[12]  Silvia Gabrielli,et al.  A Review of Online Advertising Effects on the User Experience , 2010, Int. J. Hum. Comput. Interact..

[13]  Joseph Kaye,et al.  The Effect of Ad Blocking on User Engagement with the Web , 2018, WWW.

[14]  Piotr L. Szczepański,et al.  An Automated Framework with Application to Study Url Based Online Advertisements Detection , 2013 .

[15]  J. Grabara,et al.  The Impact of Ad-Blocking on the Sustainable Development of the Digital Advertising Ecosystem , 2018, Sustainability.

[16]  Dan Wang,et al.  TDFI: Two-stage Deep Learning Framework for Friendship Inference via Multi-source Information , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[17]  Yukihiro Tagami,et al.  CTR prediction for contextual advertising: learning-to-rank approach , 2013, ADKDD '13.

[18]  Yang Zhou,et al.  Multimedia features for click prediction of new ads in display advertising , 2012, KDD.

[19]  Shitong Zhu,et al.  ShadowBlock: A Lightweight and Stealthy Adblocking Browser , 2019, WWW.

[20]  Joseph D. Rumbo.  Consumer resistance in a world of advertising clutter: The case of Adbusters , 2002 .

[21]  Martin Wattenberg,et al.  Ad click prediction: a view from the trenches , 2013, KDD.

[22]  Olivier Chapelle,et al.  Modeling delayed feedback in display advertising , 2014, KDD.

[23]  Ke Xu,et al.  Understand Love of Variety in Wireless Data Market Under Sponsored Data Plans , 2020, IEEE Journal on Selected Areas in Communications.

[24]  Emiliano De Cristofaro,et al.  Adblocking and Counter Blocking: A Slice of the Arms Race , 2016, FOCI.

[25]  Dong Wang,et al.  Click-through Prediction for Advertising in Twitter Timeline , 2015, KDD.

[26]  Joel Waldfogel,et al.  The effect of ad blocking on website traffic and quality , 2018 .

[27]  Matthew Richardson,et al.  Predicting clicks: estimating the click-through rate for new ads , 2007, WWW '07.

[28]  Zheng Wang,et al.  Internet QoS: Architectures and Mechanisms for Quality of Service , 2001 .

[29]  Viktor Krammer,et al.  An Effective Defense against Intrusive Web Advertising , 2008, 2008 Sixth Annual Conference on Privacy, Security and Trust.

[30]  Benjamin Livshits,et al.  AdGraph: A Machine Learning Approach to Automatic and Effective Adblocking , 2018, ArXiv.

[31]  Chengjie Sun,et al.  Predicting ad click-through rates via feature-based fully coupled interaction tensor factorization , 2016, Electron. Commer. Res. Appl..

[32]  Guorui Zhou,et al.  Deep Interest Network for Click-Through Rate Prediction , 2017, KDD.

[33]  Justin P. Johnson.  Targeted Advertising and Advertising Avoidance , 2011 .

[34]  Joaquin Quiñonero Candela,et al.  Practical Lessons from Predicting Clicks on Ads at Facebook , 2014, ADKDD'14.

[35]  Xuerui Wang,et al.  Click-Through Rate Estimation for Rare Events in Online Advertising , 2011 .

[36]  Aleksandra Korolova,et al.  Facebook's Advertising Platform: New Attack Vectors and the Need for Interventions , 2018, ArXiv.

[37]  Yu Sun,et al.  Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising , 2018, WWW.

[38]  Dan Wang,et al.  Variety Matters: A New Model for the Wireless Data Market under Sponsored Data Plans , 2019, 2019 IEEE/ACM 27th International Symposium on Quality of Service (IWQoS).

[39]  Massoud Pedram,et al.  Resource allocation optimization in a data center with energy storage devices , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[40]  Ashish Gupta,et al.  High-Availability at Massive Scale: Building Google's Data Infrastructure for Ads , 2015, BIRTE.