Ad allocation with secondary metrics

Darja Krushevskaja, William Simpson, Shan Muthukrishnan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Motivated by Online Ad allocation with advertisers that pursue multiple objectives, we introduce and study a problem of Ad Allocation with Secondary Metrics. For instance, advertisers pay per click which is the primary metric the platforms optimize for, but require the average cost of a conversion -the secondary metric -to be below some threshold. This is an explicit option for Facebook advertisers. Further, even when this is not an explicit option and the advertisers can only configure pay per click campaigns, sales teams often negotiate with advertisers in terms of expected conversion thresholds and this becomes the implicit secondary metric for the ad platform or the sales teams. We study this problem under both market and advertiser perspectives. • (Market Perspective) We adopt the per-impression auctioning approach used in the industry and propose modified sorting and allocation rules for the auction that explicitly take into account the secondary metric performance. We run the algorithm in an industrial setting on live traffic in a large ad network1. We find a significant impact on the realized secondary metrics without compromising primary metrics. For instance, the linear scoring function gives 30% lift on secondary metric and was selected as a default allocation algorithm in the ad network. • (Advertiser Perspective) We present an efficient dynamic programming algorithm that calculates the best response strategy for each advertiser. We implement and test this solution on offline impression data and compute strategies for advertisers. We find that for a fraction of advertisers, we could not find non empty allocation. We cross check this result with the online results, and find that 92% of these ads did not meet their target conversions. This suggests that these ads may have unrealistic expectations.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE International Conference on Big Data, Big Data 2016
EditorsRonay Ak, George Karypis, Yinglong Xia, Xiaohua Tony Hu, Philip S. Yu, James Joshi, Lyle Ungar, Ling Liu, Aki-Hiro Sato, Toyotaro Suzumura, Sudarsan Rachuri, Rama Govindaraju, Weijia Xu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1202-1211
Number of pages10
ISBN (Electronic)9781467390040
DOIs
StatePublished - Jan 1 2016
Event4th IEEE International Conference on Big Data, Big Data 2016 - Washington, United States
Duration: Dec 5 2016Dec 8 2016

Publication series

NameProceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

Other

Other4th IEEE International Conference on Big Data, Big Data 2016
CountryUnited States
CityWashington
Period12/5/1612/8/16

Fingerprint

Sales
Dynamic programming
Sorting
Costs
Industry

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Hardware and Architecture

Cite this

Krushevskaja, D., Simpson, W., & Muthukrishnan, S. (2016). Ad allocation with secondary metrics. In R. Ak, G. Karypis, Y. Xia, X. T. Hu, P. S. Yu, J. Joshi, L. Ungar, L. Liu, A-H. Sato, T. Suzumura, S. Rachuri, R. Govindaraju, ... W. Xu (Eds.), Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016 (pp. 1202-1211). [7840724] (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData.2016.7840724
Krushevskaja, Darja ; Simpson, William ; Muthukrishnan, Shan. / Ad allocation with secondary metrics. Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. editor / Ronay Ak ; George Karypis ; Yinglong Xia ; Xiaohua Tony Hu ; Philip S. Yu ; James Joshi ; Lyle Ungar ; Ling Liu ; Aki-Hiro Sato ; Toyotaro Suzumura ; Sudarsan Rachuri ; Rama Govindaraju ; Weijia Xu. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1202-1211 (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016).
@inproceedings{346c3fa5f6fc4ea28b7044d029d376e8,
title = "Ad allocation with secondary metrics",
abstract = "Motivated by Online Ad allocation with advertisers that pursue multiple objectives, we introduce and study a problem of Ad Allocation with Secondary Metrics. For instance, advertisers pay per click which is the primary metric the platforms optimize for, but require the average cost of a conversion -the secondary metric -to be below some threshold. This is an explicit option for Facebook advertisers. Further, even when this is not an explicit option and the advertisers can only configure pay per click campaigns, sales teams often negotiate with advertisers in terms of expected conversion thresholds and this becomes the implicit secondary metric for the ad platform or the sales teams. We study this problem under both market and advertiser perspectives. • (Market Perspective) We adopt the per-impression auctioning approach used in the industry and propose modified sorting and allocation rules for the auction that explicitly take into account the secondary metric performance. We run the algorithm in an industrial setting on live traffic in a large ad network1. We find a significant impact on the realized secondary metrics without compromising primary metrics. For instance, the linear scoring function gives 30{\%} lift on secondary metric and was selected as a default allocation algorithm in the ad network. • (Advertiser Perspective) We present an efficient dynamic programming algorithm that calculates the best response strategy for each advertiser. We implement and test this solution on offline impression data and compute strategies for advertisers. We find that for a fraction of advertisers, we could not find non empty allocation. We cross check this result with the online results, and find that 92{\%} of these ads did not meet their target conversions. This suggests that these ads may have unrealistic expectations.",
author = "Darja Krushevskaja and William Simpson and Shan Muthukrishnan",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/BigData.2016.7840724",
language = "English (US)",
series = "Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1202--1211",
editor = "Ronay Ak and George Karypis and Yinglong Xia and Hu, {Xiaohua Tony} and Yu, {Philip S.} and James Joshi and Lyle Ungar and Ling Liu and Aki-Hiro Sato and Toyotaro Suzumura and Sudarsan Rachuri and Rama Govindaraju and Weijia Xu",
booktitle = "Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016",
address = "United States",

}

Krushevskaja, D, Simpson, W & Muthukrishnan, S 2016, Ad allocation with secondary metrics. in R Ak, G Karypis, Y Xia, XT Hu, PS Yu, J Joshi, L Ungar, L Liu, A-H Sato, T Suzumura, S Rachuri, R Govindaraju & W Xu (eds), Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016., 7840724, Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016, Institute of Electrical and Electronics Engineers Inc., pp. 1202-1211, 4th IEEE International Conference on Big Data, Big Data 2016, Washington, United States, 12/5/16. https://doi.org/10.1109/BigData.2016.7840724

Ad allocation with secondary metrics. / Krushevskaja, Darja; Simpson, William; Muthukrishnan, Shan.

Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. ed. / Ronay Ak; George Karypis; Yinglong Xia; Xiaohua Tony Hu; Philip S. Yu; James Joshi; Lyle Ungar; Ling Liu; Aki-Hiro Sato; Toyotaro Suzumura; Sudarsan Rachuri; Rama Govindaraju; Weijia Xu. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1202-1211 7840724 (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Ad allocation with secondary metrics

AU - Krushevskaja, Darja

AU - Simpson, William

AU - Muthukrishnan, Shan

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Motivated by Online Ad allocation with advertisers that pursue multiple objectives, we introduce and study a problem of Ad Allocation with Secondary Metrics. For instance, advertisers pay per click which is the primary metric the platforms optimize for, but require the average cost of a conversion -the secondary metric -to be below some threshold. This is an explicit option for Facebook advertisers. Further, even when this is not an explicit option and the advertisers can only configure pay per click campaigns, sales teams often negotiate with advertisers in terms of expected conversion thresholds and this becomes the implicit secondary metric for the ad platform or the sales teams. We study this problem under both market and advertiser perspectives. • (Market Perspective) We adopt the per-impression auctioning approach used in the industry and propose modified sorting and allocation rules for the auction that explicitly take into account the secondary metric performance. We run the algorithm in an industrial setting on live traffic in a large ad network1. We find a significant impact on the realized secondary metrics without compromising primary metrics. For instance, the linear scoring function gives 30% lift on secondary metric and was selected as a default allocation algorithm in the ad network. • (Advertiser Perspective) We present an efficient dynamic programming algorithm that calculates the best response strategy for each advertiser. We implement and test this solution on offline impression data and compute strategies for advertisers. We find that for a fraction of advertisers, we could not find non empty allocation. We cross check this result with the online results, and find that 92% of these ads did not meet their target conversions. This suggests that these ads may have unrealistic expectations.

AB - Motivated by Online Ad allocation with advertisers that pursue multiple objectives, we introduce and study a problem of Ad Allocation with Secondary Metrics. For instance, advertisers pay per click which is the primary metric the platforms optimize for, but require the average cost of a conversion -the secondary metric -to be below some threshold. This is an explicit option for Facebook advertisers. Further, even when this is not an explicit option and the advertisers can only configure pay per click campaigns, sales teams often negotiate with advertisers in terms of expected conversion thresholds and this becomes the implicit secondary metric for the ad platform or the sales teams. We study this problem under both market and advertiser perspectives. • (Market Perspective) We adopt the per-impression auctioning approach used in the industry and propose modified sorting and allocation rules for the auction that explicitly take into account the secondary metric performance. We run the algorithm in an industrial setting on live traffic in a large ad network1. We find a significant impact on the realized secondary metrics without compromising primary metrics. For instance, the linear scoring function gives 30% lift on secondary metric and was selected as a default allocation algorithm in the ad network. • (Advertiser Perspective) We present an efficient dynamic programming algorithm that calculates the best response strategy for each advertiser. We implement and test this solution on offline impression data and compute strategies for advertisers. We find that for a fraction of advertisers, we could not find non empty allocation. We cross check this result with the online results, and find that 92% of these ads did not meet their target conversions. This suggests that these ads may have unrealistic expectations.

UR - http://www.scopus.com/inward/record.url?scp=85015205217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015205217&partnerID=8YFLogxK

U2 - 10.1109/BigData.2016.7840724

DO - 10.1109/BigData.2016.7840724

M3 - Conference contribution

AN - SCOPUS:85015205217

T3 - Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

SP - 1202

EP - 1211

BT - Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

A2 - Ak, Ronay

A2 - Karypis, George

A2 - Xia, Yinglong

A2 - Hu, Xiaohua Tony

A2 - Yu, Philip S.

A2 - Joshi, James

A2 - Ungar, Lyle

A2 - Liu, Ling

A2 - Sato, Aki-Hiro

A2 - Suzumura, Toyotaro

A2 - Rachuri, Sudarsan

A2 - Govindaraju, Rama

A2 - Xu, Weijia

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Krushevskaja D, Simpson W, Muthukrishnan S. Ad allocation with secondary metrics. In Ak R, Karypis G, Xia Y, Hu XT, Yu PS, Joshi J, Ungar L, Liu L, Sato A-H, Suzumura T, Rachuri S, Govindaraju R, Xu W, editors, Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1202-1211. 7840724. (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016). https://doi.org/10.1109/BigData.2016.7840724