Toward Controlling Discrimination in Online Ad Auctions

Elisa Celis, Anay Mehrotra, Nisheeth Vishnoi
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4456-4465, 2019.

Abstract

Online advertising platforms are thriving due to the customizable audiences they offer advertisers. However, recent studies show that advertisements can be discriminatory with respect to the gender or race of the audience that sees the ad, and may inadvertently cross ethical and/or legal boundaries. To prevent this, we propose a constrained ad auction framework that maximizes the platform’s revenue conditioned on ensuring that the audience seeing an advertiser’s ad is distributed appropriately across sensitive types such as gender or race. Building upon Myerson’s classic work, we first present an optimal auction mechanism for a large class of fairness constraints. Finding the parameters of this optimal auction, however, turns out to be a non-convex problem. We show that this non-convex problem can be reformulated as a more structured non-convex problem with no saddle points or local-maxima; this allows us to develop a gradient-descent-based algorithm to solve it. Our empirical results on the A1 Yahoo! dataset demonstrate that our algorithm can obtain uniform coverage across different user types for each advertiser at a minor loss to the revenue of the platform, and a small change to the size of the audience each advertiser reaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-mehrotra19a, title = {Toward Controlling Discrimination in Online Ad Auctions}, author = {Celis, Elisa and Mehrotra, Anay and Vishnoi, Nisheeth}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {4456--4465}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/mehrotra19a/mehrotra19a.pdf}, url = {https://proceedings.mlr.press/v97/mehrotra19a.html}, abstract = {Online advertising platforms are thriving due to the customizable audiences they offer advertisers. However, recent studies show that advertisements can be discriminatory with respect to the gender or race of the audience that sees the ad, and may inadvertently cross ethical and/or legal boundaries. To prevent this, we propose a constrained ad auction framework that maximizes the platform’s revenue conditioned on ensuring that the audience seeing an advertiser’s ad is distributed appropriately across sensitive types such as gender or race. Building upon Myerson’s classic work, we first present an optimal auction mechanism for a large class of fairness constraints. Finding the parameters of this optimal auction, however, turns out to be a non-convex problem. We show that this non-convex problem can be reformulated as a more structured non-convex problem with no saddle points or local-maxima; this allows us to develop a gradient-descent-based algorithm to solve it. Our empirical results on the A1 Yahoo! dataset demonstrate that our algorithm can obtain uniform coverage across different user types for each advertiser at a minor loss to the revenue of the platform, and a small change to the size of the audience each advertiser reaches.} }
Endnote
%0 Conference Paper %T Toward Controlling Discrimination in Online Ad Auctions %A Elisa Celis %A Anay Mehrotra %A Nisheeth Vishnoi %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-mehrotra19a %I PMLR %P 4456--4465 %U https://proceedings.mlr.press/v97/mehrotra19a.html %V 97 %X Online advertising platforms are thriving due to the customizable audiences they offer advertisers. However, recent studies show that advertisements can be discriminatory with respect to the gender or race of the audience that sees the ad, and may inadvertently cross ethical and/or legal boundaries. To prevent this, we propose a constrained ad auction framework that maximizes the platform’s revenue conditioned on ensuring that the audience seeing an advertiser’s ad is distributed appropriately across sensitive types such as gender or race. Building upon Myerson’s classic work, we first present an optimal auction mechanism for a large class of fairness constraints. Finding the parameters of this optimal auction, however, turns out to be a non-convex problem. We show that this non-convex problem can be reformulated as a more structured non-convex problem with no saddle points or local-maxima; this allows us to develop a gradient-descent-based algorithm to solve it. Our empirical results on the A1 Yahoo! dataset demonstrate that our algorithm can obtain uniform coverage across different user types for each advertiser at a minor loss to the revenue of the platform, and a small change to the size of the audience each advertiser reaches.
APA
Celis, E., Mehrotra, A. & Vishnoi, N.. (2019). Toward Controlling Discrimination in Online Ad Auctions. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:4456-4465 Available from https://proceedings.mlr.press/v97/mehrotra19a.html.

Related Material