Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions

Boxiang Lyu, Zhe Feng, Zachary Robertson, Sanmi Koyejo
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23239-23263, 2023.

Abstract

We study the design of loss functions for click-through rates (CTR) to optimize (social) welfare in advertising auctions. Existing works either only focus on CTR predictions without consideration of business objectives (e.g., welfare) in auctions or assume that the distribution over the participants’ expected cost-per-impression (eCPM) is known a priori, then use various additional assumptions on the parametric form of the distribution to derive loss functions for predicting CTRs. In this work, we bring back the welfare objectives of ad auctions into CTR predictions and propose a novel weighted rankloss to train the CTR model. Compared to existing literature, our approach provides a provable guarantee on welfare but without assumptions on the eCPMs’ distribution while also avoiding the intractability of naively applying existing learning-to-rank methods. Further, we propose a theoretically justifiable technique for calibrating the losses using labels generated from a teacher network, only assuming that the teacher network has bounded $\ell_2$ generalization error. Finally, we demonstrate the advantages of the proposed loss on synthetic and real-world data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-lyu23b, title = {Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions}, author = {Lyu, Boxiang and Feng, Zhe and Robertson, Zachary and Koyejo, Sanmi}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {23239--23263}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/lyu23b/lyu23b.pdf}, url = {https://proceedings.mlr.press/v202/lyu23b.html}, abstract = {We study the design of loss functions for click-through rates (CTR) to optimize (social) welfare in advertising auctions. Existing works either only focus on CTR predictions without consideration of business objectives (e.g., welfare) in auctions or assume that the distribution over the participants’ expected cost-per-impression (eCPM) is known a priori, then use various additional assumptions on the parametric form of the distribution to derive loss functions for predicting CTRs. In this work, we bring back the welfare objectives of ad auctions into CTR predictions and propose a novel weighted rankloss to train the CTR model. Compared to existing literature, our approach provides a provable guarantee on welfare but without assumptions on the eCPMs’ distribution while also avoiding the intractability of naively applying existing learning-to-rank methods. Further, we propose a theoretically justifiable technique for calibrating the losses using labels generated from a teacher network, only assuming that the teacher network has bounded $\ell_2$ generalization error. Finally, we demonstrate the advantages of the proposed loss on synthetic and real-world data.} }
Endnote
%0 Conference Paper %T Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions %A Boxiang Lyu %A Zhe Feng %A Zachary Robertson %A Sanmi Koyejo %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-lyu23b %I PMLR %P 23239--23263 %U https://proceedings.mlr.press/v202/lyu23b.html %V 202 %X We study the design of loss functions for click-through rates (CTR) to optimize (social) welfare in advertising auctions. Existing works either only focus on CTR predictions without consideration of business objectives (e.g., welfare) in auctions or assume that the distribution over the participants’ expected cost-per-impression (eCPM) is known a priori, then use various additional assumptions on the parametric form of the distribution to derive loss functions for predicting CTRs. In this work, we bring back the welfare objectives of ad auctions into CTR predictions and propose a novel weighted rankloss to train the CTR model. Compared to existing literature, our approach provides a provable guarantee on welfare but without assumptions on the eCPMs’ distribution while also avoiding the intractability of naively applying existing learning-to-rank methods. Further, we propose a theoretically justifiable technique for calibrating the losses using labels generated from a teacher network, only assuming that the teacher network has bounded $\ell_2$ generalization error. Finally, we demonstrate the advantages of the proposed loss on synthetic and real-world data.
APA
Lyu, B., Feng, Z., Robertson, Z. & Koyejo, S.. (2023). Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:23239-23263 Available from https://proceedings.mlr.press/v202/lyu23b.html.

Related Material