Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions
This work addresses the challenge of aligning CTR predictions with business objectives like welfare in ad auctions, offering a practical solution for advertisers and platforms.
The paper tackles the problem of designing loss functions for click-through rate (CTR) prediction to optimize social welfare in ad auctions, proposing a novel weighted rankloss that provides provable welfare guarantees without distributional assumptions on eCPMs and demonstrates advantages on synthetic and real-world data.
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.