Uncertainty Quantification of Click and Conversion Estimates for the Autobidding

Ivan Zhigalskii, Andrey Pudovikov, Aleksandr Katrutsa, Egor Samosvat
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:8253-8269, 2026.

Abstract

Modern e-commerce platforms employ various auction mechanisms to allocate paid slots for a given item. To scale this approach to the millions of auctions, the platforms suggest promotion tools based on the autobidding algorithms. These algorithms typically depend on the Click-Through-Rate (CTR) and Conversion-Rate (CVR) estimates provided by a pre-trained machine learning model. However, the predictions of such models are uncertain and can significantly affect the performance of the autobidding algorithm. To address this issue, we propose the $\texttt{DenoiseBid}$ method, which corrects the generated CTRs and CVRs to make the resulting bids more efficient in auctions. The underlying idea of our method is to employ a {Bayesian} approach and replace noisy CTR or CVR estimates with those from recovered distributions. To demonstrate the performance of the proposed approach, we perform extensive experiments on the synthetic, iPinYou, and BAT datasets. To evaluate the robustness of our approach to the noise scale, we use synthetic noise and noise estimated from the predictions of the pre-trained machine learning model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-zhigalskii26a, title = {Uncertainty Quantification of Click and Conversion Estimates for the Autobidding}, author = {Zhigalskii, Ivan and Pudovikov, Andrey and Katrutsa, Aleksandr and Samosvat, Egor}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {8253--8269}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/zhigalskii26a/zhigalskii26a.pdf}, url = {https://proceedings.mlr.press/v337/zhigalskii26a.html}, abstract = {Modern e-commerce platforms employ various auction mechanisms to allocate paid slots for a given item. To scale this approach to the millions of auctions, the platforms suggest promotion tools based on the autobidding algorithms. These algorithms typically depend on the Click-Through-Rate (CTR) and Conversion-Rate (CVR) estimates provided by a pre-trained machine learning model. However, the predictions of such models are uncertain and can significantly affect the performance of the autobidding algorithm. To address this issue, we propose the $\texttt{DenoiseBid}$ method, which corrects the generated CTRs and CVRs to make the resulting bids more efficient in auctions. The underlying idea of our method is to employ a {Bayesian} approach and replace noisy CTR or CVR estimates with those from recovered distributions. To demonstrate the performance of the proposed approach, we perform extensive experiments on the synthetic, iPinYou, and BAT datasets. To evaluate the robustness of our approach to the noise scale, we use synthetic noise and noise estimated from the predictions of the pre-trained machine learning model.} }
Endnote
%0 Conference Paper %T Uncertainty Quantification of Click and Conversion Estimates for the Autobidding %A Ivan Zhigalskii %A Andrey Pudovikov %A Aleksandr Katrutsa %A Egor Samosvat %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-zhigalskii26a %I PMLR %P 8253--8269 %U https://proceedings.mlr.press/v337/zhigalskii26a.html %V 337 %X Modern e-commerce platforms employ various auction mechanisms to allocate paid slots for a given item. To scale this approach to the millions of auctions, the platforms suggest promotion tools based on the autobidding algorithms. These algorithms typically depend on the Click-Through-Rate (CTR) and Conversion-Rate (CVR) estimates provided by a pre-trained machine learning model. However, the predictions of such models are uncertain and can significantly affect the performance of the autobidding algorithm. To address this issue, we propose the $\texttt{DenoiseBid}$ method, which corrects the generated CTRs and CVRs to make the resulting bids more efficient in auctions. The underlying idea of our method is to employ a {Bayesian} approach and replace noisy CTR or CVR estimates with those from recovered distributions. To demonstrate the performance of the proposed approach, we perform extensive experiments on the synthetic, iPinYou, and BAT datasets. To evaluate the robustness of our approach to the noise scale, we use synthetic noise and noise estimated from the predictions of the pre-trained machine learning model.
APA
Zhigalskii, I., Pudovikov, A., Katrutsa, A. & Samosvat, E.. (2026). Uncertainty Quantification of Click and Conversion Estimates for the Autobidding. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:8253-8269 Available from https://proceedings.mlr.press/v337/zhigalskii26a.html.

Related Material