Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?

Ashwinkumar Badanidiyuru
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:4802-4819, 2026.

Abstract

Online advertising platforms rely on machine learning models to predict click-through rates (pCTR) and conversion rates (pCVR) for auction mechanisms. We introduce a novel framework to study the interaction between recommender system model quality, auction format, and autobidder behavior. We formalize when model improvements—defined via a refinement relation inspired by filtrations in probability theory—lead to improvements in platform-level Evaluation Criteria Metrics (ECM) such as revenue, welfare, or liquid welfare. Our main contributions are: (1) a formal definition of model improvement based on cluster refinement, and (2) a systematic characterization of ECM monotonicity across different combinations of bidder types (tCPA, max-CPA), auction formats (first-price, second-price, VCG), and budget constraints. We show that first-price auctions with uniform bidding guarantee revenue monotonicity for tCPA bidders without budgets (via Jensen’s inequality), while second-price auctions and budget constraints can break this property. We provide full numerical constructions for the non-monotonicity results. Our findings have practical implications for advertising platforms seeking to align model improvements with business outcomes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-badanidiyuru26a, title = {Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?}, author = {Badanidiyuru, Ashwinkumar}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {4802--4819}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/badanidiyuru26a/badanidiyuru26a.pdf}, url = {https://proceedings.mlr.press/v306/badanidiyuru26a.html}, abstract = {Online advertising platforms rely on machine learning models to predict click-through rates (pCTR) and conversion rates (pCVR) for auction mechanisms. We introduce a novel framework to study the interaction between recommender system model quality, auction format, and autobidder behavior. We formalize when model improvements—defined via a refinement relation inspired by filtrations in probability theory—lead to improvements in platform-level Evaluation Criteria Metrics (ECM) such as revenue, welfare, or liquid welfare. Our main contributions are: (1) a formal definition of model improvement based on cluster refinement, and (2) a systematic characterization of ECM monotonicity across different combinations of bidder types (tCPA, max-CPA), auction formats (first-price, second-price, VCG), and budget constraints. We show that first-price auctions with uniform bidding guarantee revenue monotonicity for tCPA bidders without budgets (via Jensen’s inequality), while second-price auctions and budget constraints can break this property. We provide full numerical constructions for the non-monotonicity results. Our findings have practical implications for advertising platforms seeking to align model improvements with business outcomes.} }
Endnote
%0 Conference Paper %T Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes? %A Ashwinkumar Badanidiyuru %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-badanidiyuru26a %I PMLR %P 4802--4819 %U https://proceedings.mlr.press/v306/badanidiyuru26a.html %V 306 %X Online advertising platforms rely on machine learning models to predict click-through rates (pCTR) and conversion rates (pCVR) for auction mechanisms. We introduce a novel framework to study the interaction between recommender system model quality, auction format, and autobidder behavior. We formalize when model improvements—defined via a refinement relation inspired by filtrations in probability theory—lead to improvements in platform-level Evaluation Criteria Metrics (ECM) such as revenue, welfare, or liquid welfare. Our main contributions are: (1) a formal definition of model improvement based on cluster refinement, and (2) a systematic characterization of ECM monotonicity across different combinations of bidder types (tCPA, max-CPA), auction formats (first-price, second-price, VCG), and budget constraints. We show that first-price auctions with uniform bidding guarantee revenue monotonicity for tCPA bidders without budgets (via Jensen’s inequality), while second-price auctions and budget constraints can break this property. We provide full numerical constructions for the non-monotonicity results. Our findings have practical implications for advertising platforms seeking to align model improvements with business outcomes.
APA
Badanidiyuru, A.. (2026). Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:4802-4819 Available from https://proceedings.mlr.press/v306/badanidiyuru26a.html.

Related Material