Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All

Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56570-56614, 2025.

Abstract

We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address this, recent work has proposed machine learning (ML)-based preference elicitation algorithms that aim to elicit only the most critical information from bidders to maximize efficiency. However, while the SOTA ML-based algorithms elicit bidders’ preferences via value queries, ICAs that are used in practice elicit information via demand queries. In this paper, we introduce a novel ML algorithm that provably makes use of the full information from both value and demand queries, and we show via experiments that combining both query types results in significantly better learning performance in practice. Building on these insights, we present MLHCA, a new ML-powered auction that uses value and demand queries. MLHCA significantly outperforms the previous SOTA, reducing efficiency loss by up to a factor 10, with up to 58% fewer queries. Thus, MLHCA achieves large efficiency improvements while also reducing bidders’ cognitive load, establishing a new benchmark for both practicability and efficiency. Our code is available at https://github.com/marketdesignresearch/MLHCA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-soumalias25a, title = {Prices, Bids, Values: One {ML}-Powered Combinatorial Auction to Rule Them All}, author = {Soumalias, Ermis and Heiss, Jakob and Weissteiner, Jakob and Seuken, Sven}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {56570--56614}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/soumalias25a/soumalias25a.pdf}, url = {https://proceedings.mlr.press/v267/soumalias25a.html}, abstract = {We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address this, recent work has proposed machine learning (ML)-based preference elicitation algorithms that aim to elicit only the most critical information from bidders to maximize efficiency. However, while the SOTA ML-based algorithms elicit bidders’ preferences via value queries, ICAs that are used in practice elicit information via demand queries. In this paper, we introduce a novel ML algorithm that provably makes use of the full information from both value and demand queries, and we show via experiments that combining both query types results in significantly better learning performance in practice. Building on these insights, we present MLHCA, a new ML-powered auction that uses value and demand queries. MLHCA significantly outperforms the previous SOTA, reducing efficiency loss by up to a factor 10, with up to 58% fewer queries. Thus, MLHCA achieves large efficiency improvements while also reducing bidders’ cognitive load, establishing a new benchmark for both practicability and efficiency. Our code is available at https://github.com/marketdesignresearch/MLHCA.} }
Endnote
%0 Conference Paper %T Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All %A Ermis Soumalias %A Jakob Heiss %A Jakob Weissteiner %A Sven Seuken %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-soumalias25a %I PMLR %P 56570--56614 %U https://proceedings.mlr.press/v267/soumalias25a.html %V 267 %X We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address this, recent work has proposed machine learning (ML)-based preference elicitation algorithms that aim to elicit only the most critical information from bidders to maximize efficiency. However, while the SOTA ML-based algorithms elicit bidders’ preferences via value queries, ICAs that are used in practice elicit information via demand queries. In this paper, we introduce a novel ML algorithm that provably makes use of the full information from both value and demand queries, and we show via experiments that combining both query types results in significantly better learning performance in practice. Building on these insights, we present MLHCA, a new ML-powered auction that uses value and demand queries. MLHCA significantly outperforms the previous SOTA, reducing efficiency loss by up to a factor 10, with up to 58% fewer queries. Thus, MLHCA achieves large efficiency improvements while also reducing bidders’ cognitive load, establishing a new benchmark for both practicability and efficiency. Our code is available at https://github.com/marketdesignresearch/MLHCA.
APA
Soumalias, E., Heiss, J., Weissteiner, J. & Seuken, S.. (2025). Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:56570-56614 Available from https://proceedings.mlr.press/v267/soumalias25a.html.

Related Material