Machine Learning-Powered Combinatorial Clock Auction
Ermis Soumalias, Jakob Weissteiner, Jakob Heiss, Sven Seuken

TL;DR
This paper introduces a practical machine learning-powered combinatorial clock auction that uses demand queries instead of value queries, significantly improving efficiency and reducing rounds in spectrum auction domains.
Contribution
It presents a novel ML method for demand query elicitation and an efficient approach to identify high-potential demand queries, bridging the gap between research and practical auction design.
Findings
Outperforms traditional CCA in efficiency across multiple domains
Achieves higher efficiency with fewer rounds
Exhibits higher clearing potential using linear prices
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, several papers have recently proposed machine learning (ML)-based preference elicitation algorithms that aim to elicit only the most important information from bidders. However, from a practical point of view, the main shortcoming of this prior work is that those designs elicit bidders' preferences via value queries (i.e., ``What is your value for the bundle ?''). In most real-world ICA domains, value queries are considered impractical, since they impose an unrealistically high cognitive burden on bidders, which is why they are not used in practice. In this paper, we address this shortcoming by designing an ML-powered combinatorial clock auction that elicits information from the bidders only via…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAuction Theory and Applications · Stock Market Forecasting Methods
MethodsIndependent Component Analysis
