[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124650-en":3,"doc-seo-124650-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124650,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Machine Learning-powered Combinatorial Clock Auction","Iterative combinatorial auctions face a key difficulty: the bundle space expands exponentially with the number of items, making full preference elicitation infeasible. Existing ML-driven elicitation methods improve efficiency but rely on value queries, which are impractical in real ICA deployments due to excessive bidder cognitive burden. This work proposes an ML-powered combinatorial clock auction that uses only demand queries, and introduces a demand-query training method plus a clearing-potential optimization with theory.","Machine Learning-powered Combinatorial Clock Auction  \nErmis Soumalias 1,3 * , Jakob Weissteiner 1,3 * , Jakob Heiss2,3 , Sven Seuken 1,3  \n1University of Zurich  \n2ETH Zurich  \n3ETH AI Center  \nermis@ifi.uzh.ch, weissteiner@ifi.uzh.ch, jakob.heiss@math.ethz.ch, seuken@ifi.uzh.ch  \narXiv :2308 . 10226v1 [ cs .GT] 20 Aug 2023  \nAbstract  \nWe 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 {A, B}?”) . 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 demand queries (i.e.,“At prices p, what is your most preferred bundle of items?”) . We make two key technical contributions: First, we present a novel method for training an ML model on demand queries. Second, based on those trained ML models, we introduce an efficient method for determining the demand query with the highest clearing potential, for which we also provide a theoretical foundation. We experimentally evaluate our ML-based demand query mechanism in several spectrum auction domains and compare it against the most established real-world ICA: the combinatorial clock auction (CCA) . Our mechanism significantly outperforms the CCA in terms of efficiency in all domains, it achieves higher efficiency in a significantly reduced number of rounds, and, using linear prices, it exhibits vastly higher clearing potential. Thus, with this paper we bridge the gap between research and practice and propose the first practical ML-powered ICA.  \n1 Introduction  \nCombinatorial auctions (CAs) are used to allocate multiple items among several bidders who may view those items as complements or substitutes. In a CA, bidders are allowed to submit bids over bundles of items. CAs have enjoyed widespread adoption in practice, with their applications ranging from allocating spectrum licences (Cramton 2013) to TV ad slots (Goetzendorff et al. 2015) and airport landing/take-off slots (Rassenti, Smith, and Bulfin 1982) .  \nOne of the key challenges in CAs is that the bundle space  \ngrows exponentially in the number of items, making it in-*These authors contributed equally.  \nfeasible for bidders to report their full value function in all but the smallest domains. Moreover, Nisan and Segal (2006) showed that for general value functions, CAs require an exponential number of bids in order to achieve full efficiency in the worst case. Thus, practical CA designs cannot provide efficiency guarantees in real world settings with more than a modest number of items. Instead, the focus has shifted towards iterative combinatorial auctions (ICAs), where bidders interact with the auctioneer over a series of rounds, providing a limited amount of information, and the aim of the auctioneer is to find a highly efficient allocation.  \nThe most established mechanism following this interaction paradigm is the combinatorial clock auction (CCA)(Ausubel, Cramton, and Milgrom 2006) . The CCA has been used extensively for spectrum allocation, generating over $20 Billion in revenue between 2012 and 2014 alone (Ausubel and Baranov 2017) . Speed of convergence is a critical consideration for any ICA since each round can entail costly computations and business modelling for the bidders (Kwasnica et al. 2005 ; Milgrom and Segal 2017 ; Bichler, Hao, and Adomavicius 201","cbCaig5sw9yfz8jA","https://ap.wps.com/l/cbCaig5sw9yfz8jA","pdf",1207101,1,26,"English","en",105,"# Abstract\n# Introduction\n## Combinatorial auctions and iterative interaction\n## ML-powered preference elicitation","[{\"question\":\"Why is preference elicitation difficult in iterative combinatorial auctions?\",\"answer\":\"The number of possible bundles grows exponentially with the number of items, making it infeasible to elicit full value functions from bidders.\"},{\"question\":\"What limitation of prior ML-based ICA methods is addressed in this paper?\",\"answer\":\"Prior approaches rely on value queries about bundle values, which impose an unrealistically high cognitive burden on bidders and are therefore often impractical.\"},{\"question\":\"How does the proposed ML-powered combinatorial clock auction improve practice relevance?\",\"answer\":\"It elicits bidder information only via demand queries, and it introduces methods for training ML models on demand queries and selecting the demand query with the highest clearing potential.\"}]","Machine Learning-powered Combinatorial Clock Auction | PDF",1785893527,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-powered-combinatorial-clock-auction","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-powered-combinatorial-clock-auction/124650/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is preference elicitation difficult in iterative combinatorial auctions?","Question",{"text":75,"@type":76},"The number of possible bundles grows exponentially with the number of items, making it infeasible to elicit full value functions from bidders.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitation of prior ML-based ICA methods is addressed in this paper?",{"text":80,"@type":76},"Prior approaches rely on value queries about bundle values, which impose an unrealistically high cognitive burden on bidders and are therefore often impractical.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed ML-powered combinatorial clock auction improve practice relevance?",{"text":84,"@type":76},"It elicits bidder information only via demand queries, and it introduces methods for training ML models on demand queries and selecting the demand query with the highest clearing potential.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]