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

2024-11-14

AI Summary

To address the inefficiency of preference elicitation in combinatorial auctions caused by combinatorial explosion of item bundles, this paper proposes MLHCA—a machine learning–enhanced iterative combinatorial auction mechanism. MLHCA is the first mechanism to theoretically unify value queries and demand queries, thereby overcoming the exponential growth bottleneck of traditional bundle spaces. It introduces the first practical, computationally efficient ML-driven framework for combinatorial auctions, integrating neural network–based bidder preference modeling, active query selection, and joint learning over dual-modal queries (value and demand). Experiments demonstrate that MLHCA reduces efficiency loss by up to 10× and cuts the number of queries by up to 58% compared to state-of-the-art methods. Consequently, it significantly alleviates bidders’ cognitive burden and provides a scalable, novel solution for large-scale combinatorial auctions.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 substantially 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.

Problem

• Iterative Combinatorial Auctions
• Efficiency Enhancement
• Information Processing

Innovation

• Machine Learning Hybrid Combinatorial Auction
• Efficiency Improvement
• Bidder Burden Reduction