Online Budget-Feasible Mechanism Design with Predictions

2025-05-30

AI Summary

This paper studies budget-feasible online procurement auction design: a buyer with a strict budget constraint seeks to maximize a (monotone or non-monotone) submodular utility function over strategically rational, randomly arriving sellers. We introduce the prediction-augmented paradigm into budget-feasible mechanism design for the first time, proposing an online mechanism that simultaneously guarantees truthfulness and budget feasibility, achieving a significantly improved competitive ratio over prediction-agnostic mechanisms under the random-arrival model. Theoretically, we establish that predictions can substantially enhance online performance, yet cannot improve the best-known approximation ratios in the offline setting—thereby characterizing the fundamental limits of prediction efficacy. Our approach integrates online stochastic algorithms, submodular optimization, and prediction-augmented mechanism design, balancing consistency and robustness. This work establishes a novel paradigm for strategic, budget-constrained online procurement.

Technology Category

• Game Theory and Economic Paradigms: Mechanism Design
• Machine Learning: Online Learning & Bandits
• Multiagent Systems: Mechanism Design

Application Category

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

Abstract

Augmenting the input of algorithms with predictions is an algorithm design paradigm that suggests leveraging a (possibly erroneous) prediction to improve worst-case performance guarantees when the prediction is perfect (consistency), while also providing a performance guarantee when the prediction fails (robustness). Recently, Xu and Lu [2022] and Agrawal et al. [2024] proposed to consider settings with strategic agents under this framework. In this paper, we initiate the study of budget-feasible mechanism design with predictions. These mechanisms model a procurement auction scenario in which an auctioneer (buyer) with a strict budget constraint seeks to purchase goods or services from a set of strategic agents, so as to maximize her own valuation function. We focus on the online version of the problem where the arrival order of agents is random. We design mechanisms that are truthful, budget-feasible, and achieve a significantly improved competitive ratio for both monotone and non-monotone submodular valuation functions compared to their state-of-the-art counterparts without predictions. Our results assume access to a prediction for the value of the optimal solution to the offline problem. We complement our positive results by showing that for the offline version of the problem, access to predictions is mostly ineffective in improving approximation guarantees.

Problem

• Designing truthful budget-feasible online mechanisms with predictions
• Improving competitive ratios for submodular valuations using predictions
• Evaluating prediction effectiveness in offline procurement auction settings

Innovation

• Online budget-feasible mechanism design with predictions
• Truthful mechanisms for strategic agents
• Improved competitive ratio using predictions