Contextual Procurement Auctions with Bandit Learning

2026-07-07

AI Summary

This work addresses the challenge of learning product valuations from noisy feedback in repeated contextual procurement auctions, while simultaneously ensuring incentive compatibility and minimizing social welfare loss. The authors propose two novel mechanisms: an Explore-then-Commit mechanism and a Frozen-Payments UCB mechanism, both enabling a tunable trade-off between incentive violation and social welfare regret. The former achieves a regret bound of Õ((ng)^{1/3}T^{2/3}), while the latter allows flexible balancing—via parameter tuning—between Õ(√(ngT)) regret and Õ(T^{3/4}) incentive error, or achieving both at Õ(T^{2/3}). Combining techniques from multi-armed bandits, contextual modeling, and mechanism design, the paper establishes corresponding lower bounds, demonstrating the near-optimality of the proposed approaches.

Abstract

We study repeated contextual procurement auctions in which the platform must learn context-dependent product values from bandit feedback. We give an exactly truthful explore-then-commit mechanism with $\widetilde O((ng)^{1/3}T^{2/3})$ regret. We also give a frozen-payment UCB mechanism with a regret-incentive tradeoff: the near-UCB tuning attains \(\widetilde O(\sqrt{ngT})\) welfare regret, while for fixed \(n,g\) its total incentive error is \(\widetilde O(T^{3/4})\); the balanced tuning gives \(\widetilde O(T^{2/3})\) on both scales. Regret is measured as welfare loss relative to the full-information efficient allocation. We prove a matching lower bound for the frozen-payment regret-incentive tradeoff.

Problem

• contextual procurement auctions
• bandit learning
• truthful mechanism
• regret-incentive tradeoff
• welfare regret

Innovation

• contextual procurement auctions
• bandit learning
• truthful mechanism
• regret-incentive tradeoff
• frozen-payment UCB