Randomly Wrong Signals: Bayesian Auction Design with ML Predictions

2026-10-15 · ArXiv

arXiv:2502.08792v4 Announce Type: replace-cross

Abstract: Machine learning can help sellers predict buyers' willingness to pay, but its predictions may be plausible and yet entirely unrelated to a buyer's value. We introduce a Bayesian auction model that distinguishes such hallucinations from ordinary measurement noise. We characterize revenue-maximizing auctions with publicly disclosed predictions in the benchmark where informative predictions are exact. For a single buyer, this characterization explains when the seller should follow a prediction and when to hedge against its failure by ignoring it or capping the price. These insights guide the design of simple auctions that account for both hallucinations and measurement noise. Numerical experiments show that the resulting auctions achieve near-optimal revenue.

原文链接：https://arxiv.org/abs/2502.08792

查看更多资讯请见 AI 行业资讯。