AI RESEARCH
Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness
arXiv CS.LG
•
ArXi:2605.12840v1 Announce Type: cross Marketplace platforms routinely evaluate pricing and allocation policies using logged observational data, yet strong offline performance does not imply that a policy is safe to deploy. In real-time bidding (RTB) marketplaces, reserve-price and floor-policy changes affect not only revenue but also fill, advertiser value, budget pacing, and competition across auctions, creating feedback and interference.