Learning to Price with Persuasion
2026-08-17 • Computer Science and Game Theory
Computer Science and Game TheoryMachine Learning
AI summaryⓘ
The authors study a market setup where sellers not only set prices but also provide information to buyers about how well a product fits their tastes. They explore how sellers can learn to create the best combination of pricing and information-sharing strategies when they don't know what buyers believe about their own preferences. The study includes methods for learning from past buyer data and from observing buyers' reactions over time. Despite the problem being complex, the authors provide an efficient algorithm to find nearly optimal strategies that maximize seller revenue. This work connects learning theory with economic design in markets where sellers and buyers have different information.
mechanism designinformation designsignaling schemeeconomic theoryrevenue maximizationbuyer preferenceslearning theoryonline learningFPTASasymmetric information
Authors
Maria-Florina Balcan, Tejas Pagare, Karan Singh
Abstract
Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al. (2022), where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers' behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was left open by Bergemann et al. (2022). Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information.