Oct 2023· Neural Information Processing Systems· Vol abs/2310.20096· 17 citations· 50 references
Computer Science
TL;DR
The experiments demonstrate that this new deep learning framework can almost precisely replicate all known solutions from theory, expand to more complex settings, and be used to establish the optimality of new designs for data markets and make conjectures in regard to the structure of optimal designs.
Abstract
The data market design problem is a problem in economic theory to find a set of signaling schemes (statistical experiments) to maximize expected revenue to the information seller, where each experiment reveals some of the information known to a seller and has a corresponding price [Bergemann et al., 2018]. Each buyer has their own decision to make in a world environment, and their subjective expected value for the information associated with a particular experiment comes from the improvement in this decision and depends on their prior and value for different outcomes. In a setting with multiple buyers, a buyer's expected value for an experiment may also depend on the information sold to others [Bonatti et al., 2022]. We introduce the application of deep learning for the design of revenue-optimal data markets, looking to expand the frontiers of what can be understood and achieved. Relative to earlier work on deep learning for auction design [D\"utting et al., 2023], we must learn signaling schemes rather than allocation rules and handle obedience constraints $-$ these arising from modeling the downstream actions of buyers $-$ in addition to incentive constraints on bids. Our experiments demonstrate that this new deep learning framework can almost precisely replicate all known solutions from theory, expand to more complex settings, and be used to establish the optimality of new designs for data markets and make conjectures in regard to the structure of optimal designs.
This work considers 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 and gives the first FPTAS to compute a scheme that maxim...
This paper develops a machine learning approach for training such agents to act effectively as sellers in a multi-item bargaining environment, where a seller concurrently negotiates a catalog of substitutable assets across a pool of independent buyers.
S. Liu, Claire Chen, Jiuqi Wang et al.· 1 citation
Learning to Price in Two-Sided Markets
Many two-sided platforms set purchase prices for sellers and selling prices for buyers. In “Two-Sided Pricing and Learning with Buyer Choice: A Generalized SGD Method,” Lin and Huh study how platforms can make these decisions when responses on both sides are uncertain and must be...
Mei-Chun Lin, W. T. Huh· Operational Research· 0 citations
To commit to buying external data or participate in collaborative learning, one must decide whether the additional data will improve prediction enough to justify the cost. This comes with several challenges: (i) the decision often relies only on aggregated statistics available publicly, rather than individual-level dat...
Filip Kovacevic, Edwige Cyffers, Stefano Sarao Mannelli et al.· 0 citations
We consider a data seller who designs pricing mechanisms over multiple datasets to maximize revenue from budget-constrained buyers. The seller offers multiple datasets and assigns each a pricing function that maps the quantity purchased to a total payment. The goal is to design these pricing functions to maximize reven...
B. Chaudhury, Jugal Garg, Eklavya Sharma et al.· 0 citations