The paper tackles the data market design problem, which seeks signaling schemes that maximize revenue for an information seller. It applies deep learning to learn these schemes, addressing both obedience and incentive constraints, and demonstrates that the framework can replicate known theoretical solutions, extend to more complex scenarios, and suggest new optimal designs. The study builds on prior auction‑design work and introduces a novel approach for revenue‑optimal data markets.
By Sai Srivatsa Ravindranath, Yanchen Jiang, David C. Parkes
FastCombo is a deep reinforcement learning method for iterative combinatorial auctions that learns price policies offline and applies them online with a single neural‑network forward pass. By formulating the problem as a partially observable Markov decision process, it assigns credit to queries that enable future decisions, thereby reducing the expected number of auction rounds. Experiments show that FastCombo achieves competitive clearing while cutting online price‑selection time by roughly 300–900 times compared to a standard Bayesian baseline.
By Luis F. Paul Tosta, Quinn Arnold, Gianluca Brero
arXiv:2608. 16699v1 Announce Type: cross 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.
By Maria-Florina Balcan, Tejas Pagare, Karan Singh
arXiv:2610.22516v1 Announce Type: cross
Abstract: In modern commerce, firms and platforms typically use customer features from different sources to personalize prices: some features are verified usin...
By Jinjiang Zou, Yang Li, Zemin Zheng
arXiv:2604. 05845v2 Announce Type: replace-cross Abstract: Auto-bidding services optimize real-time bidding strategies for advertisers under key performance indicator (KPI) constraints such as target return on investment and budget.
By Linghui Meng, Chun Gan, Shengsheng Niu, Chengcheng Zhang, Chenchen Li, Chuan Yang, Yi Mao, Xin Zhu, Jie He, Zhangang Lin, Ching Law
The paper introduces LLM‑Auction, a learning‑based generative auction mechanism that integrates ad allocation with large language model (LLM) generation. It redefines the auction object from discrete ad slots to distributions over LLM outputs, aligning allocation with advertiser value and user experience while inherently modeling allocation externalities without extra inference cost. The authors prove allocation monotonicity and continuity, show a first‑price payment rule has favorable incentive properties, and demonstrate state‑of‑the‑art allocation efficiency in a simulated LLM‑as‑a‑judge environment.
By Chujie Zhao, Qun Hu, Shiping Song, Dagui Chen, Han Zhu, Jian Xu, Bo Zheng
The paper introduces a scalable framework that uses decentralized markets of self‑interested agents to solve multi‑step tasks. It shows that when agents compete through sequential auctions, perfect competition fails because clones drive profits to zero, while no competition also collapses value extraction. By allowing heterogeneous agents to shade bids strategically, the authors demonstrate that imperfect competition can sustain profitable margins while still achieving high task success rates at low costs, evaluating four bidding algorithms across three auction protocols.
By Ian Gemp, Shubhendu Trivedi, Adam Fisch, Fantine Huot, Michael Kaisers, Mirella Lapata, William W. Cohen, Alekh Agarwal, Kate Larson, Jacob Eisenstein
arXiv:2606. 28943v1 Announce Type: cross Abstract: Learning to bid in repeated multi-unit auctions with bandit feedback poses a fundamental challenge.
By Junhan Li, Yuxin Zhang, Haoran Wang, Minghao Chen
arXiv:2304. 14385v4 Announce Type: replace-cross Abstract: We consider a novel pricing and advertising framework in which a seller not only sets the product price but also designs flexible advertising schemes to influence customers' valuations of the product.
By Shipra Agrawal, Yiding Feng, Wei Tang
arXiv:2608. 00123v1 Announce Type: cross Abstract: LLM-native advertising embeds sponsored content directly into model-generated responses, shifting the unit of sale from a fixed slot to a moment within an evolving conversation.
By Yan Fang, Jialin Chen, Chun Gan, Hang Yu, Mingjun Nie, Yeyu Zhang, Fengxiang He, Ching Law
arXiv:2606. 05363v1 Announce Type: cross Abstract: On a platform with many sellers, should a pricing algorithm explicitly model competitors' prices when learning demand?
By Yuhang Wu, Assaf Zeevi
The paper extends the Expected Cost-per-Mille (eCPM) framework to handle auction and hybrid "Auction with Buy It Now" (ABIN) listings by deriving a marginal eCPM (meCPM) that captures the incremental value of showing an additional impression for items whose prices evolve dynamically. This unified ranking objective allows fixed-price, auction, and ABIN listings to be compared and ranked together. A production implementation was tested via online A/B experiments on a large e-commerce platform, yielding positive revenue gains and statistically significant improvements in user metrics, leading to deployment in production.
By Greg Kocher, Sanjana Arun