Online Market Making and the Value of Observing the Order Book

• URL: http://arxiv.org/abs/2605.19584v1
• Date: Tue, 19 May 2026 09:26:01 GMT
• Title: Online Market Making and the Value of Observing the Order Book
• Abstract summary: We study an online market-making problem in which a learner sequentially posts bid and ask prices for a single asset.<n>We introduce an action-dependent feedback model inspired by real limit order books.<n>We show that this additional information fundamentally changes the learnability of the problem.
• Score: 44.5487486690729
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study an online market-making problem in which a learner sequentially posts bid and ask prices for a single asset while interacting with traders holding private valuations. Unlike existing online learning formulations that assume fully censored feedback, we introduce an action-dependent feedback model inspired by real limit order books: when a trade occurs, the trader's valuation remains hidden, whereas when no trade occurs, informative feedback about supply and demand is revealed. We show that this additional information fundamentally changes the learnability of the problem. In the stochastic setting with i.i.d. market prices, we propose an elimination-based algorithm that achieves $O(\sqrt T)$ regret with high probability, without requiring any smoothness assumptions on the distribution of trader valuations. We then extend this result to a broad class of mean-reverting price processes by considering both local, autoregressive dynamics and a weaker global drift condition based on cumulative deviations from the mean. Under either assumption, we establish high-probability $O(\sqrt T)$ regret bounds, relying on a new concentration inequality of independent interest. Finally, in the adversarial setting with oblivious prices, we design an explore-then-perturb algorithm that guarantees $O(T^{2/3})$ regret in expectation. Our results quantify the value of observing the order book in online market making and demonstrate that even limited, action-dependent feedback can substantially improve regret guarantees compared to standard bandit feedback models.

Related papers

• Learning to Price and Stock Under Contextual and Censored Demand [5.326846590465264]
  We present a framework where we model demand as a linear combination of basis functions with unknown coefficients.<n>We propose an efficient algorithm to achieve regret bound $mathcalO(KsqrtTlog T)$ under concave revenue conditions and $mathcalO(K2/3T2/3(log T)1/2)$ for the general case.
  arXiv  Detail & Related papers  (2026-09-05T13:21:46Z)
• Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets [57.179679246370114]
  In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices.<n>During deployment, these agents trade in live markets where their own transactions can shift asset prices, a phenomenon known as market impact.<n>Traditional robust RL approaches address this model misspecification by optimizing the worst-case performance over a set of uncertainties.<n>We develop a novel class of elliptic uncertainty sets, enabling efficient and tractable robust policy evaluation.
  arXiv  Detail & Related papers  (2025-10-22T18:22:25Z)
• A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokerage [8.049531918823758]
  We study a contextual version of the repeated brokerage problem.<n>In each interaction, two traders with private valuations for an item seek to buy or sell based on the learner's-a broker-proposed price, which is informed by some contextual information.<n>The broker's goal is to maximize the traders' net utility-also known as the gain from trade-by minimizing regret compared to an oracle with perfect knowledge of traders' valuation distributions.
  arXiv  Detail & Related papers  (2025-03-03T08:42:55Z)
• Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents [69.58565132975504]
  Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks.<n>We present the Agent Trading Arena, a virtual zero-sum stock market in which LLM-based agents engage in competitive multi-agent trading.
  arXiv  Detail & Related papers  (2025-02-25T08:41:01Z)
• Minimax Optimality in Contextual Dynamic Pricing with General Valuation Models [8.981637739384674]
  We study contextual dynamic pricing, where a decision maker posts personalized prices based on observable contexts.<n>Each valuation is modeled as an unknown latent function of the context, corrupted by independent and identically distributed market noise.
  arXiv  Detail & Related papers  (2024-06-24T23:43:56Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• Equilibrium of Data Markets with Externality [5.383900608313559]
  We model real-world data markets, where sellers post fixed prices and buyers are free to purchase from any set of sellers. A key component here is the negative externality buyers induce on one another due to data purchases. We prove that platforms intervening through a transaction cost can lead to a pure equilibrium with strong welfare guarantees.
  arXiv  Detail & Related papers  (2023-02-16T00:57:49Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design [158.0041488194202]
  We study reserve price optimization in multi-phase second price auctions. From the seller's perspective, we need to efficiently explore the environment in the presence of potentially nontruthful bidders. Third, the seller's per-step revenue is unknown, nonlinear, and cannot even be directly observed from the environment.
  arXiv  Detail & Related papers  (2022-10-19T03:49:05Z)
• Distribution-free Contextual Dynamic Pricing [5.773269033551628]
  Contextual dynamic pricing aims to set personalized prices based on sequential interactions with customers. In this paper, we consider contextual dynamic pricing with unknown random noise in the valuation model. Our distribution-free pricing policy learns both the contextual function and the market noise simultaneously.
  arXiv  Detail & Related papers  (2021-09-15T14:52:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.