Online marketplaces will be transformed by autonomous AI agents acting on behalf of consumers. Rather than humans browsing and clicking, AI agents can parse webpages or interact through APIs to evaluate products, and transact. This raises a fundamental question: what do AI agents buy—and why? We develop ACES, a sandbox environment that pairs a platform-agnostic agent with a fully programmable mock marketplace to study this. We first explore aggregate choices, revealing that modal choices can differ across models, with AI agents sometimes concentrating on a few products, raising competition questions. We then analyze the current drivers of choices through randomized experiments on product positions and listing attributes. Models show sizeable and heterogeneous position effects: all favor the top row, yet different models prefer different columns, undermining the assumption of a universal ''top'' rank. They penalize sponsored tags, reward endorsements, and sensitivities to price, ratings, and reviews are directionally as expected, but vary sharply across models. Our findings reveal how AI agents behave in e-commerce, and surface concrete monitoring, seller strategy, platform design, and regulatory questions.

In today's digital world, interaction with online platforms is ubiquitous, and thus content moderation is important for protecting users from content that do not comply with pre-established community guidelines. Given the vast volume of content generated online daily, having an efficient content moderation system throughout every stage of planning is particularly important. We study the short-term planning problem of allocating human content reviewers to different harmful content categories. We use tools from fair division and study the application of competitive equilibrium and leximin allocation rules for addressing this problem. On top of the traditional Fisher market setup, we additionally incorporate novel aspects that are of practical importance. The first aspect is the forecasted workload of different content categories, which puts constraints on the allocation chosen by the planner. We show how a formulation that is inspired by the celebrated Eisenberg-Gale program allows us to find an allocation that not only satisfies the forecasted workload, but also fairly allocates the remaining working hours from the content reviewers among all content categories. A fair allocation of oversupply provides a guardrail in cases where the actual workload deviates from the predicted workload. The second practical consideration is time dependent allocation that is motivated by the fact that partners need scheduling guidance for the reviewers across days to achieve efficiency. To address the time component, we introduce new extensions of the various fair allocation approaches for the single-time period setting, and we show that many properties extend in essence, albeit with some modifications. Lastly, related to the time component, we additionally investigate how to satisfy markets' desire for smooth allocation (i.e, an allocation that does not vary much from time to time) so that the switch in staffing is minimized. We demonstrate the performance of our proposed approaches through real-world data obtained from Meta.

We study the following fundamental data-driven pricing problem. How can/should a decision-maker price its product based on observations at a single historical price? The decision-maker optimizes over (potentially randomized) pricing policies to maximize the worst-case ratio of the revenue it can garner compared to an oracle with full knowledge of the distribution of values, when the latter is only assumed to belong to broad non-parametric set. In particular, our framework applies to the widely used regular and monotone non-decreasing hazard rate (mhr) classes of distributions. For settings where the seller knows the exact probability of sale associated with one historical price or only a confidence interval for it, we fully characterize optimal performance and near-optimal pricing algorithms that adjust to the information at hand. As examples, against mhr distributions, we show that it is possible to guarantee $85%$ of oracle performance if one knows that half of the customers have bought at the historical price, and if only $1%$ of the customers bought, it still possible to guarantee $51%$ of oracle performance. The framework we develop leads to new insights on the value of information for pricing, as well as the value of randomization. In addition, it is general and allows to characterize optimal deterministic mechanisms and incorporate uncertainty in the probability of sale.

In the present paper, we study the following fundamental problem: how should a decision-maker price based on a finite and limited number of samples from the distribution of values of customers. The decision-maker's objective is to select a pricing policy with maximum competitive ratio when the value distribution is only known to belong to some general non-parametric class. We study achievable performance for two central classes, regular and monotone hazard rate (mhr) distributions, through a general framework. To date, only results are available for a single sample and two samples. We improve existing results but also obtain the first results on achievable performance as the number of samples increases. At a higher level, this work also provides insights on the value of samples for pricing purposes. For example, against mhr distributions (resp. regular), two samples suffice to ensure 71% (resp. 61%) of optimal oracle performance, and ten samples guarantee $80%$ (resp. $65%$) of such performance. Our analysis relies on the introduction of a new (simple) class of policies and the derivation of tractable lower bounds on their performance through factor revealing dynamic programs.

Auctions are widely used in practice. While also extensively studied in the literature, most of the developments rely on significant assumptions about common knowledge on the seller and buyers' sides. In this work, we study the design of optimal prior-independent selling mechanisms. In particular, the seller faces buyers whose values are drawn from an unknown distribution, and only knows that the distribution belongs to a particular class. We analyze a competitive ratio objective, in which the seller attempts to optimize the worst-case fraction of revenues garnered compared to those of an oracle with knowledge of the distribution. Our results are along two dimensions. We first characterize the structure of optimal mechanisms. Leveraging such structure, we then establish tight lower and upper bounds on performance, leading to a crisp characterization of optimal performance for a spectrum of families of distributions. In particular, our results imply that a second price auction is an optimal mechanism when the seller only knows that the distribution of buyers has a monotone increasing hazard rate, and guarantees at least 71.53% of the optimal revenue against any distribution within this class. Furthermore, a second price auction is near-optimal when the class of admissible distributions is that of those with increasing virtual values (aka regular). Under this class, it guarantees a fraction of 50% of optimal revenues and no mechanism can guarantee more than 55.6%.