arXiv subjects

Omar Besbes

Publications and source records attributed to Omar Besbes.

At least 19 recordsLinked to original sources

arXiv2026

How Risky Is Your Data-Driven Policy?

Data-driven algorithms are ubiquitous across industries, and there is an extensive literature on analyzing their \emph{average} performance. The risk profile of such algorithms, while critical, is much less understood. This paper quantifies the risk of data-driven policies and isolates its sources. We evaluate a policy through the conditional value-at-risk (CVaR) of its loss over the training sample, any policy randomization, and the future outcome, at a fixed unknown distribution. Regret against an oracle that knows the distribution decomposes into expected post-sample regret (PS), the average outcome-only CVaR gap of the selected action, and a sample-risk premium (SR), the additional tail risk omitted by averaging those evaluations. The analogous premium vanishes under expected loss. We characterize when the premium vanishes and how large it is relative to post-sample regret. For losses with a continuous density near the tail cutoff, we identify conditions under which both components decay at the same rate, yet the limiting ratio of the premium to post-sample regret can reach the thousands. When a probability mass at the cutoff moves with the action, the premium can decay more slowly and dominate post-sample regret. We establish conditions under which sample average approximation learns the oracle action at rate $n^{-1/2}$ in both settings, but its combined-risk regret is of order $n^{-1}$ in the first and $n^{-1/2}$ in the second. In finite-sample numerical examples of SAA in both settings, the premium accounts for approximately $74\%$--$97\%$ of regret.

stat.ML↗

arXiv2026

Beyond Expected Profit: How Risk Aversion Alters Learning in the Data-Driven Newsvendor

We study how risk aversion changes learning and the value of data in the classical newsvendor problem. We evaluate data-driven policies through the Conditional Value-at-Risk (CVaR) of realized loss on the combined draw of an i.i.d.\ historical sample and an independent future demand from the same distribution. We measure worst-case regret over demand distributions on a bounded interval relative to an oracle that knows the distribution. We show that, for every fixed positive risk level, Sample Average Approximation (SAA) can retain regret bounded away from zero as the sample size $n$ grows, even at a fixed demand distribution, and characterize its asymptotic worst-case regret. We trace this failure to persistent variability in the learned order, which contributes to tail risk under this combined-risk evaluation. We establish that risk aversion also slows the minimax learning rate over all data-driven policies from $Θ(n^{-1/2})$ under expectation to $Θ(n^{-1/4})$. We construct policies that average nearby order statistics and attain this optimal rate. For finite samples, we reduce worst-case analysis for mixtures of convex combinations of order statistics to Bernoulli demand on the endpoints of the interval. We use this reduction to formulate a linear program for computing minimax policies within this class to any accuracy. In numerical experiments, we find that minimizing this objective alone can leave substantial average CVaR regret when each learned order is evaluated over future demand alone. We therefore develop a two-stage linear program that minimizes the worst-case value of this average regret while allowing a prescribed increase in the original objective. This yields improvements across a broad range of scenarios. Our results show that risk aversion changes both the rate at which data improve decisions and the policies needed to realize that improvement.

math.OC↗

arXiv2026

Impact of Rankings and Personalized Recommendations in Marketplaces

Decision-making often requires individuals to navigate large sets of options with incomplete information and imperfectly formed preferences. Information provisioning tools, such as public rankings and personalized recommendations, have become central to guiding these choices, yet their welfare implications across different market environments remain poorly understood. This paper studies a stylized large-market model to quantify the aggregate value of these tools under uncapacitated supply and capacitated supply. Agent utility is a weighted combination of a common term (population-level quality) and an idiosyncratic term (individual-specific fit). Agents observe noisy signals of these components: public rankings improve estimates of common quality, while personalized recommendations additionally reveal idiosyncratic fit. In uncapacitated settings, both tools improve welfare through better selection. Their relative value is governed by preference heterogeneity: rankings are highly effective when preferences are relatively homogeneous, whereas the marginal value of personalization grows as heterogeneity increases. In stark contrast, under capacity constraints, a strict conservation logic applies: learning common quality primarily reshuffles assignments without increasing aggregate average agent welfare. However, revealing idiosyncratic fit generates substantial welfare gains by mitigating congestion on overdemanded items and unlocking match-specific value. We demonstrate that these core insights are robust across model extensions including alternative extreme-value tail distributions and heterogeneous supply-side priorities. Finally, introducing strategic supply-side pricing reveals a stark distributional dichotomy: while information expands total surplus, the newly generated value is ultimately extracted by the short side of the market.

econ.TH↗

arXiv2026

Battery Operations in Electricity Markets: Strategic Behavior and Distortions

Battery storage can reduce electricity generation costs by shifting energy across time, but as privately owned batteries become large, they may also be able to exert market power. We study how this market power distorts storage decisions in a two-settlement electricity market with stochastic demand and heterogeneous generator flexibility. We compare centralized battery operations, which minimize generation cost, with decentralized battery operations, in which each battery maximizes its own profit. For a baseline model with linear inverse supply curves, we characterize equilibrium battery policies and generation costs in closed form. Relative to centralized operations, a strategic battery distorts storage decisions in three ways: it withholds discharge, shifts participation from the day-ahead market to the real-time market, and responds too weakly to real-time demand fluctuations. These distortions raise generation cost, but the resulting efficiency loss admits tight, distribution-free bounds. We measure the resulting efficiency loss through the Price of Anarchy metric, which compares the cost reduction achieved by centralized batteries to that achieved by strategic batteries. For a single battery, the Price of Anarchy lies between $9/8$ and $4/3$; with $n$ competing batteries, the Price of Anarchy is bounded above by $1+1/(n(n+2))$. Similar bounds continue to hold in richer settings with capacity constraints, battery inefficiency, and virtual bidding. We also show why market power mitigation is subtle: interventions that target one distortion can backfire by redirecting behavior toward another and increasing system cost. Numerical experiments calibrated to California and Texas markets show that losses from a single strategic battery are meaningful but moderate, and that even limited battery competition brings the Price of Anarchy close to one across the specifications we study.

econ.TH↗

arXiv2026

Fast Revenue Maximization

Problem definition: We study a data-driven pricing problem in which a seller sets a price for a single item based on demand observed at a limited number of historical prices. Our goal is to quantify the value of such information and to guide efficient price experimentation under practical constraints. Methodology/results: Our main methodological contribution is an exact reduction that characterizes the maximin revenue ratio, defined as the worst-case revenue achievable using only past data relative to the optimal revenue under full information. This reduction transforms an infinite-dimensional problem into a tractable one-dimensional optimization problem, allowing us to compute near-optimal pricing policies with explicit guarantees and to precisely quantify the value of historical data. Managerial implications: Motivated by practical constraints that limit price changes, we first evaluate the value of local information and show that the sign of the revenue gradient at a single price can provide significant guidance. We then use our framework to design efficient price experiments: we develop a method to select the next price to test so as to maximize future robust performance, and show how to substantially reduce the number of experiments needed to achieve target revenue guarantees in dynamic pricing. Finally, we show that our approach remains effective with noisy demand data, achieving near-optimal performance with as few as 25 to 100 samples per price.

cs.GT↗

arXiv2025

What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce

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 leverage APIs to view, evaluate and choose products. We investigate the behavior of AI agents using ACES, a provider-agnostic framework for auditing agent decision-making. We reveal that agents can exhibit choice homogeneity, often concentrating demand on a few ``modal'' products while ignoring others entirely. Yet, these preferences are unstable: model updates can drastically reshuffle market shares. Furthermore, randomized trials show that while agents have improved over time on simple tasks with a clearly identified best choice, they exhibit strong position biases -- varying across providers and model versions, and persisting even in text-only "headless" interfaces -- undermining any universal notion of a ``top'' rank. Agents also consistently penalize sponsored tags while rewarding platform endorsements, and sensitivities to price, ratings, and reviews vary sharply across models. Finally, we demonstrate that sellers can respond: a seller-side agent making simple, query-conditional description tweaks can drive significant gains in market share. These findings reveal that agentic markets are volatile and fundamentally different from human-centric commerce, highlighting the need for continuous auditing and raising questions for platform design, seller strategy and regulation.

cs.AI↗

arXiv2025

From Contextual Data to Newsvendor Decisions: On the Actual Performance of Data-Driven Algorithms

In this work, we study how the relevance/quality and quantity of past data influence performance by analyzing a contextual Newsvendor problem, in which a decision-maker trades off between underage and overage costs under uncertain demand. We consider a setting in which past demands observed under ``close by'' contexts come from close by distributions and analyze the performance of data-driven algorithms through a notion of context-dependent worst-case expected regret. We analyze the broad class of Weighted Empirical Risk Minimization (WERM) policies which weigh past data according to their similarity in the contextual space. This class includes classical policies such as ERM, k-Nearest Neighbors and kernel-based policies. Our main methodological contribution is to characterize exactly the worst-case regret of any WERM policy on any given configuration of contexts. To the best of our knowledge, this provides the first understanding of tight performance guarantees in any contextual decision-making problem, with past literature focusing on upper bounds via concentration inequalities. We instead take an optimization approach, and isolate a structure in the Newsvendor loss function that allows to reduce the infinite-dimensional optimization problem over worst-case distributions to a simple line search. This in turn allows us to unveil fundamental insights that were obfuscated by previous general-purpose bounds. We characterize actual guaranteed performance as a function of the contexts, as well as granular insights on the learning curve of algorithms.

cs.LG↗

arXiv2025

Beyond IID: data-driven decision-making in heterogeneous environments

How should one leverage historical data when past observations are not perfectly indicative of the future, e.g., due to the presence of unobserved confounders which one cannot "correct" for? Motivated by this question, we study a data-driven decision-making framework in which historical samples are generated from unknown and different distributions assumed to lie in a heterogeneity ball with known radius and centered around the (also) unknown future (out-of-sample) distribution on which the performance of a decision will be evaluated. This work aims at analyzing the performance of central data-driven policies but also near-optimal ones in these heterogeneous environments and understanding key drivers of performance. We establish a first result which allows to upper bound the asymptotic worst-case regret of a broad class of policies. Leveraging this result, for any integral probability metric, we provide a general analysis of the performance achieved by Sample Average Approximation (SAA) as a function of the radius of the heterogeneity ball. This analysis is centered around the approximation parameter, a notion of complexity we introduce to capture how the interplay between the heterogeneity and the problem structure impacts the performance of SAA. In turn, we illustrate through several widely-studied problems -- e.g., newsvendor, pricing -- how this methodology can be applied and find that the performance of SAA varies considerably depending on the combinations of problem classes and heterogeneity. The failure of SAA for certain instances motivates the design of alternative policies to achieve rate-optimality. We derive problem-dependent policies achieving strong guarantees for the illustrative problems described above and provide initial results towards a principled approach for the design and analysis of general rate-optimal algorithms.

cs.LG↗

arXiv2025

Robust Auction Design with Support Information

A seller wants to sell an item to $n$ buyers. Buyer valuations are drawn i.i.d. from a distribution unknown to the seller; the seller only knows that the support is included in $[a, b]$. To be robust, the seller chooses a DSIC mechanism that optimizes the worst-case performance relative to the ideal expected revenue the seller could have collected with knowledge of buyers' valuations. Our analysis unifies the regret and the ratio objectives. For these objectives, we derive an optimal mechanism and the corresponding performance in quasi-closed form, as a function of the support information $[a, b]$ and the number of buyers $n$. Our analysis reveals three regimes of support information and a new class of robust mechanisms. i.) When $a/b$ is below a threshold, the optimal mechanism is a second-price auction (SPA) with random reserve, a focal class in earlier literature. ii.) When $a/b$ is above another threshold, SPAs are strictly suboptimal, and an optimal mechanism belongs to a class of mechanisms we introduce, which we call pooling auctions (POOL); whenever the highest value is above a threshold, the mechanism still allocates to the highest bidder, but otherwise the mechanism allocates to a uniformly random buyer, i.e., pools low types. iii.) When $a/b$ is between two thresholds, a randomization between SPA and POOL is optimal. We also characterize optimal mechanisms within nested central subclasses of mechanisms: standard mechanisms that only allocate to the highest bidder, SPA with random reserve, and SPA with no reserve. We show strict separations in terms of performance across classes, implying that deviating from standard mechanisms is necessary for robustness.

econ.TH↗

arXiv2024

On the Robustness of Second-Price Auctions in Prior-Independent Mechanism Design

Classical Bayesian mechanism design relies on the common prior assumption, but such prior is often not available in practice. We study the design of prior-independent mechanisms that relax this assumption: the seller is selling an indivisible item to $n$ buyers such that the buyers' valuations are drawn from a joint distribution that is unknown to both the buyers and the seller; buyers do not need to form beliefs about competitors, and the seller assumes the distribution is adversarially chosen from a specified class. We measure performance through the worst-case regret, or the difference between the expected revenue achievable with perfect knowledge of buyers' valuations and the actual mechanism revenue. We study a broad set of classes of valuation distributions that capture a wide spectrum of possible dependencies: independent and identically distributed (i.i.d.) distributions, mixtures of i.i.d. distributions, affiliated and exchangeable distributions, exchangeable distributions, and all joint distributions. We derive in quasi closed form the minimax values and the associated optimal mechanism. In particular, we show that the first three classes admit the same minimax regret value, which is decreasing with the number of competitors, while the last two have the same minimax regret equal to that of the single buyer case. Furthermore, we show that the minimax optimal mechanisms have a simple form across all settings: a second-price auction with random reserve prices, which shows its robustness in prior-independent mechanism design. En route to our results, we also develop a principled methodology to determine the form of the optimal mechanism and worst-case distribution via first-order conditions that should be of independent interest in other minimax problems.

econ.TH↗

arXiv2024

The Fault in Our Recommendations: On the Perils of Optimizing the Measurable

Recommendation systems are widespread, and through customized recommendations, promise to match users with options they will like. To that end, data on engagement is collected and used. Most recommendation systems are ranking-based, where they rank and recommend items based on their predicted engagement. However, the engagement signals are often only a crude proxy for utility, as data on the latter is rarely collected or available. This paper explores the following question: By optimizing for measurable proxies, are recommendation systems at risk of significantly under-delivering on utility? If so, how can one improve utility which is seldom measured? To study these questions, we introduce a model of repeated user consumption in which, at each interaction, users select between an outside option and the best option from a recommendation set. Our model accounts for user heterogeneity, with the majority preferring ``popular'' content, and a minority favoring ``niche'' content. The system initially lacks knowledge of individual user preferences but can learn them through observations of users' choices over time. Our theoretical and numerical analysis demonstrate that optimizing for engagement can lead to significant utility losses. Instead, we propose a utility-aware policy that initially recommends a mix of popular and niche content. As the platform becomes more forward-looking, our utility-aware policy achieves the best of both worlds: near-optimal utility and near-optimal engagement simultaneously. Our study elucidates an important feature of recommendation systems; given the ability to suggest multiple items, one can perform significant exploration without incurring significant reductions in engagement. By recommending high-risk, high-reward items alongside popular items, systems can enhance discovery of high utility items without significantly affecting engagement.

cs.IR↗

arXiv2024

The Best of Many Robustness Criteria in Decision Making: Formulation and Application to Robust Pricing

In robust decision-making under non-Bayesian uncertainty, different robust optimization criteria, such as maximin performance, minimax regret, and maximin ratio, have been proposed. In many problems, all three criteria are well-motivated and well-grounded from a decision-theoretic perspective, yet different criteria give different prescriptions. This paper initiates a systematic study of overfitting to robustness criteria. How good is a prescription derived from one criterion when evaluated against another criterion? Does there exist a prescription that performs well against all criteria of interest? We formalize and study these questions through the prototypical problem of robust pricing under various information structures, including support, moments, and percentiles of the distribution of values. We provide a unified analysis of three focal robust criteria across various information structures and evaluate the relative performance of mechanisms optimized for each criterion against the others. We find that mechanisms optimized for one criterion often perform poorly against other criteria, highlighting the risk of overfitting to a particular robustness criterion. Remarkably, we show it is possible to design mechanisms that achieve good performance across all three criteria simultaneously, suggesting that decision-makers need not compromise among criteria.

math.OC↗

arXiv2023

Dynamic Resource Allocation: Algorithmic Design Principles and Spectrum of Achievable Performances

Dynamic resource allocation problems are ubiquitous, arising in inventory management, order fulfillment, online advertising, and other applications. We initially focus on one of the simplest models of online resource allocation: the multisecretary problem. In the multisecretary problem, a decision maker sequentially hires up to $B$ out of $T$ candidates, and candidate ability values are drawn i.i.d. from a distribution $F$ on $[0,1]$. First, we investigate fundamental limits on performance as a function of the value distribution under consideration. We quantify performance in terms of regret, defined as the additive loss relative to the best performance achievable in hindsight. We present a novel fundamental regret lower bound scaling of $Ω(T^{1/2 - 1/2(1 + β)})$ for distributions with gaps in their support, with $β$ quantifying the mass accumulation of types (values) around these gaps. This lower bound contrasts with the constant and logarithmic regret guarantees shown to be achievable in prior work, under specific assumptions on the value distribution. Second, we introduce a novel algorithmic principle, Conservativeness with respect to Gaps (CwG), which yields near-optimal performance with regret scaling of $\tilde{O}(T^{1/2 - 1/2(1 + β)})$ for any distribution in a class parameterized by the mass accumulation parameter $β$. We then turn to operationalizing the CwG principle across dynamic resource allocation problems. We study a general and practical algorithm, Repeatedly Act using Multiple Simulations (RAMS), which simulates possible futures to estimate a hindsight-based approximation of the value-to-go function. We establish that this algorithm inherits theoretical performance guarantees of algorithms tailored to the distribution of resource requests, including our CwG-based algorithm, and find that it outperforms them in numerical experiments.

math.PR↗

arXiv2023

Contextual Inverse Optimization: Offline and Online Learning

We study the problems of offline and online contextual optimization with feedback information, where instead of observing the loss, we observe, after-the-fact, the optimal action an oracle with full knowledge of the objective function would have taken. We aim to minimize regret, which is defined as the difference between our losses and the ones incurred by an all-knowing oracle. In the offline setting, the decision-maker has information available from past periods and needs to make one decision, while in the online setting, the decision-maker optimizes decisions dynamically over time based a new set of feasible actions and contextual functions in each period. For the offline setting, we characterize the optimal minimax policy, establishing the performance that can be achieved as a function of the underlying geometry of the information induced by the data. In the online setting, we leverage this geometric characterization to optimize the cumulative regret. We develop an algorithm that yields the first regret bound for this problem that is logarithmic in the time horizon. Finally, we show via simulation that our proposed algorithms outperform previous methods from the literature.

cs.LG↗

arXiv2022

How Big Should Your Data Really Be? Data-Driven Newsvendor: Learning One Sample at a Time

We study the classical newsvendor problem in which the decision-maker must trade-off underage and overage costs. In contrast to the typical setting, we assume that the decision-maker does not know the underlying distribution driving uncertainty but has only access to historical data. In turn, the key questions are how to map existing data to a decision and what type of performance to expect as a function of the data size. We analyze the classical setting with access to past samples drawn from the distribution (e.g., past demand), focusing not only on asymptotic performance but also on what we call the transient regime of learning, i.e., performance for arbitrary data sizes. We evaluate the performance of any algorithm through its worst-case relative expected regret, compared to an oracle with knowledge of the distribution. We provide the first finite sample exact analysis of the classical Sample Average Approximation (SAA) algorithm for this class of problems across all data sizes. This allows to uncover novel fundamental insights on the value of data: it reveals that tens of samples are sufficient to perform very efficiently but also that more data can lead to worse out-of-sample performance for SAA. We then focus on the general class of mappings from data to decisions without any restriction on the set of policies and derive an optimal algorithm (in the minimax sense) as well as characterize its associated performance. This leads to significant improvements for limited data sizes, and allows to exactly quantify the value of historical information.

math.OC↗

arXiv2022

Optimal Pricing with a Single Point

We study the following fundamental data-driven pricing problem. How can/should a decision-maker price its product based on data at a single historical price? How valuable is such data? We consider a decision-maker who optimizes over (potentially randomized) pricing policies to maximize the worst-case ratio of the revenue she can garner compared to an oracle with full knowledge of the distribution of values, when the latter is only assumed to belong to a 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. The framework we develop is general and allows to characterize optimal performance for deterministic or more general randomized mechanisms, and leads to fundamental novel insights on the value of data for pricing. 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.

cs.GT↗

arXiv2022

Mechanism Design under Approximate Incentive Compatibility

A fundamental assumption in classical mechanism design is that buyers are perfect optimizers. However, in practice, buyers may be limited by their computational capabilities or a lack of information, and may not be able to perfectly optimize. This has motivated the introduction of approximate incentive compatibility (IC) as an appealing solution concept for practical mechanism design. While most of the literature focuses on the analysis of particular approximate IC mechanisms, this paper is the first to study the design of optimal mechanisms in the space of approximate IC mechanisms and to explore how much revenue can be garnered by moving from exact to approximate incentive constraints. We study the problem of a seller facing one buyer with private values and analyze optimal selling mechanisms under $\varepsilon$-incentive compatibility. We establish that the gains that can be garnered depend on the local curvature of the seller's revenue function around the optimal posted price when the buyer is a perfect optimizer. If the revenue function behaves locally like an $α$-power for $α\in (1,\infty)$, then no mechanism can garner gains higher than order $\varepsilon^{α/(2α-1)}$. This improves upon state-of-the-art results which imply maximum gains of $\varepsilon^{1/2}$ by providing the first parametric bounds that capture the impact of revenue function's curvature on revenue gains. Furthermore, we establish that an optimal mechanism needs to randomize as soon as $\varepsilon>0$ and construct a randomized mechanism that is guaranteed to achieve order $\varepsilon^{α/(2α-1)}$ additional revenues, leading to a tight characterization of the revenue implications of approximate IC constraints. Our work brings forward the need to optimize not only over allocations and payments but also over best responses, and we develop a new framework to address this challenge.

econ.TH↗

arXiv2020

Static Pricing: Universal Guarantees for Reusable Resources

We consider a fundamental pricing model in which a fixed number of units of a reusable resource are used to serve customers. Customers arrive to the system according to a stochastic process and upon arrival decide whether or not to purchase the service, depending on their willingness-to-pay and the current price. The service time during which the resource is used by the customer is stochastic and the firm may incur a service cost. This model represents various markets for reusable resources such as cloud computing, shared vehicles, rotable parts, and hotel rooms. In the present paper, we analyze this pricing problem when the firm attempts to maximize a weighted combination of three central metrics: profit, market share, and service level. Under Poisson arrivals, exponential service times, and standard assumptions on the willingness-to-pay distribution, we establish a series of results that characterize the performance of static pricing in such environments. In particular, while an optimal policy is fully dynamic in such a context, we prove that a static pricing policy simultaneously guarantees 78.9% of the profit, market share, and service level from the optimal policy. Notably, this result holds for any service rate and number of units the firm operates. Our proof technique relies on a judicious construction of a static price that is derived directly from the optimal dynamic pricing policy. In the special case where there are two units and the induced demand is linear, we also prove that the static policy guarantees 95.5% of the profit from the optimal policy. Our numerical findings on a large testbed of instances suggest that the latter result is quite indicative of the profit obtained by the static pricing policy across all parameters.

cs.DS↗