cs.AIOct 9, 2026

AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization

Authors: Omar El Housni, Marouane Ibn Brahim

Organizations: Cornell Tech, Cornell University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

AI shopping assistants increasingly influence which products consumers consider. We study retail assortment planning under AI mediation, where a retailer chooses a catalog, an AI intermediary forms a customer-facing shortlist, and the customer chooses from that shortlist according to a multinomial logit model. We consider both deterministic mediation, in which the AI follows a fixed segment-specific ranking, and stochastic mediation based on the Plackett-Luce model. Empirically, we construct a dataset of product rankings from leading AI models, estimate Plackett-Luce ranking models, and evaluate their predictive performance on held-out assortments. Combining these estimates with synthetic customer preferences, we find that accounting for AI mediation can materially change optimal assortments and revenue. Across the tested capacity configurations, ignoring mediation yields mean revenue losses between 2.52% and 11.37% relative to the PL optimum. A much simpler deterministic plug-in, based only on the ordering of fitted AI utilities, performs substantially better, with mean losses of at most 0.53%. Motivated by this performance, we study assortment optimization under deterministic mediation. We characterize its computational complexity and show that, for any fixed number of customer segments, the problem admits a fully polynomial-time approximation scheme.

Figures & tables

Figure 1: AI-mediated shopping sequence.
Product categoryNumber of productsProduct attributesListed price ($): median [min, max]
Lightning chargers25Wattage; connector type; cable length; port count16.79 [6.90, 32.65]
Robot vacuums22Suction power; run time; Wi-Fi capability; mopping; self-emptying200.86 [49.99, 1,149.99]
Pet leashes25Product type; species; length; closure type; material18.00 [8.85, 29.95]
Table 1: Product universes and information available to the AI ranking models.
SampleTest rankingsTrain NLLTest NLLTop-1Top-3Top-5Jaccard
All categories5,4003.3603.31278.8%68.4%66.6%0.879
By product category
Lightning chargers1,8003.7123.62478.6%64.5%61.4%0.859
Robot vacuums1,8003.1173.16477.3%70.6%69.7%0.891
Pet leashes1,8003.2493.14880.6%70.1%68.8%0.886
By AI model
Table 2: Training fit and out-of-sample predictive performance of the estimated PL models.
Figure 2: Mediation regimes across the seven capacity environments.
Figure 3: Assortment size and assortment contraction across the seven capacity settings.
BBKKMediatedMean ∣SPL⋆∣|S^{\star}_{\mathrm{PL}}|Direct-MNL revenue lossDeterministic revenue loss
  share MeanP95MaxMeanP95Max
8396.05%4.209.80%28.04%57.08%0.52%2.70%9.02%
8585.78%5.604.04%13.85%37.96%0.18%0.99%4.83%
10396.05%4.2011.37%30.66%52.11%0.53%2.70%9.02%
10585.78%5.885.50%18.45%37.90%0.26%1.45%4.83%
10766.03%6.842.52%10.36%23.83%0.08%0.59%2.16%
Table 3: Policy performance across the seven capacity environments.
Figure 4: Revenue loss by customer–AI preference alignment at B=10B=10 . Panel A reports mean direct-MNL revenue loss and Panel B reports mean deterministic revenue loss, both for K∈{3,5,7}K\in\{3,5,7\} .
Figure 5: Assortment response and mediation mechanism by preference alignment. Panel A reports mean ∣SPL⋆∣−K\lvert S_{\mathrm{PL}}^{\star}\rvert-K for each capacity environment. Panel B reports the corresponding share of instances in the active-filtering regime.
 m=1m=1Fixed m≥2m\geq 2Arbitrary mm
Fixed KKPolynomialPolynomialO(n1−ϵ)O(n^{1-\epsilon}) -inapproximable
Arbitrary KKPolynomialNP-hard; FPTASO(n1−ϵ)O(n^{1-\epsilon}) -inapproximable
Table 4: Computational complexity and approximability of deterministic AI-mediated assortment optimization.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Revenue loss by customer–AI preference alignment across the full capacity grid.
Figure 7: Preference alignment and filtering mechanisms across the full capacity grid.
More in this topic

Assortment Optimization

Assortment optimization selects and positions products to maximize revenue or platform value under customer-choice models and operational constraints.

See all 13 papers

Explore similar work

CardsList
Sep 10, 2026

Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce

AI shopping assistants increasingly redirect consumer discovery, creating an urgent need for tools that support seller-side competitive decision-making. We present a multi-agent AI system that automates competitive visibility measurement and root cause diagnosis in LLM-mediated ecommerce. The system introduces Agentic Share-of-Search (ASoS) as the decision target, deploys query agents across leading AI platforms, and uses a ReAct-based diagnostic agent to recommend prioritized merchandising interventions. A 100-trial ablation study, presented as a feasibility evaluation of this prototype, shows the agent recovers the ablated signal in 39% of trials (95% CI: 30.0% - 48.8%, 5.5x over chance), rising to 63.9% among high-correlation ablations.

Spandan Ghose Chowdhury

College of Computing, Georgia Institute of Technology Atlanta, Georgia, USA

Multi-Agent LLM SystemsAI-Assisted Decision MakingAgentic Commerce
AskPDF
Jan 28, 2023

Combinatorial Inference on the Optimal Assortment in Multinomial Logit Models

Assortment optimization has received active explorations in the past few decades due to its practical importance. Despite the extensive literature dealing with optimization algorithms and latent score estimation, uncertainty quantification for the optimal assortment still needs to be explored and is of great practical significance. Instead of estimating and recovering the complete optimal offer set, decision-makers may only be interested in testing whether a given property holds true for the optimal assortment, such as whether they should include several products of interest in the optimal set, or how many categories of products the optimal set should include. This paper proposes a novel inferential framework for testing such properties. We consider the widely adopted multinomial logit (MNL) model, where we assume that each customer will purchase an item within the offered products with a probability proportional to the underlying preference score associated with the product. We reduce inferring a general optimal assortment property to quantifying the uncertainty associated with the sign change point detection of the marginal revenue gaps. We show the asymptotic normality of the marginal revenue gap estimator, and construct a maximum statistic via the gap estimators to detect the sign change point. By approximating the distribution of the maximum statistic with multiplier bootstrap techniques, we propose a valid testing procedure. We also conduct numerical experiments to assess the performance of our method.

Shuting Shen, Xi Chen, Ethan X. Fang +1

Department of Biostatistics, Harvard T.H. Chan School of Public Health · Leonard N. Stern School of Business, New York University · Department of Biostatistics & Bioinformatics, Duke University

Statistical Hypothesis TestingAssortment Optimization
AskPDF
May 2, 2026

Right-Sizing Communication and Recommendation Set Size in AI-Assisted Search

We model the interaction between a user and an AI driven recommendation system. The user initiates the process by conveying preference information through a costly and noisy message. The AI assistant, acting as a Bayesian agent, interprets the user's message to form a posterior belief about their true preferences and make product recommendations. In particular, it determines how many recommendations to present so as to maximize the user's expected utility from their final choice, while accounting for the search cost induced by the size of the recommendation set. We use mutual information based cost functions to model the two distinct costs incurred by the user during the interaction: (i) a communication cost, which increases with the precision of their preference message, and (ii) a search cost, which increases with the size of the recommendation set provided by the AI assistant. We study products and preferences which live in d dimensional space, and ask how the user's expected payoff can be maximized. For large d, we characterize how optimal message precision and recommendation set size depend on the cost parameters, under two distinct distributions from which recommendations can be sampled from the product universe: (i) Bayes' posterior belief, and (ii) an optimized tilted distribution. Under the posterior sampling scheme (i), we identify a hybrid regime, in which an efficient interaction policy requires jointly optimizing the amount of information (in bits) conveyed by the user and the number of recommendations provided by the AI assistant. In the tilted sampling scheme (ii), our results show that the optimal interaction policy uses only one of communication and search, favoring whichever of them is less costly.

Jing Dong, Prakirt Raj Jhunjhunwala, Yash Kanoria

Columbia Business School, Columbia University · Amazon.com Inc.

Information RetrievalRecommender SystemsHuman-AI Decision MakingPreference Elicitation
AskPDF