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

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

    Sep 10, 2026Spandan Ghose ChowdhuryMulti-Agent LLM SystemsAI-Assisted Decision Making

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

  2. Combinatorial Inference on the Optimal Assortment in Multinomial Logit Models

    Jan 28, 2023Shuting Shen, Xi Chen, Ethan X. Fang +1Statistical Hypothesis TestingAssortment Optimization

    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

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

    May 2, 2026Jing Dong, Prakirt Raj Jhunjhunwala, Yash KanoriaInformation RetrievalRecommender Systems

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