Ai changes what retailers should sell for higher revenue
AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization
Artificial Intelligence
Summary
Shopping assistants powered by AI decide which products customers see first, which affects what they buy. The authors study how retailers can pick their product lineup better knowing how these AI helpers shorten the list customers choose from. They find that ignoring AI's role can cost retailers several percent in revenue, but a simpler model based on AI's product rankings can come close to the best possible results. They also show that optimizing product choices under AI influence is doable with efficient algorithms if customer groups are limited.
What this means in practice
- •For retail merchandisers: Adjust product selections by factoring in AI assistant behavior to boost sales and reduce revenue loss.
- •For ecommerce platform teams: Design AI-based product recommendation systems that generate customer shortlists optimizing for retailer revenue.
Authors
Omar El Housni, Marouane Ibn Brahim
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.