TwinStore creates digital store copies with virtual shoppers deciding purchases
TwinStore: A Synthetic Consumer Platform Using Vision--Language Models
Artificial Intelligence
Summary
Shopping in physical stores is hard to study and improve because you can't easily test changes without affecting real shoppers. The authors developed TwinStore, a tool that makes a digital copy of a store from pictures or floor plans and fills it with virtual shoppers. These shoppers walk the aisles and buy products just like real people, letting store managers try different layouts, prices, and promotions virtually. This helps test ideas before changing the real store. The tool’s simulated shopping patterns closely match real consumer behavior, making it a useful way to plan retail strategies.
What this means in practice
- •For retail store planners: Create virtual store copies to test layout, pricing, and promotion changes before applying them in real stores.
- •For marketing teams: Use built-in marketing tools and simulations to forecast shopper responses and optimize campaign designs.
Authors
Minhyeok Lee
Abstract
We present TwinStore, a source-available synthetic consumer platform for physical retail built on vision--language models. TwinStore turns a store into a digital twin---from 82 ready-made formats, a floor-plan image or phone photos of its shelves---and fills it with synthetic shoppers who plan a trip, walk the aisles and decide what to buy by looking at rendered shelves with packs, price tags and promotion signs. Every trip ends in a receipt, so a layout, price, pack or promotion can be tried on the same shoppers before it reaches the store. Around this core, TwinStore provides 3D playback, paired comparisons and layout optimization, shopper interviews, a trade-area model, counterfactual edits of real shelf photos, a marketing studio with eleven tools, and an assistant that turns a plain sentence into a drafted study or an answer grounded in a run's own numbers. In a held-out validation on eleven public datasets, simulated receipts approach the households' own natural variation (category-mix divergence 0.017--0.018 against a real drift of 0.012), price elasticities fall inside the range measured in the field, and three independent decision models agree. TwinStore runs on cloud or on-device models and is distributed with installers for Windows, macOS and Linux.