cs.AIOct 22, 2026
SaveTwinStore: A Synthetic Consumer Platform Using Vision--Language Models
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.
Figures & tables
Figure 2: Architecture. Inputs from the real store (1) build the twin: the store itself, the situation of the day and the trade area (2). Synthetic shoppers run on one of three engines and on cloud, on-device or mixed models (3). Their trips feed the decision tools (4). Every run is seeded, cached and paired; the platform ships as a launcher, an engine with an API, and a web application.
| Rule-based | Language | Vision | |
|---|---|---|---|
| Decides from | probabilities fitted to receipts | text: persona, store directory, situation | images: the store map at the door and rendered or photographed shelf faces |
| Plan | rule plan | pattern, then intent | one call at the entrance |
| Impulse purchases | probabilities | a text stage | glances at the best-seen faces |
| Reacts to packs, facings, signs | no | no | yes |
| Model calls per shopper | none | about three | one plan and one to three glances |
| Typical use | screening many options | reasoning, interviews | visual levers, final checks |
Table 1: The three shopper engines.
Figure 3: One vision shopper’s trip. A household with its attributes and usual products meets the day’s situation (1), plans at the entrance from the store map (2), walks a path along which a visibility model ranks the shelf faces in view (3), glances at rendered faces and names what catches the eye with an interest score (4), and buys through a seeded draw within budget (5). Below: the image the model receives, its structured answer, and the paired design that runs one population through two stores.
Figure 4: A tour of the application. (a) A new store from one of 82 formats in two steps. (b) A phone photo of a shelf read into a planogram. (c) Shelf Lab: counterfactual edits of a real shelf photo. (d) The trade area with homes, rival stores and the store’s visitors. (e) One shopper’s trip with the shelves they saw and the reasons they gave. (f) A choice-based conjoint study with its market simulator.
| Tool | Question | Output |
|---|---|---|
| A/B tests | What do a price, discount, sign, placement or new pack change? | paired effects by segment with intervals; an automatic report; price sweeps with a demand curve, elasticity and the revenue-maximizing price |
| Shelf tests | Does a new pack, price or sign stand out on the shelf? | paired pick share and stand-out per respondent |
| Concept tests | Which pack or price do respondents prefer? | five-point ratings, top-two-box shares, preference shares, acceptable price ranges, verbatims |
| Conjoint | Which features and prices win the choice? | part-worths with intervals, importance, willingness to pay, a market simulator |
| Staff scripts | Which wording sells better? | paired purchase intent, trust and pressure |
| Field pilots | Does it hold in the real store? | a shift-balanced schedule and sample size; observed conversion; leave-one-out checks by staff and shift; staff time and a cost scenario |
Table 2: The eleven tools of the marketing studio.
Figure 5: Protocol and data. Top: on The Complete Journey , households’ receipts of the history weeks are the only inputs; settings are tuned on weeks 27–39 and frozen; the test predicts weeks 40–53 for households excluded from calibration, with a second test panel of new households. Bottom: eleven public datasets test individual aspects of shopping behavior.
Figure 6: As close as the households’ own past. (a) The category mix of simulated trips differs from the real mix of unseen weeks by little more than real households differ from their own earlier weeks. (b) A classifier separates simulated from real receipts only slightly better than a household’s earlier from its later receipts. (c) Differences between households: by age, the most likely simulated trip tracks the real deviations more closely than one of the household’s own earlier trips; by income, children and household size, shoppers who never see their history match one of their own past receipts. The rule engine does not.
| Check | Vision shoppers | Real reference |
|---|---|---|
| Category mix (JSD) | 0.017–0.018 | 0.012 (own earlier weeks) |
| Household hit vs. best-sellers | to , CI | – |
| Demographic deviations, history hidden ( ) | 0.27 ( ) | 0.30 (own earlier receipt) |
| Repeat-purchase share | 0.56–0.72 | 0.73 |
| Real vs. simulated classifier (AUC) | 0.56–0.62 | 0.52 (own earlier receipt) |
| Own-price elasticity | to | to |
Table 3: Validation summary on held-out data. Ranges span decision models and modes.
Figure 7: Agreement ledger. Each row divides a simulated behavioral magnitude by its real counterpart; perfect agreement sits on the 1 line. Bars show the range across decision models and modes.
Figure 8: Response to the levers. (a) Simulated own-price elasticities lie inside the range measured in the field. (b) Correlation between simulated and real effects of the day on held-out households.
Appendix figures & tables13 assets
Supplementary material from the paper’s appendix.
Appendix
| Screens | A check on the sample store | |
|---|---|---|
| C1 | Figs. 9 , 10 and 19 | Every fixture, product, price and opening hour is a record that can be read, edited and exported; the 3D view renders the same records the shoppers use. |
| C2 | Figs. 13 and 10 | A promotion added to a rendered shelf face changes 0.8 % of its pixels, all in the ribbon and the tag; an edit of a shelf photograph changes no pixel outside the edited regions. |
| C3 | Fig. 14 | Any of the 2,440 shoppers can be opened; each purchase shows its time, shelf, price and the reason recorded at that step. |
| C4 | Figs. 11 and 15 | The revenue on screen equals the sum over the per-shopper export ($21,032.06 over 2,440 rows); receipts, POS files and tracks can be uploaded and compared with the simulation. |
| C5 | Figs. 16 and 17 | The layout comparison pairs 2,440 shoppers and reports intervals; unpaired, the same difference would not be distinguishable from noise. |
Table 4: Conditions for an informative synthetic receipt , where each is visible, and a check on the sample store.
Figure 9: Building the twin. (a) The new-store page: name, address, type, working days and hours; the address grounds the trade area (1), and a furnished format is the default starting layout (2). (b) The 82 formats, each with its grid size, displays and default assortment, and a preview of the floor plan (3). (c) A store from a plan image, read by a vision model with a geometric fallback. (d) The store’s records: information, synthetic customers by persona, fixtures and products. (e) The same records rendered in 3D.
Figure 10: From a shelf photograph to a planogram and its counterfactuals. (a) The sample store’s fridge photograph after reading: detected slots on the photo (1), each product with its category, price, facings and reading confidence (2), and the summary of 12 products, 15 facings, 4 shelves and 1 gap (3). (b) Shelf Lab’s six edits and the Sim2real comparison. (c) Five edits applied by the edit engine: a swap (1), a stock-out (2), a new pack on two facings (3), a price cut shown against the old price (4) and a 1+1 sign (5). No pixel outside the edited regions changes.
Figure 11: The simulated day. (a) Monday at 1:28 pm in the stored language-engine run of the sample store: a recorded thought and a pick above the shoppers (1), the clock and speed (2), layers and views (3), live totals of the receipts so far (4) and questions about the run (5). (b) Footfall and (c) predicted congestion over the day. (d) Revenue, buyers and stop-to-buy rate per fixture, from the rule-based run on all 2,440 shoppers.
Figure 12: Configuring a run. (a) The rule-based preview on all 2,440 personas, with no model calls. (b) Vision shoppers on a sample of 30, with the expected number of calls stated before the run. (c) Advanced settings: the situation of the day, preset or described in words (1), visitors predicted from the neighborhood (2), and what the vision shoppers decide (3).
Figure 13: What a vision shopper sees , as rendered by the engine from the sample store. (a) The store map and text directory received at the door. (b) A shelf face with a tag “# price” under every pack. (c) The same face with a 1+1 ribbon on #7 (1) and a 30 % cut on #11 (2): 0.8 % of the pixels change. (d) The 3D shopper’s-eye view, used to inspect trips. Bottom right: what the model receives with each image and the structure of its answer.
Figure 14: Following one shopper in the stored language-engine run. (a) The 2,440 shoppers sorted by spend; the top shopper (1). (b) Her persona, route and stops (2) and the steps with the thoughts recorded at them (3). (c) The trip as a receipt, each line tied to its time and reason; the marked step 4 shows a narrated step checked against the picks. (d) The same trip as a row of the per-shopper export.
Figure 15: From trips to results. (a) While a day plays: visitors by hour (1), totals of the receipts so far (2) and questions about the run (3). (b) Run results of the rule-based run on all 2,440 shoppers, with a breakdown by age. (c) Products ranked by revenue, run diagnostics, and the upload of the store’s receipts, POS exports and movement tracks for comparison with the simulation.
Figure 16: Comparing two layouts on the same shoppers. (a) The comparison window for the two stored runs of the sample store: the selected runs and the verdict (rings), then every metric with both means, the paired difference and its 95 % interval, the probability that B is better and the paired sample a 5 % effect would need. (b) The spend difference with the paired interval and with the interval two independent samples of the same size would give, computed from the runs’ per-shopper exports. (c) The layout optimizer. (d) The comparison read row by row.
Figure 17: An A/B test from the marketing studio : a 30 % discount and a move to eye level for one tea, each against the unchanged layout with the same 1,000 rule-based shoppers. (a) The verdict (1) and the arms with revenue per visitor and its paired intervals (2). (b) Units of the tested product per 100 visitors (3) and the response by segment (4).
Figure 18: The other study builders : (a) shelf test, (b) concept test, (c) conjoint, (d) staff scripts, (e) product images, and (f) price checks and inventory reviews, which work on observed records without model calls.
Figure 19: The trade area of the sample store. (a) The generated neighborhood with homes, workplaces, schools, venues and rival stores, the rings that contain 50 % and 80 % of the store’s customers and the lines from where they come (1); the area’s population (2) and the store’s weekday visitors (3). (b) Weekday against weekend. (c, d) Visits by hour and who comes, on a weekday and at the weekend.
Figure 20: Working with the platform. (a) Three of the six interface languages. (b) The floor on a phone. (c) The command palette, which reaches every store and tool and passes a typed question to the assistant. (d) The model page: a local vision model chosen for the computer’s hardware (1) and cloud providers whose keys stay on the machine (2).
More in this topic
Synthetic Data Generation
Synthetic data generation creates artificial examples, simulations, and datasets to train, test, or protect machine-learning systems.
See all 620 papers