Skip to content

What it is (and is not)

LookAlike is a discovery and triage tool for retail real estate. You pick a US retail brand; it fits a presence model that contrasts the tracts holding that brand’s stores with a national background of tracts; then it ranks every continental-US census tract by fit to that model—and shows you, per neighborhood, exactly which features drove the match.

That is the claim. It is not a sales predictor. It is a way to decide where to look, not a recommendation to open.

Pick a brand. A searchable picker at the top of the left panel lists 99 curated brands (for example Trader Joe’s, Whole Foods Market, Chipotle, Starbucks, Costco, Dollar General, Sephora, REI, Sweetgreen, Shake Shack, 7-Eleven, Walgreens), each naming its store source — or add any other United States chain from OpenStreetMap by name or Wikidata identifier and score it live in the browser (with an OpenStreetMap-coverage caveat). Brands you add are saved in your browser and reappear in the picker under “Your brands” on later visits. Switching among brands you have already viewed is instant, because each brand’s national scores are cached in memory rather than re-computed.

See a national fit map. The map colors only high-fit tracts (the median tract is left dark on purpose, so you see where to look, not just noise). Click any neighborhood to see:

  • A fit percentile (a within-brand rank from 0–100, where ~100 is the tract that best matches the brand’s pattern, and 50 is the median)
  • A fit band (Strong, Moderate, or Weak) measured against the brand’s own store tracts. Like the percentile, its reference is brand-specific
  • A low ACS reliability badge when the tract has a small population or a large income margin of error
  • A radar fingerprint showing how that tract compares to the brand’s typical store tract across the 18 scored features
  • A “why it matches” breakdown (the features that raise the score most)
  • A “what works against it” section (the features that lower the score most, with the brand’s typical value for each)
  • A feature-comparison table grouped by theme
  • A plain-English assessment of the trade-offs

Filter and refine. Open markets only (tracts without the brand already), by state, by metro area (choose from 383 Metropolitan Statistical Areas), by minimum fit threshold, or by competition (at least a chosen distance from your own stores, or no competitor from the same category within 6 km).

Rank metros. A “Top metros” view ranks metropolitan areas by how many open, high-fit-rank neighborhoods each holds — a starting point for “which market first?”, stated as rank concentration, not market quality.

Overlay existing stores. See where the brand currently operates and the distance from any candidate to the nearest store (out to 6 km).

Upload your own stores. Fit a presence model on your own store list. Authenticated CSVs become private, versioned retail-client datasets with persisted tract assignments and metric definitions; national scoring remains live in the browser. Optional columns let you give better-performing locations more weight or avoid lookalikes of failed, closed, or underperforming locations.

Tune the factors. Reweight the five scored themes (income/wealth/housing cost, education, density/transportation, age/household type, retail/dining context) or switch themes on and off entirely. Each theme also opens an advanced per-feature layer to weight a single feature within a group. At 1x the score is the fitted model; other weights scale each theme’s contribution. The map and rankings re-score live. These weights are your scenario assumptions, surfaced transparently.

Compare two brands. See a diverging map (a fixed, colorblind-safe blue-and-orange pair shows which brand a tract leans toward; brightness shows how strongly it resembles either), plus three ranked lists (Leans A / Resembles both / Leans B). A custom upload can also be compared against a built-in brand.

Check robustness. For any tract, ask whether its high rank is robust or hinges on one theme. The tool re-scores it under equal weighting and with each theme removed.

See nearby chains. Which of the tracked brands have a store within 6 km—a quick competitive-density read.

Mark “not a fit.” Flag a lookalike that is wrong on the ground; the tool hides it, and once you have flagged a few, it shows the features your rejected tracts most share—teaching you where the method misleads.

Shortlist and export. Star neighborhoods into a persistent shortlist (saved per brand in your browser), add notes, and export a print-ready PDF report or CSV (with the resemblance disclaimer, the fit band, and the reliability flag baked in). The ranked-list CSV export also carries the competition columns.

Save and share. Persist named scenarios (brand, weights, compare, metro, filters) to your browser to switch between markets, and use the Copy link button to share the current view. The link restores the brand, report mode, theme and feature weights, filters, metro, compare brand, selected tract, site pin, and pinned shortlist. When you are signed in, the link is a saved view that also records the data release and any custom store points.

Every continental-US census tract (~83,000) is described by 18 scored features: demographics and housing from the US Census American Community Survey (median income, education, density, age, household composition, tenure, vehicle access, commute mode, poverty) plus retail context from Overture Maps (density of all points of interest, grocery stores, restaurants, cafés, and shopping per square kilometer). Race and ethnicity shares are shown as population context only; they are not model inputs.

Skewed features are log-scaled first. Each feature is then clipped to the national 1st–99th percentile and standardized against the national distribution.

A brand’s store locations are mapped to the tracts that contain them—one observation per occupied tract, so a Costco fuel station and warehouse don’t double-count. For each brand an L2-regularized logistic regression (a presence model) contrasts those store tracts against a fixed background of every fourth scoreable tract. Each feature enters with a linear and a squared term, so the model can prefer a middle range, not only “more” or “less.” Values beyond the range of the brand’s own store tracts earn no extra credit.

The model score becomes a 0–100 fit percentile—a within-brand rank among all scoreable tracts. ~100 is the tract that best matches that brand’s pattern; 50 is the national median. Percentiles are NOT comparable across brands.

Validation: does the model capture anything?

Section titled “Validation: does the model capture anything?”

For each brand, the tool reports a footprint coherence score. The pipeline refits the model five times, each time holding out the stores in one fifth of the counties, then checks where those held-out store tracts rank. County-blocked folds keep a store’s neighbors out of its own test.

  • Distinctive chains (93 or above) score high: for example Sephora at 99.2.
  • Diffuse chains (below 85) score low: for example Circle K at 75.5, because it operates almost everywhere.
  • Across the 99 curated brands, coherence ranges from 75.5 to 99.2, median 92.0.

In a county-blocked comparison on 21 brands, the presence model ranked held-out store tracts at a median of about the 93rd percentile, against about the 72nd for the earlier distance-to-average method. This is a validation check, not a sales claim.

Data sources (all open, no API key required)

Section titled “Data sources (all open, no API key required)”
LayerSourceLicense
DemographicsUS Census ACS 2020–2024 5-year, table-based Summary File (bulk .dat)Public domain
Tract boundaries + land areaUS Census TIGER/Line 2024Public domain
Retail context (POI density)Overture Maps Places (public GeoParquet on S3, release 2026-09-23.1)CDLA-Permissive 2.0
Metro areasUS Census CBSA delineation (OMB 2023); 383 Metropolitan Statistical AreasPublic domain
Brand store locationsAll The Places (CC0) or OpenStreetMap via the Overpass APICC0 / ODbL
BasemapOpenFreeMap dark vector style over OpenStreetMap data; no keyOpenMapTiles / ODbL

See data sources for exact URLs and tables.

Not a revenue, sales, or foot-traffic forecaster. A neighborhood’s fit to your brand’s pattern says nothing about how much money it will make.

Not a recommendation engine. It does not say “open here.” It says “this place looks like your existing markets; go investigate.”

Not a substitute for due diligence, brokerage, or local knowledge. Real estate availability, zoning, rent, competition dynamics, operations, and local relationships all matter more than fit.

Not a black box. Every match is feature-driven and explained. You see exactly which factors raised and lowered the score.

Not a gentrification or displacement forecaster. The tool may surface neighborhoods undergoing demographic change. Using it to gentrify communities is an application choice, not the tool’s intent.

Not dependent on proprietary data. The tool ships entirely on open data to demonstrate that the weak-correlation problem in site selection is not a data-access problem—it is a fundamental fact about geography.

  • Store coverage from All The Places and OpenStreetMap is good for large national chains but imperfect; a few stores may be missing or stale. Upload your own store list for an exact footprint.
  • ACS carries a multi-year lag and sampling error, worst in small tracts. The 2020–2024 estimates use 5-year averaging.
  • The feature set and weighting are interpretable choices, not ground truth. Different reasonable features would shift rankings somewhat. Trust the explanation over the exact rank.
  • Fit ignores crucial real-world factors: rent, real-estate availability, zoning, competition dynamics, operations, and local knowledge—all of which actually decide whether a location works.

Franchise developers vetting new markets before scouting in person.

Tenant-rep brokers doing early market screening for restaurant and retail clients.

Retail real-estate teams looking for a discovery tool to surface candidate neighborhoods and spark due-diligence conversations.

Anyone curious where a brand’s “kind of neighborhood” recurs across the country.