Capture-Demand Swarm · Territory-Analysis-Market-Scoring Agent · Competitor-Density-Territory-Mapping Skill · Build pillar · Published July 12, 2026

How to build competitor-density territory mapping for multi-state franchise development

A 4-skill bundle (Discover + Geofence + Score + Recommend) layered above the existing Esri ArcGIS Business Analyst + Sites USA + Tango Analytics + Buxton + Mapping Analytics + Kalibrate + Pitney Bowes Mapinfo + SiteZeus + eSite Analytics + RetailStat + Smart Site (Synergos Technologies) site-selection ecosystem + the Placer.ai + SafeGraph + Foursquare + StreetLight Data + INRIX foot-traffic substrate + the Google Maps Places API + Bing Maps + Yelp Fusion + OpenStreetMap Overpass + Foursquare Places competitor-discovery substrate + the CoStar + Reonomy + Black Knight + LoopNet + CBRE + JLL + Cushman & Wakefield + ATTOM + Realquest (CoreLogic) real-estate substrate. Anchored on FTC Franchise Rule 16 CFR Part 436 Item 19 Financial Performance Representation substantiation + per-state Franchise Investment Law FPR enforcement + FDD Item 12 territorial-rights cross-check + per-source Places API Terms of Service + scraping case law + CCPA + CPRA + state-comprehensive-privacy + GDPR + NIST AI RMF + ISO 42001 + EU AI Act.

Start with the AI Readiness Assessment Engage the Fractional CMO with AI Swarm Take the 3-question scope quiz

The 4-skill bundle on the territory-analysis-market-scoring agent

Competitor-density territory mapping is one skill on the territory-analysis-market-scoring agent. The skill decomposes into four operationally distinct sub-skills, each with its own success criteria and its own handoff to the next.

1. Discover

Per-source competitor discovery across Google Maps Places API + Bing Maps Local Search + Yelp Fusion + Apple Maps Connect + OpenStreetMap Overpass + Foursquare Places + Placer.ai Places + SafeGraph Places. Each source contributes under its own Terms of Service and license posture, recorded per record. NAP canonicalization (USPS address via Smarty or Loqate, phone E.164 via Twilio Lookup, name trimmed + lowercased) followed by strict-match-then-fuzzy-match (Levenshtein, Jaro-Winkler, Soundex) deduplicates against a canonical competitor record. Crunchbase, PitchBook, and Owler are pulled for emerging competitors not yet on Places.

2. Geofence

Per-candidate-territory polygon resolution across multiple overlays for analyst review: per-radius (1, 3, 5, 10 mile operator-defined per banner format), per-drive-time isochrone (15 or 30 minute computed via Google Maps Distance Matrix, Mapbox Isochrone, HERE Routing, or Esri Network Analyst), per-Voronoi tessellation against sibling franchisee FDD Item 12 territory geometry, per-DMA overlay (Nielsen DMA Boundaries), per-MSA overlay (OMB MSA Boundaries), per-zoning overlay (Black Knight or municipal data), per-traffic AADT (state DOT, CalTrans, INRIX, StreetLight Data). Reilly, Huff, Converse, Christaller gravity models are available as one analytical input among many; they do not substitute for the white-space score.

3. Score

Density is the per-polygon count of competitors per square mile broken out by class: direct (same NAICS or SIC, same banner format), indirect (substitute serving the same customer need), emerging (recently launched per Crunchbase or PitchBook signal). White-space is the spread between modeled demand (Esri Tapestry + Census ACS + Nielsen Claritas PRIZM + Acxiom Personicx + Experian Mosaic demographic and psychographic overlays + Placer.ai + SafeGraph mobility + Esri Tapestry + Census ACS income tables) and observed supply (the density count). Projected revenue is an ensemble (XGBoost or LightGBM or CatBoost + transformer + Bayesian posterior) reported with explicit confidence interval — never a point estimate alone.

4. Recommend

Recommendation to the franchise-development team includes the polygon, the density count by class, the white-space score with confidence interval, the projected revenue with confidence interval, the FDD Item 12 territorial-rights cross-check (handoff to the FDD-territorial-protection -gating skill), the per-source data-license + ToS posture evidence, and the FPR substantiation file (every model input, every model version, every hyperparameter, every source attribution). Analyst override is supported and logged with rationale. Realized revenue is reconciled against projection in the audit trail so the next model-fitting cycle has supervised signal.

The real ecosystem this skill sits above

Site-selection + mobility substrate

Esri ArcGIS Business Analyst, Sites USA, Tango Analytics, Buxton, Mapping Analytics, Kalibrate, Pitney Bowes Mapinfo, SiteZeus, eSite Analytics, RetailStat, Smart Site (Synergos Technologies), Modern Realty Intelligence, MapInfo Pro, Maptitude (Caliper), eSpatial, Maptive, BatchGeo for the mapping substrate. Placer.ai, SafeGraph, Foursquare, UberMedia (Cuebiq), Near Intelligence, AirSage, StreetLight Data, INRIX for mobility + foot-traffic.

Competitor discovery + demographics

Google Maps Places API, Bing Maps Local Search, Apple Maps Connect, Yelp Fusion API, OpenStreetMap Overpass, Foursquare Places API, Crunchbase, PitchBook, Owler, SimilarWeb, Comparably, Glassdoor for competitor discovery + signal. Esri Tapestry, Census ACS, Nielsen Claritas PRIZM, Acxiom Personicx, Experian Mosaic for demographic + psychographic segmentation.

Real estate + zoning

CoStar, Reonomy, Black Knight, Zillow Research, LoopNet, CBRE, JLL, Cushman & Wakefield, ATTOM, Realquest (CoreLogic), Roofstock, Crexi, CompStak for real-estate comparables + transaction history. Black Knight + municipal zoning portals for zoning + permit class.

5-anchor compliance overlay

Anchor 1 — FTC Franchise Rule 16 CFR Part 436 Item 19 FPR substantiation + state Franchise Investment Law FPR enforcement (operationally distinctive)

The FTC Franchise Rule (16 CFR Part 436, amended 2007) Item 19 governs Financial Performance Representations. A franchisor may make no FPR, or may make one — but if it makes an FPR, the representation must have a reasonable basis at disclosure, must be in writing in the FDD, and the franchisor must possess written substantiation. Projected revenue from competitor-density mapping (white-space score multiplied by projected unit revenue) flows directly into FPR territory the moment it touches a prospect. Per-state Franchise Investment Laws layer state enforcement on top: California Corporations Code Sections 31000 et seq (California Franchise Investment Law), Michigan Franchise Investment Law MCL 445.1501 et seq, Maryland Franchise Registration and Disclosure Law (Md Code Bus Reg Title 14 Subtitle 2), Illinois Franchise Disclosure Act 815 ILCS 705, Minnesota Franchise Act Minn Stat 80C, New York General Business Law Article 33, Virginia Retail Franchising Act, Washington Franchise Investment Protection Act RCW 19.100. The substantiation file (every source + every dedup decision + every model version + every hyperparameter + every confidence interval) must survive both FTC and state-administrator review. Operationally distinctive — this anchor is the unique compliance frame for this skill.

Anchor 2 — FDD Item 12 territorial-rights cross-check

Every recommended territory geometry is cross-checked against sibling franchisee FDD Item 12 territorial-rights of record via handoff to the FDD-territorial-protection -gating skill. A polygon that overlaps a sibling franchisee exclusive or protected territory cannot be recommended; it routes to franchisor counsel review. Encroachment claims are a recurring source of FDD litigation; the cross-check belongs upstream of the recommendation, not downstream of a signed agreement.

Anchor 3 — Per-source data licensing + Places API ToS + scraping case law

Google Maps Places API Terms of Service prohibits storing Places data for more than 30 days except cached place IDs; Places output must be shown on a Google Map when displayed to end users. Yelp Fusion API Terms require attribution and prohibit using returned data outside attribution- required surfaces. OpenStreetMap data is licensed under the Open Database License (ODbL) with attribution and share-alike requirements. Foursquare Places, Placer.ai, and SafeGraph each carry per-license commercial terms. Where smaller directories require scraped fallback, hiQ Labs v LinkedIn 9th Cir 2022 narrow CFAA construction + Van Buren v United States 2021 narrow exceeding- authorized-access + Meta v Bright Data ND Cal 2024 constrain the criminal frame but do not authorize ToS breach as a contract matter.

Anchor 4 — CCPA + CPRA + state-comprehensive-privacy + GDPR

Prospect data and competitor records may contain personal information under California Consumer Privacy Act + California Privacy Rights Act + Virginia VCDPA + Colorado CPA + Connecticut CTDPA + Utah UCPA + Texas TDPSA + Oregon OCPA + Montana CDPA + Indiana INCDPA + Tennessee TIPA + Iowa ICDPA + Delaware DPDPA + New Hampshire NHDPA + New Jersey NJDPA + Minnesota MCDPA + Maryland MODPA + Rhode Island + Kentucky and General Data Protection Regulation in EU jurisdictions. Audit trail preserves data-subject- access-request fulfillment evidence per prospect record.

Anchor 5 — NIST AI RMF + ISO 42001 + EU AI Act + per-vendor LLM zero-retention

AI-driven Score modeling operates under NIST AI Risk Management Framework + ISO 42001 AI Management System + applicable EU AI Act articles + per-vendor LLM zero- retention posture verified before any prospect or franchisee record is sent to a model endpoint. Model provenance + version pointer is recorded in the substantiation file alongside FPR-relevant inputs.

6-workstream pre-engagement-baseline reporting cycle

Projected revenue is what the model says with a confidence interval, not what Completions promises. The first 30 days of every Tier 2 Setup Sprint or Tier 3 Fractional CMO engagement establishes the baseline; subsequent reporting is on observed change versus the documented baseline.

Discover coverage. Per-source competitor discovery completion rate, per-source license + ToS posture, per-source NAP-dedup pass rate.
Geofence coverage. Per-polygon resolution completion across radius + drive-time + Voronoi + DMA + MSA + zoning + traffic overlays, per-polygon-version pointer freshness.
Score quality. Per-polygon density count by competitor class, per-polygon white-space confidence interval, per-polygon projected-revenue confidence interval, per-polygon model-version pointer.
Recommend quality. Per-territory franchise- development-decision routing rate, per-territory FDD Item 12 cross-check completion, per-territory analyst override rate, per-territory realized-vs-projected reconciliation rate.
5-anchor compliance posture freshness. FTC Franchise Rule Item 19 FPR substantiation file freshness + per-state FIL FPR posture (California + Michigan + Maryland + Illinois + Minnesota + New York + Virginia + Washington) + FDD Item 12 cross-check + per-source Places API ToS + scraping case-law posture + CCPA + CPRA + state- comprehensive-privacy + GDPR + NIST AI RMF + ISO 42001 + EU AI Act + per-vendor LLM zero-retention posture.
Audit-trail completeness. Per-territory FPR substantiation file (every source attribution + every dedup decision + every model version + every hyperparameter + every confidence interval), per-recommendation audit record, per-analyst-override rationale, per-realized-vs-projected reconciliation entry.

Frequently asked questions

What does competitor-density territory mapping for multi-state franchise development actually involve?

Competitor-density territory mapping for a franchisor evaluating where the next 10-100 units should be sold means resolving each candidate trade-area to a geographic polygon (radius, drive-time isochrone, Voronoi tessellation against sibling franchisee territories, DMA + MSA overlay), discovering every direct + indirect + emerging competitor inside the polygon from multiple sources (Google Maps Places API + Bing Maps Local Search + Yelp Fusion + OpenStreetMap Overpass + Foursquare Places + Placer.ai Places + SafeGraph Places), deduplicating against canonical NAP, scoring density and white-space, and producing a recommendation to franchise-development with the audit trail required to defend any projected revenue claim to a prospect. The skill sits above the existing site-selection ecosystem (Esri ArcGIS Business Analyst + Buxton + Tango Analytics + SiteZeus + Sites USA + Kalibrate + Mapping Analytics + Pitney Bowes Mapinfo + eSite Analytics + RetailStat + Smart Site by Synergos Technologies) rather than replacing it — those vendors ship the substrate; this skill composes them into a defensible franchise-development workflow.

Why does FTC Franchise Rule Item 19 FPR substantiation drive every decision in this skill?

The FTC Franchise Rule (16 CFR Part 436, amended 2007) Item 19 governs Financial Performance Representations a franchisor may make to a prospect. A franchisor may elect to make no FPR, or may make an FPR — but if it makes one, the representation must have a reasonable basis at the time of disclosure, must be in writing in the FDD, and the franchisor must possess written substantiation. Projected revenue numbers derived from competitor-density territory mapping (white-space score times projected unit revenue) flow directly into FPR territory. Per-state Franchise Investment Laws (California Corporations Code Sections 31000 et seq., Michigan Franchise Investment Law MCL 445.1501 et seq., Maryland Franchise Registration and Disclosure Law Md Code Bus Reg Title 14 Subtitle 2, Illinois Franchise Disclosure Act 815 ILCS 705, Minnesota Franchise Act Minn Stat 80C, New York General Business Law Article 33, Virginia Retail Franchising Act, Washington Franchise Investment Protection Act RCW 19.100) layer state-level FPR enforcement on top. The substantiation file — competitor discovery sources + dedup logic + density model + projected revenue model + confidence interval — must survive both FTC review and state-administrator review.

How does the Discover skill source competitors under per-source ToS?

The Discover sub-skill pulls competitors from multiple sources because no single source is complete. Google Maps Places API (Places API Terms of Service prohibits storing Places data for more than 30 days except specific cached IDs; output must be displayed on a Google Map when shown to end users), Bing Maps Local Search (Microsoft Maps Platform Terms), Yelp Fusion API (Yelp Fusion API Terms prohibit using returned data outside attribution-required surfaces), Apple Maps Connect (operator-only listing access), OpenStreetMap Overpass (Open Database License attribution-share-alike), Foursquare Places API (Foursquare ToS), Placer.ai Places + SafeGraph Places (per-license commercial data). The skill must store per-source attribution + per-source license posture + per-source retention window per record. Where smaller directories or niche aggregators do not publish an API, scraped fallback sits inside the hiQ Labs v LinkedIn 9th Cir 2022 narrow CFAA frame as constrained by Van Buren v United States 2021 and Meta v Bright Data ND Cal 2024 — CFAA narrow construction does not authorize ToS breach as a contract matter. The dedup step canonicalizes NAP using the same address + phone + name canonicalization as the NAP-monitoring skill (USPS address via Smarty or Loqate, phone E.164 via Twilio Lookup or libphonenumber, name trimmed + lowercased) before strict-match-then-fuzzy-match (Levenshtein, Jaro-Winkler, Soundex) is applied.

How does the Geofence skill resolve trade-area polygons?

The Geofence sub-skill resolves each candidate trade-area to multiple polygon overlays for analyst review: per-radius (typical 1-mile, 3-mile, 5-mile, 10-mile depending on banner format), per-drive-time isochrone (typical 15-minute, 30-minute, computed via Google Maps Distance Matrix or Mapbox Isochrone or HERE Routing or Esri Network Analyst), per-Voronoi tessellation against sibling franchisee territory geometry (so a prospect territory cannot extend into a sibling franchisee FDD Item 12 exclusive or protected territory), per-DMA overlay (Nielsen DMA Boundaries) and per-MSA overlay (OMB MSA Boundaries) for advertising market alignment, per-zoning overlay (Black Knight or municipal zoning data) for use-class permission, per-traffic AADT (state DOT, CalTrans, INRIX, StreetLight Data) for drive-by exposure where banner format requires it. Gravity-model approaches (Reilly, Huff, Converse, Christaller) are available when the analyst chooses them, with explicit caveat that gravity models predict market-share probabilities and are not a substitute for white-space scoring — they belong in the substantiation file as one input, not as the answer.

How does the Score skill compute density and white-space?

Density is the per-polygon count of direct + indirect + emerging competitors per square mile, broken out by competitor class (direct same-NAICS-or-SIC = same-banner-format, indirect substitute = different-banner-but-same-customer-need, emerging = recently-funded-or-recently-launched per Crunchbase + PitchBook + Owler). White-space is the spread between modeled demand (demographic overlay from Esri Tapestry + Census ACS + Nielsen Claritas PRIZM + Acxiom Personicx + Experian Mosaic, mobility from Placer.ai + SafeGraph, spending power from Esri Tapestry + Census ACS income tables) and observed supply (the density count above). Projected revenue is generated from an ensemble model (gradient-boosted trees from XGBoost or LightGBM or CatBoost, transformer architecture, Bayesian posterior) with explicit confidence interval. The skill never reports a point estimate without a confidence interval, and the substantiation file documents every input + every model version + every hyperparameter so an FTC examiner or a state-administrator examiner can reproduce the projection from the file alone.

How does Completions report on territory mapping without fabricating KPI commitments?

Pre-engagement baseline is established in the first 30 days. Reporting cycles cover the six workstreams: Discover coverage (per-source competitor discovery completion rate + per-source license + ToS posture + per-source NAP-dedup pass rate), Geofence coverage (per-polygon resolution completion across radius + drive-time + Voronoi + DMA + MSA + zoning + traffic overlays + per-polygon-version pointer freshness), Score quality (per-polygon density count by competitor class + per-polygon white-space confidence interval + per-polygon projected-revenue confidence interval + per-polygon model-version pointer), Recommend quality (per-territory franchise-development-decision routing rate + per-territory FDD Item 12 cross-check + per-territory analyst override rate + per-territory rollback rate when realized revenue diverges from projection), 5-anchor compliance posture freshness (FTC Franchise Rule Item 19 FPR substantiation + per-state FIL FPR + FDD Item 12 cross-check + per-source Places API ToS + scraping case law + ADA + UDAP + CCPA + CPRA + state-comprehensive-privacy + GDPR + NIST AI RMF + ISO 42001 + EU AI Act + per-vendor LLM zero-retention), audit-trail completeness (per-territory FPR substantiation file completeness + per-recommendation audit record + per-realized-vs-projected reconciliation entry). Numeric outcome commitments are not made in advance — projected revenue is what the model says with a confidence interval, not what Completions promises.

Engage Completions

Multi-state franchisors evaluating where the next 10-100 units should be sold need a competitor-density territory mapping workflow whose every projected revenue claim can survive FTC review and state-administrator review. Completions architects the workflow as a 4-skill bundle layered above the existing Esri + Buxton + Tango + SiteZeus + Placer.ai + SafeGraph + CoStar + Black Knight ecosystem. Start with the Tier 1 AI Readiness Assessment (2-3 weeks), build with the Tier 2 Setup Sprint (4-8 weeks), or engage Tier 3 Fractional CMO with AI Swarm (, 6-month minimum) for embedded executive orchestration.