What is continuous per-market scoring — and what is the per-market-Bayesian-hierarchical-times-HHI-competitive-density-times-price-elasticity-times-Sherman-Clayton-Antitrust-times-replication-crisis problem distinctive to this skill?

A DTC ecommerce operator with $5M-$50M annual revenue ships per-market (Nielsen DMA 210-market + Census MSA 935-market + ZIP-cluster 30,000+ + Block Group 220,000+) per-period (W-day + W-week + W-month + W-quarter) per-channel (organic + paid-search + paid-social + display + email + SMS + retail) scoring across 5-25 KPIs (demand + conversion + AOV + CAC + LTV + repeat-rate + churn + saturation + expansion-headroom). With 210 DMA × 25 KPIs × W-week = 5,250 per-market-period observations per week + 935 MSA × 25 KPIs = 23,375 per-week observations. The four-skill bundle on the per-market-scoring agent — Score, Calibrate, Compare, Audit — sits above the geo-demographic + consumer-demand + competitive-density + Bayesian-hierarchical substrate (Nielsen DMA + Census MSA + Esri ArcGIS + MapBox + SafeGraph + Placer.ai + Resonate + Acxiom + Experian + Nielsen Scarborough + comScore + Google Trends + SparkToro + SimilarWeb + Semrush + Ahrefs + Moz + Sensor Tower + scikit-learn + XGBoost + LightGBM + CatBoost + PyMC + NumPyro + Stan + brms + Google CausalImpact + BSTS + DoWhy + EconML + Robyn + LightweightMMM + PyMC-Marketing) and writes a per-market per-period canonical scoring record. The operationally distinctive anchor: per-market consumer-demand scoring algorithm + per-market consumer-price elasticity (demand + cross-price + income) + per-market competitive density (Herfindahl-Hirschman Index (HHI) + Lerner Index + Concentration Ratio CR3/CR5 + Berry concentration + per-market entry-barrier + per-market exit-barrier) + per-market CAC/LTV ratio + per-market organic-share + per-market paid-share + per-market AOV potential + per-market churn-risk + per-market saturation-index + per-market expansion-headroom + per-market Bayesian hierarchical model (per-market intercept + per-market slope + per-market interaction + per-market shrinkage + per-market partial-pooling + per-market complete-pooling + per-market no-pooling) + per-market causal-impact (CausalImpact + BSTS + DoWhy + EconML + counterfactual decomposition) + per-market change-point detection (Bayesian change-point + PELT + Binary Segmentation + CUSUM change-point) + per-market replication-crisis discipline (Ioannidis + Amrhein-Greenland-McShane + Rosenbaum Γ + Cornfield + E-value + falsification + negative-control + per-market placebo + reverse causality + Bonferroni + BH FDR + Holm-Bonferroni + Šidák).

Why do Nielsen + Esri + SafeGraph + Resonate + Google Trends + SimilarWeb + Semrush + Ahrefs + Robyn + LightweightMMM break at multi-market-multi-period-Bayesian-hierarchical scale?

Each geo-demographic + consumer-demand + paid-search + MMM vendor ships per-account flat per-market primitive at single-vendor single-KPI level. None coordinates per-market per-period multi-vendor scoring against per-market consumer-demand + per-market price elasticity + per-market HHI competitive density + per-market CAC/LTV + per-market Bayesian hierarchical model (partial-pooling + complete-pooling + no-pooling shrinkage) + per-market causal-impact + per-market change-point detection + per-market replication-crisis discipline. None handles Sherman Antitrust Act + Clayton Act per-market HHI competitive-risk gating at the cross-market level. None gates against FDD Item 19 financial performance representations when per-market scoring shared with franchisees + FINRA Rule 2210 when public-company per-market + SOX 302/404/906 + FASB ASC 280 segment reporting. None writes a per-market per-period WORM scoring audit trail. The four-skill bundle Score + Calibrate + Compare + Audit sits above the geo-demographic + consumer-demand + competitive-density + Bayesian-hierarchical substrate — it does not replace it.

How does Score + Calibrate work?

Score runs per-market per-period multi-vendor data ingestion + per-market consumer-demand scoring: per-market organic-search-share (via SimilarWeb + Semrush + Ahrefs + Moz + Sistrix) + per-market paid-search-share (via SpyFu + iSpionage + KeywordSpy) + per-market social-share (via Brandwatch + Talkwalker + Meltwater + Sprinklr) + per-market visit (via SafeGraph + Placer.ai + Near + Resonate) + per-market consumer-demographics (Nielsen Scarborough + Acxiom + Experian + Equifax + Mosaic + PRIZM + ClaritasGeo) + per-market mobile-app (Sensor Tower + App Annie + data.ai + Apptopia). Per-market consumer-price elasticity (demand elasticity + cross-price elasticity + income elasticity via econometric estimation). Per-market competitive density (HHI Herfindahl-Hirschman Index + Lerner Index + Concentration Ratio CR3/CR5 + Berry concentration + entry/exit barrier). Per-market CAC/LTV potential. Calibrate runs per-market Bayesian hierarchical model fitting (PyMC + NumPyro + Stan + brms): per-market intercept + per-market slope + per-market interaction + per-market shrinkage + per-market partial-pooling (random-effects) + per-market complete-pooling + per-market no-pooling + per-market hyperprior tuning. Per-market WAIC + LOO-CV model-selection. Per-market posterior predictive check.

What does Compare + Audit do?

Compare runs per-market per-period peer-cohort comparison: per-market vs peer-market same-demographic + same-competitive-density + same-stage-of-lifecycle. Per-market causal-impact (Google CausalImpact + BSTS + DoWhy + EconML + counterfactual decomposition + ATE + CATE + ITE + LATE). Per-market change-point detection (Bayesian change-point + PELT + Binary Segmentation + CUSUM change-point). Per-market replication-crisis discipline (Ioannidis 2005 + Amrhein Greenland McShane 2019 + per-market Rosenbaum sensitivity (Γ) + Cornfield + E-value (VanderWeele Ding 2017) + falsification test + negative-control + per-market placebo + reverse causality + Bonferroni + Benjamini-Hochberg FDR + Holm-Bonferroni + Šidák multi-comparison correction). Per-market severity classification: P0 Sherman Antitrust/Clayton Act competitive-risk (HHI > 2500 + market-concentration-flag + per-market price-fixing-risk) + P1 per-market causal-impact gap 72-hour + P2 per-market replication-crisis robustness 7-day + P3 per-market change-point drift 30-day + P4 docs-only. Gate runs 5 anchors per-market per-period before any scoring distributes to ad-spend allocation + market-expansion decision systems. (1) Per-market Bayesian hierarchical + HHI competitive density + price elasticity + CAC/LTV + causal-impact + change-point detection + replication-crisis discipline. (2) Sherman Antitrust Act + Clayton Act + per-market HHI competitive-risk gating + FTC Section 5 + Pfizer 1972 + CFPB UDAAP + Lanham + USPTO + Robinson-Patman + per-state UDTPA. (3) FDD Item 19 financial performance representations when per-market scoring shared with franchisees + 15-state franchise + HIPAA + FINRA Rule 2210 + Rule 3110 + SEC Regulation FD + per-state professional licensing. (4) EU AI Act Article 50 transparency when AI-ML per-market scoring + Article 13/14/15 + Annex III when AI-ML per-market scoring drives ad-spend allocation + Article 6/27 FRIA + DSA + DMA + GDPR Article 6/7/22/28/30 + LGPD + DPDP + PIPEDA + Quebec Law 25 + CCPA + CPRA + 18-state. (5) WCAG 2.2 AA + ARIA + EAA + ADA Title III + Section 508 + SOX 302/404/906 + COSO + Exchange Act 13(b)(2) + FASB ASC 280 segment reporting + SEC Reg S-K. Audit writes a per-market per-period WORM scoring record: per-market score snapshot + per-market Bayesian hierarchical model + per-market causal-impact + per-anchor gate-pass + Sherman/Clayton HHI gate + AI-ML provenance + EU AI Act FRIA. Retention: 7-year FTC + 7-year IRS + 7-year HIPAA + 7-year state bar + 6-year SEC + 3-year FINRA + 7-year SOX + GDPR Article 30 + EU AI Act Article 12 + SOC 2 CC7/CC8.

What does this skill connect to on the per-market-scoring agent and across the swarm?

On the per-market-scoring agent: per-market consumer-demand scoring + per-market competitive density + per-market Bayesian hierarchical + per-market causal-impact + per-market change-point. Across the swarm: per-location AI-calibrated forecasting (#600 same per-location-cohort substrate + same replication-crisis discipline) + per-location per-cohort two-sigma anomaly detection (#608 same statistical-process-control + multi-comparison correction substrate) + root-cause attribution sketch (#604 DOWNSTREAM consumer of per-market scoring) + per-state-overlay-composer (#599 UPSTREAM canonical for Sherman/Clayton + FDD Item 19 + FINRA per-state) + integration-drift-monitor agent (#562 + #569 + #570) + tiered pre-filter deterministic gates + per-vertical compliance overlay. Commercial-pillar parent: /market-expansion-analytics.

What does the 6-workstream pre-engagement-baseline reporting cycle look like for this skill?

Every two weeks during the Tier 3 Fractional CMO with AI Swarm engagement, six workstreams report against the pre-engagement baseline. Workstream 1: per-portfolio per-market per-period scoring coverage — markets covered + periods scored + KPIs ingested. Workstream 2: Score per-market multi-vendor ingestion flow — per-market organic-share + paid-search + social + visit + demographics + mobile-app + price elasticity + HHI competitive density absorbed. Workstream 3: Calibrate per-market Bayesian hierarchical flow — per-market intercept + slope + interaction + shrinkage + partial-pooling + WAIC + LOO-CV + posterior predictive check. Workstream 4: Compare per-market peer-cohort flow — per-market vs peer comparison + causal-impact + change-point + replication-crisis discipline + multi-comparison correction. Workstream 5: Regulatory-defense audit coverage — per-market Bayesian + HHI + price elasticity + replication-crisis + Sherman Antitrust + Clayton Act + EU AI Act Article 50 + FDD Item 19 + FINRA + SOX + FASB ASC 280. Workstream 6: FBC feedback-loop pattern-learning — per-market realized-vs-predicted scoring + per-market Bayesian-shrinkage retrospective + per-market Sherman/Clayton HHI enforcement retrospective.

Build pillar · per-market-scoring agent

How to build continuous per-market scoring

Nielsen DMA + Census MSA + ZIP-cluster + Block Group + Tract + Esri ArcGIS + MapBox + SafeGraph + Placer.ai + Near + GeoIQ + Resonate + Acxiom + Experian + Equifax + Mosaic + PRIZM + Nielsen Scarborough + comScore + Google Trends + SparkToro + Brandwatch + Talkwalker + Meltwater + Sprinklr + SimilarWeb + Semrush + Ahrefs + Moz + Sistrix + SpyFu + iSpionage + KeywordSpy + Sensor Tower + App Annie + data.ai + Apptopia + scikit-learn + XGBoost + LightGBM + CatBoost + PyMC + NumPyro + Stan + brms + Google CausalImpact + BSTS + DoWhy + EconML + Robyn + LightweightMMM + PyMC-Marketing ship per-account flat per-market scoring primitives. The Score + Calibrate + Compare + Audit skill bundle on the per-market-scoring agent sits above the geo-demographic + consumer-demand + competitive-density + Bayesian-hierarchical substrate and writes a per-market per-period canonical scoring record with named regulatory anchors covering per-market Bayesian hierarchical model + HHI competitive density + price elasticity + CAC/LTV + causal-impact + change-point + replication-crisis discipline + Sherman Antitrust Act + Clayton Act when HHI signals competitive risk + EU AI Act Article 50 + FDD Item 19 + FINRA 2210 + SOX 302/404/906 + FASB ASC 280.

Published January 13, 2027 · 3,200 words

The 4-skill bundle on the per-market-scoring agent

One agent. Four coordinated skills. The Score + Calibrate + Compare + Audit bundle runs above the geo-demographic + consumer-demand + competitive-density + Bayesian- hierarchical substrate and writes one canonical per-market per-period scoring record.

Score

Per-market per-period multi-vendor ingestion: per- market organic-search-share + per-market paid-search- share + per-market social-share + per-market visit + per-market consumer-demographics + per-market mobile- app. Per-market consumer-price elasticity (demand + cross-price + income). Per-market competitive density (HHI + Lerner Index + Concentration Ratio CR3/CR5 + Berry concentration + entry/exit barrier). Per-market CAC/LTV potential.

Calibrate

Per-market Bayesian hierarchical model fitting (PyMC + NumPyro + Stan + brms): per-market intercept + slope + interaction + shrinkage + partial-pooling (random-effects) + complete-pooling + no-pooling + hyperprior tuning. Per-market WAIC + LOO-CV model- selection. Per-market posterior predictive check.

Compare

Per-market per-period peer-cohort comparison: per- market vs peer-market same-demographic + same- competitive-density + same-stage-of-lifecycle. Per- market causal-impact (CausalImpact + BSTS + DoWhy + EconML + ATE + CATE + ITE + LATE). Per-market change- point detection (Bayesian + PELT + Binary Segmentation + CUSUM). Per-market replication-crisis discipline (Ioannidis + Amrhein-Greenland-McShane + Rosenbaum Γ + Cornfield + E-value + Bonferroni + BH FDR + Holm + Šidák). Per-market severity P0-P4.

Audit

Per-market per-period WORM scoring record: per-market score snapshot + per-market Bayesian hierarchical model + per-market causal-impact + per-anchor gate- pass + Sherman/Clayton HHI gate + AI-ML provenance + EU AI Act FRIA. Retention: 7-year FTC + 7-year IRS + 7-year HIPAA + 7-year state bar + 6-year SEC + 3-year FINRA + 7-year SOX + GDPR Article 30 + EU AI Act Article 12 + SOC 2 CC7/CC8.

The real ecosystem this sits above

Score + Calibrate + Compare + Audit does not replace geo- demographic vendors, consumer-demand data, competitive- density indices, or Bayesian-hierarchical samplers. It sits above them and writes one canonical per-market per- period scoring record.

Geo-demographic + consumer-demand

Nielsen DMA + Census MSA + ZIP-cluster + Block Group
Esri ArcGIS + MapBox + SafeGraph + Placer.ai + Near
Resonate + Acxiom + Experian + Equifax + Mosaic + PRIZM
Nielsen Scarborough + comScore + Google Trends + SparkToro
SimilarWeb + Semrush + Ahrefs + Moz + Sistrix + SpyFu

Bayesian hierarchical + causal-impact

PyMC + NumPyro + Stan + brms Bayesian samplers
scikit-learn + XGBoost + LightGBM + CatBoost
Google CausalImpact + BSTS + StateSpace + ARIMA + VAR
DoWhy + EconML + causalml causal inference
Robyn + LightweightMMM + PyMC-Marketing Bayesian MMM

Warehouse + streaming + warehouse

Snowflake + BigQuery + Databricks + Redshift + ClickHouse
dbt + Dataform + SQLMesh + Airflow + Prefect + Dagster
Iceberg + Hudi + Delta Lake time-travel
Sensor Tower + App Annie + data.ai + Apptopia mobile
HHI + Lerner Index + Berry concentration competitive density

Compliance overlay

Five anchors run per-market per-period before any scoring distributes to ad-spend allocation + market-expansion decision systems. The first anchor is operationally distinctive: per-market Bayesian hierarchical model + HHI competitive density + price elasticity + CAC/LTV + causal- impact + change-point + replication-crisis discipline converge on every per-market scoring decision.

Anchor 1: Per-market Bayesian hierarchical + HHI + price elasticity + CAC/LTV + causal-impact + change- point + replication-crisis discipline (operationally distinctive)

Per-market (Nielsen DMA + Census MSA + ZIP-cluster + Block Group + Tract + per-state + per-country) consumer-demand scoring algorithm. Per-market consumer- price elasticity (demand + cross-price + income). Per-market competitive density (Herfindahl-Hirschman Index (HHI) + Lerner Index + Concentration Ratio CR3/ CR5 + Berry concentration + per-market entry-barrier + per-market exit-barrier). Per-market CAC/LTV ratio + per-market organic-share + per-market paid-share + per-market AOV potential + per-market churn-risk + per-market saturation-index + per-market expansion- headroom. Per-market Bayesian hierarchical model (per- market intercept + slope + interaction + shrinkage + partial-pooling + complete-pooling + no-pooling + hyperprior tuning + WAIC + LOO-CV). Per-market causal- impact (CausalImpact + BSTS + DoWhy + EconML + counterfactual decomposition + ATE + CATE + ITE + LATE). Per-market change-point detection (Bayesian change-point + PELT + Binary Segmentation + CUSUM). Per-market replication-crisis discipline (Ioannidis + Amrhein-Greenland-McShane + Rosenbaum sensitivity Γ + Cornfield + E-value (VanderWeele Ding 2017) + falsification + negative-control + per-market placebo + reverse causality + Bonferroni + BH FDR + Holm- Bonferroni + Šidák multi-comparison correction).

Anchor 2: Sherman Antitrust + Clayton Act + FTC + Lanham

Sherman Antitrust Act + Clayton Act when per-market HHI signals competitive risk (HHI > 2500 + market- concentration-flag + per-market price-fixing-risk + per-market collusion-flag) + FTC Section 5 + Pfizer 1972 + CFPB UDAAP + Lanham + USPTO + Robinson-Patman + per-state UDTPA.

Anchor 3: FDD Item 19 + HIPAA + FINRA + per-vertical

FDD Item 19 financial performance representations when per-market scoring shared with franchisees + 15-state franchise + HIPAA 45 CFR 164.502/504/514 + state mini- HIPAA + FINRA Rule 2210 + Rule 3110 + SEC Regulation FD + per-state professional licensing.

Anchor 4: EU AI Act + AI-ML per-market scoring

EU AI Act Article 50 transparency when AI-ML per- market scoring + Article 13/14/15 + Annex III when AI-ML per-market scoring drives ad-spend allocation + Article 6/27 FRIA + DSA + DMA. GDPR Article 6/7/22/28/30 + LGPD + DPDP + PIPEDA + Quebec Law 25 + CCPA + CPRA + 18-state.

Anchor 5: Accessibility + SOX + FASB + WORM retention

WCAG 2.2 AA + ARIA + EAA + ADA Title III + Section 508. SOX 302/404/906 + COSO + Exchange Act 13(b)(2) + FASB ASC 280 segment reporting + SEC Reg S-K. NIST AI RMF + ISO 42001 + ISO 27001 + SOC 2 Type II. Per-vendor LLM zero-retention + per-source DPA + per-API rate- limit. Storage: AWS S3 Object Lock + Azure Blob immutable + GCS + Wasabi WORM. Retention: 7-year FTC + 7-year IRS + 7-year HIPAA + 7-year state bar + 6- year SEC + 3-year FINRA + 7-year SOX + GDPR Article 30 + EU AI Act Article 12 + SOC 2 CC7/CC8.

6-workstream reporting cycle

Every two weeks during a Tier 3 Fractional CMO engagement, six workstreams report against the pre-engagement baseline. No per-market scoring accuracy claims. Process commitments only.

1. Per-portfolio per-market per-period scoring coverage. Markets covered + periods scored + KPIs ingested.
2. Score per-market multi-vendor ingestion flow. Per-market organic-share + paid-search + social + visit + demographics + mobile-app + price elasticity + HHI competitive density absorbed.
3. Calibrate per-market Bayesian hierarchical flow. Per-market intercept + slope + interaction + shrinkage + partial-pooling + WAIC + LOO-CV + posterior predictive check.
4. Compare per-market peer-cohort flow. Per-market vs peer comparison + causal-impact + change- point + replication-crisis discipline + multi-comparison correction.
5. Regulatory-defense audit coverage. Per-market Bayesian + HHI + price elasticity + replication-crisis + Sherman Antitrust + Clayton Act + EU AI Act Article 50 + FDD Item 19 + FINRA + SOX + FASB ASC 280.
6. FBC feedback-loop pattern-learning. Per-market realized-vs-predicted scoring + per-market Bayesian-shrinkage retrospective + per-market Sherman/ Clayton HHI enforcement retrospective.

FAQ

What is continuous per-market scoring — and what is the per-market-Bayesian-hierarchical-times-HHI-competitive-density-times-price-elasticity-times-Sherman-Clayton-Antitrust-times-replication-crisis problem distinctive to this skill?: A DTC ecommerce operator with $5M-$50M annual revenue ships per-market (Nielsen DMA 210-market + Census MSA 935-market + ZIP-cluster 30,000+ + Block Group 220,000+) per-period (W-day + W-week + W-month + W-quarter) per-channel (organic + paid-search + paid-social + display + email + SMS + retail) scoring across 5-25 KPIs (demand + conversion + AOV + CAC + LTV + repeat-rate + churn + saturation + expansion-headroom). With 210 DMA × 25 KPIs × W-week = 5,250 per-market-period observations per week + 935 MSA × 25 KPIs = 23,375 per-week observations. The four-skill bundle on the per-market-scoring agent — Score, Calibrate, Compare, Audit — sits above the geo-demographic + consumer-demand + competitive-density + Bayesian-hierarchical substrate (Nielsen DMA + Census MSA + Esri ArcGIS + MapBox + SafeGraph + Placer.ai + Resonate + Acxiom + Experian + Nielsen Scarborough + comScore + Google Trends + SparkToro + SimilarWeb + Semrush + Ahrefs + Moz + Sensor Tower + scikit-learn + XGBoost + LightGBM + CatBoost + PyMC + NumPyro + Stan + brms + Google CausalImpact + BSTS + DoWhy + EconML + Robyn + LightweightMMM + PyMC-Marketing) and writes a per-market per-period canonical scoring record. The operationally distinctive anchor: per-market consumer-demand scoring algorithm + per-market consumer-price elasticity (demand + cross-price + income) + per-market competitive density (Herfindahl-Hirschman Index (HHI) + Lerner Index + Concentration Ratio CR3/CR5 + Berry concentration + per-market entry-barrier + per-market exit-barrier) + per-market CAC/LTV ratio + per-market organic-share + per-market paid-share + per-market AOV potential + per-market churn-risk + per-market saturation-index + per-market expansion-headroom + per-market Bayesian hierarchical model (per-market intercept + per-market slope + per-market interaction + per-market shrinkage + per-market partial-pooling + per-market complete-pooling + per-market no-pooling) + per-market causal-impact (CausalImpact + BSTS + DoWhy + EconML + counterfactual decomposition) + per-market change-point detection (Bayesian change-point + PELT + Binary Segmentation + CUSUM change-point) + per-market replication-crisis discipline (Ioannidis + Amrhein-Greenland-McShane + Rosenbaum Γ + Cornfield + E-value + falsification + negative-control + per-market placebo + reverse causality + Bonferroni + BH FDR + Holm-Bonferroni + Šidák).
Why do Nielsen + Esri + SafeGraph + Resonate + Google Trends + SimilarWeb + Semrush + Ahrefs + Robyn + LightweightMMM break at multi-market-multi-period-Bayesian-hierarchical scale?: Each geo-demographic + consumer-demand + paid-search + MMM vendor ships per-account flat per-market primitive at single-vendor single-KPI level. None coordinates per-market per-period multi-vendor scoring against per-market consumer-demand + per-market price elasticity + per-market HHI competitive density + per-market CAC/LTV + per-market Bayesian hierarchical model (partial-pooling + complete-pooling + no-pooling shrinkage) + per-market causal-impact + per-market change-point detection + per-market replication-crisis discipline. None handles Sherman Antitrust Act + Clayton Act per-market HHI competitive-risk gating at the cross-market level. None gates against FDD Item 19 financial performance representations when per-market scoring shared with franchisees + FINRA Rule 2210 when public-company per-market + SOX 302/404/906 + FASB ASC 280 segment reporting. None writes a per-market per-period WORM scoring audit trail. The four-skill bundle Score + Calibrate + Compare + Audit sits above the geo-demographic + consumer-demand + competitive-density + Bayesian-hierarchical substrate — it does not replace it.
How does Score + Calibrate work?: Score runs per-market per-period multi-vendor data ingestion + per-market consumer-demand scoring: per-market organic-search-share (via SimilarWeb + Semrush + Ahrefs + Moz + Sistrix) + per-market paid-search-share (via SpyFu + iSpionage + KeywordSpy) + per-market social-share (via Brandwatch + Talkwalker + Meltwater + Sprinklr) + per-market visit (via SafeGraph + Placer.ai + Near + Resonate) + per-market consumer-demographics (Nielsen Scarborough + Acxiom + Experian + Equifax + Mosaic + PRIZM + ClaritasGeo) + per-market mobile-app (Sensor Tower + App Annie + data.ai + Apptopia). Per-market consumer-price elasticity (demand elasticity + cross-price elasticity + income elasticity via econometric estimation). Per-market competitive density (HHI Herfindahl-Hirschman Index + Lerner Index + Concentration Ratio CR3/CR5 + Berry concentration + entry/exit barrier). Per-market CAC/LTV potential. Calibrate runs per-market Bayesian hierarchical model fitting (PyMC + NumPyro + Stan + brms): per-market intercept + per-market slope + per-market interaction + per-market shrinkage + per-market partial-pooling (random-effects) + per-market complete-pooling + per-market no-pooling + per-market hyperprior tuning. Per-market WAIC + LOO-CV model-selection. Per-market posterior predictive check.
What does Compare + Audit do?: Compare runs per-market per-period peer-cohort comparison: per-market vs peer-market same-demographic + same-competitive-density + same-stage-of-lifecycle. Per-market causal-impact (Google CausalImpact + BSTS + DoWhy + EconML + counterfactual decomposition + ATE + CATE + ITE + LATE). Per-market change-point detection (Bayesian change-point + PELT + Binary Segmentation + CUSUM change-point). Per-market replication-crisis discipline (Ioannidis 2005 + Amrhein Greenland McShane 2019 + per-market Rosenbaum sensitivity (Γ) + Cornfield + E-value (VanderWeele Ding 2017) + falsification test + negative-control + per-market placebo + reverse causality + Bonferroni + Benjamini-Hochberg FDR + Holm-Bonferroni + Šidák multi-comparison correction). Per-market severity classification: P0 Sherman Antitrust/Clayton Act competitive-risk (HHI > 2500 + market-concentration-flag + per-market price-fixing-risk) + P1 per-market causal-impact gap 72-hour + P2 per-market replication-crisis robustness 7-day + P3 per-market change-point drift 30-day + P4 docs-only. Gate runs 5 anchors per-market per-period before any scoring distributes to ad-spend allocation + market-expansion decision systems. (1) Per-market Bayesian hierarchical + HHI competitive density + price elasticity + CAC/LTV + causal-impact + change-point detection + replication-crisis discipline. (2) Sherman Antitrust Act + Clayton Act + per-market HHI competitive-risk gating + FTC Section 5 + Pfizer 1972 + CFPB UDAAP + Lanham + USPTO + Robinson-Patman + per-state UDTPA. (3) FDD Item 19 financial performance representations when per-market scoring shared with franchisees + 15-state franchise + HIPAA + FINRA Rule 2210 + Rule 3110 + SEC Regulation FD + per-state professional licensing. (4) EU AI Act Article 50 transparency when AI-ML per-market scoring + Article 13/14/15 + Annex III when AI-ML per-market scoring drives ad-spend allocation + Article 6/27 FRIA + DSA + DMA + GDPR Article 6/7/22/28/30 + LGPD + DPDP + PIPEDA + Quebec Law 25 + CCPA + CPRA + 18-state. (5) WCAG 2.2 AA + ARIA + EAA + ADA Title III + Section 508 + SOX 302/404/906 + COSO + Exchange Act 13(b)(2) + FASB ASC 280 segment reporting + SEC Reg S-K. Audit writes a per-market per-period WORM scoring record: per-market score snapshot + per-market Bayesian hierarchical model + per-market causal-impact + per-anchor gate-pass + Sherman/Clayton HHI gate + AI-ML provenance + EU AI Act FRIA. Retention: 7-year FTC + 7-year IRS + 7-year HIPAA + 7-year state bar + 6-year SEC + 3-year FINRA + 7-year SOX + GDPR Article 30 + EU AI Act Article 12 + SOC 2 CC7/CC8.
What does this skill connect to on the per-market-scoring agent and across the swarm?: On the per-market-scoring agent: per-market consumer-demand scoring + per-market competitive density + per-market Bayesian hierarchical + per-market causal-impact + per-market change-point. Across the swarm: per-location AI-calibrated forecasting (#600 same per-location-cohort substrate + same replication-crisis discipline) + per-location per-cohort two-sigma anomaly detection (#608 same statistical-process-control + multi-comparison correction substrate) + root-cause attribution sketch (#604 DOWNSTREAM consumer of per-market scoring) + per-state-overlay-composer (#599 UPSTREAM canonical for Sherman/Clayton + FDD Item 19 + FINRA per-state) + integration-drift-monitor agent (#562 + #569 + #570) + tiered pre-filter deterministic gates + per-vertical compliance overlay. Commercial-pillar parent: /market-expansion-analytics.
What does the 6-workstream pre-engagement-baseline reporting cycle look like for this skill?: Every two weeks during the Tier 3 Fractional CMO with AI Swarm engagement, six workstreams report against the pre-engagement baseline. Workstream 1: per-portfolio per-market per-period scoring coverage — markets covered + periods scored + KPIs ingested. Workstream 2: Score per-market multi-vendor ingestion flow — per-market organic-share + paid-search + social + visit + demographics + mobile-app + price elasticity + HHI competitive density absorbed. Workstream 3: Calibrate per-market Bayesian hierarchical flow — per-market intercept + slope + interaction + shrinkage + partial-pooling + WAIC + LOO-CV + posterior predictive check. Workstream 4: Compare per-market peer-cohort flow — per-market vs peer comparison + causal-impact + change-point + replication-crisis discipline + multi-comparison correction. Workstream 5: Regulatory-defense audit coverage — per-market Bayesian + HHI + price elasticity + replication-crisis + Sherman Antitrust + Clayton Act + EU AI Act Article 50 + FDD Item 19 + FINRA + SOX + FASB ASC 280. Workstream 6: FBC feedback-loop pattern-learning — per-market realized-vs-predicted scoring + per-market Bayesian-shrinkage retrospective + per-market Sherman/Clayton HHI enforcement retrospective.

Engage Completions

Two ways to engage. The Tier 1 AI Readiness Assessment maps the geo-demographic + consumer-demand + competitive- density + Bayesian-hierarchical substrate + per-market Bayesian + HHI + price elasticity + CAC/LTV + causal- impact + replication-crisis discipline surface against the Score + Calibrate + Compare + Audit bundle. The Tier 3 Fractional CMO with AI Swarm embeds 1-2 days per week for 6+ months and runs the bundle end-to-end against the per-market-scoring agent across the swarm.

Tier 1 AI Readiness Assessment — $10k, 2-3 weeks Tier 3 Fractional CMO with AI Swarm — $15-25k/mo Not sure which tier? Take the 3-question quiz