Customer Segment Analysis — Quick Prioritization

You're a marketing data analyst. Perform a customer segment analysis. Population: {{customer_population}} Date range: {{date_range}} Approx. customer count: {{total_customers}} Business type: {{{business_type: ecommerce, SaaS/subscription, B2B, marketplace, retail, app-based}}} Data source: {{{data_source: CRM, analytics platform, ecommerce platform, data warehouse, hypothetical/benchmarks}}} Segment by: {{primary_dimensions}} Cross-reference top segments by: {{secondary_dimensions}} **Calculate per segment:** Revenue, AOV, LTV ({{{ltv_method: historical total, predicted, 90-day, 12-month}}}), repeat/retention rate, CAC (if available), LTV:CAC ratio, segment size, growth rate. **Rank by:** {{{ranking: LTV descending, LTV:CAC ratio, revenue contribution, growth rate, composite score}}} **Minimum segment size:** {{min_segment_size}} customers (exclude anything smaller) **Flag segments where:** {{segment_conditions}} **Deliver:** 1. **Executive summary** — 3-5 key findings, single most actionable insight, revenue at stake. 2. **Ranked segment table** — Segment | Size | Revenue | AOV | LTV | Repeat Rate | Growth | Rank. Flag high-value segments. 3. **Top 5 deep-dives** — profile, key metrics, behavioral drivers, growth potential, risks. 4. **Segment intersections** — which dimensional combinations create "super segments" worth targeting specifically? 5. **Targeting playbook for top {{num_segments}} segments** — recommended channels, targeting approach, messaging angle, budget allocation %, expected ROI, first test to run. 6. **Deprioritize list** — segments consuming disproportionate resources vs. value. 7. **Data gaps** — what additional data would improve this analysis. Rules: Flag where small samples limit confidence. Don't confuse correlation with causation. Segments must be targetable, not just describable. Account for CAC when recommending budget. Recommend against over-segmentation — merge segments that behave nearly identically.