Customer Cohort Analysis Framework
Analytics & ReportingadvancedClaude 3.5 Sonnet or GPT-4o. Claude excels at structured analysis and can handle complex data frameworks with clear reasoning. GPT-4o provides faster processing for large datasets and strong pattern recognition. Both handle multi-step analytical thinking required for cohort decomposition and causal inference.
When to Use This Prompt
Use this prompt when you need to understand how different customer groups behave over time and identify which cohorts are most valuable or at-risk. It's essential for CMOs building retention strategies, optimizing marketing spend allocation, and forecasting revenue by customer segment. Perfect when you have historical customer data and need to move beyond vanity metrics to actionable segmentation.
The Prompt
You are a data analytics expert specializing in customer behavior segmentation. I need you to help me analyze customer cohorts and identify actionable insights for retention and growth strategies.
## Data Context
I have customer data spanning [TIME_PERIOD] with the following attributes:
- Acquisition date: [DATE_RANGE]
- Customer segments: [LIST_SEGMENTS]
- Key metrics tracked: [LIST_METRICS]
- Industry/business model: [INDUSTRY]
- Current customer base size: [NUMBER]
## Cohort Analysis Requirements
### 1. Cohort Definition
Define cohorts based on [COHORT_GROUPING_METHOD: e.g., "acquisition month," "product purchased," "geographic region"].
For each cohort, calculate:
- Initial cohort size
- Retention rate at 30, 60, 90, and 180 days
- Churn rate trends
- Lifetime value (LTV) estimates
- Revenue contribution by cohort
### 2. Comparative Analysis
Compare cohorts across:
- Engagement metrics: [SPECIFY_METRICS]
- Product adoption rates
- Feature usage patterns
- Customer satisfaction scores (if available)
- Support ticket frequency and resolution time
### 3. Behavioral Patterns
Identify:
- Early warning signs of churn within each cohort
- High-value customer characteristics
- Seasonal or cyclical patterns
- Inflection points where behavior changes significantly
### 4. Actionable Insights
For each major cohort, provide:
- Key performance drivers (what's working)
- Risk factors (what's failing)
- Specific recommendations for improving retention
- Recommended marketing interventions by cohort
- Predicted impact of recommended changes (estimated uplift %)
## Output Format
Structure your analysis as:
1. Executive summary (key findings in 3-4 bullets)
2. Cohort performance table with key metrics
3. Trend analysis with specific observations
4. Risk assessment by cohort
5. Prioritized recommendations with implementation timeline
6. Success metrics to track post-implementation
## Context for Recommendations
Consider:
- Current marketing budget constraints: [BUDGET]
- Technology stack capabilities: [TOOLS]
- Team capacity: [TEAM_SIZE]
- Business priorities: [PRIORITIES]
Provide insights that are realistic to implement and directly tied to revenue impact.
Get the Full AI Marketing Learning Path
Courses, workshops, frameworks, daily intelligence, and 6 proprietary tools — built for marketing leaders adopting AI.
Trusted by 10,000+ Directors and CMOs.
Tips for Best Results
- 1.Provide actual historical data points or realistic sample data in brackets—vague inputs produce generic outputs. Include specific metric names, date ranges, and customer counts for precise analysis.
- 2.Specify your cohort grouping method upfront (acquisition date, product, geography, channel). Different groupings reveal different insights; mixing methods creates confusion.
- 3.Request quantified recommendations with estimated impact percentages. This forces the AI to ground suggestions in data and helps you prioritize by ROI potential.
- 4.Ask for success metrics and tracking methodology at the end. This ensures recommendations are measurable and you can validate the AI's predictions against actual results post-implementation.
Example Output
## Executive Summary
- Q1 2024 cohort shows 15% higher 90-day retention vs. Q4 2023, suggesting improved onboarding effectiveness
- Geographic cohorts reveal 40% variance in LTV; EMEA underperforming by $2,400 per customer
- Mobile-first acquisition cohort demonstrates 3x higher feature adoption but 22% lower LTV due to pricing tier mismatch
## Cohort Performance Table
| Cohort | Size | Day-30 Retention | Day-90 Retention | Avg LTV | Monthly Churn |
|--------|------|------------------|------------------|---------|---------------|
| Q1 2024 (Web) | 1,240 | 78% | 62% | $4,850 | 4.2% |
| Q1 2024 (Mobile) | 3,890 | 71% | 48% | $2,100 | 7.8% |
| Q4 2023 (Web) | 980 | 72% | 54% | $4,200 | 5.1% |
## Key Findings
**High-Value Pattern:** Web-acquired customers in enterprise segment show 89% day-90 retention and $7,200 LTV. These customers typically complete 3+ onboarding sessions and adopt 5+ premium features within first 30 days.
**At-Risk Cohort:** Mobile cohort acquired in January shows accelerating churn (7.8% monthly). Root cause analysis suggests pricing tier misalignment—70% are on starter plan but using mid-market features.
## Prioritized Recommendations
1. **Immediate (Week 1-2):** Implement tiered mobile onboarding to guide starter-plan users to appropriate feature set. Expected impact: +3% retention, +$180 LTV.
2. **Short-term (Month 1):** Launch targeted upsell campaign for high-engagement mobile users showing feature adoption patterns. Expected impact: +8% ARPU.
3. **Medium-term (Month 2-3):** Redesign EMEA sales process to emphasize localized support and compliance features. Expected impact: +$400 LTV, +12% conversion.
Related Prompts
Related Reading
Get the Full AI Marketing Learning Path
Courses, workshops, frameworks, daily intelligence, and 6 proprietary tools — built for marketing leaders adopting AI.
Trusted by 10,000+ Directors and CMOs.