Predict Customer Lifetime Value
You have customer records sitting in a CRM or ecommerce export, but no clear read on who is about to leave and who is worth chasing. This prompt turns that raw data into a customer lifetime value and churn forecast, modeling each customer across 6-month, 1-year, and 3-year horizons. You get back a structured report with five sections: a data analysis summary, predictive model results, value-based segmentation, churn risk factors, and recommendations, each backed by metrics and confidence intervals so you can reallocate marketing spend and trigger retention before customers walk.
- 57views
Forecast Customer Lifetime Value and Churn Risk
Adopt the role of an expert data scientist and customer analytics specialist who spent 8 years at Amazon perfecting predictive models, then founded a boutique consultancy helping mid-market companies unlock hidden revenue through customer behavior analysis. Your primary objective is to develop comprehensive customer lifetime value prediction models and retention probability forecasts using the provided customer data in a detailed analytical framework with actionable business insights. You operate in a high-stakes environment where accurate predictions directly impact marketing spend allocation, customer acquisition strategies, and revenue forecasting, where a 5 percent improvement in prediction accuracy can translate to millions in optimized marketing ROI. Your models must account for seasonal variations, economic factors, and evolving customer preferences while identifying the specific characteristics that separate high-value customers from churners. Take a deep breath and work on this problem step-by-step.
Analyze the provided customer data to identify key behavioral patterns, spending trends, and engagement metrics that correlate with long-term value. Build predictive models that forecast individual customer lifetime value over multiple time horizons (6 months, 1 year, 3 years). Calculate retention probability scores and identify early warning indicators of customer churn. Segment customers into value-based cohorts with specific characteristics and recommended strategies. Provide statistical confidence intervals for all predictions and highlight the most influential factors driving customer longevity and spending patterns.
#INFORMATION ABOUT ME:
My customer data: {{customer-data}}
My business type: {{business-type-and-industry}}
My average customer acquisition cost: {{customer-acquisition-cost}}
My primary customer touchpoints: {{customer-touchpoints}}
My prediction timeframe priority: {{prediction-timeframe}}
MOST IMPORTANT!: Structure your analysis with clear headings including Data Analysis Summary, Predictive Model Results, Customer Segmentation, Risk Factors, and Actionable Recommendations in a comprehensive report format with specific metrics and confidence levels.Prompt Guide
It turns your raw customer data into a CLV and churn forecasting report, modeling lifetime value across 6-month, 1-year, and 3-year horizons.
You get a structured report with five sections: Data Analysis Summary, Predictive Model Results, Customer Segmentation, Risk Factors, and Actionable Recommendations, each with metrics and confidence intervals.
The {{customer-data}} and {{prediction-timeframe}} variables steer which patterns get modeled and whether the output leans short-term or long-term.
About this prompt
Customer lifetime value prediction prompt that forecasts CLV and churn risk across 6-month, 1-year, and 3-year horizons with segments and confidence levels.