Cohort analysis and customer retention
Complete cohort analysis to measure and understand customer retention with aha moment identification.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
Je veux réaliser une analyse de cohorte pour [PRODUIT/SERVICE] avec les données suivantes : [DESCRIPTION_DONNEES] (dates d'inscription, connexions, achats, churns sur [PERIODE]).
Type de cohortes : [TYPE_COHORTE] (ex : mois d'acquisition, canal d'acquisition, plan souscrit, segment géographique)
Métrique de rétention : [METRIQUE] (ex : connexions actives, transactions, MRR conservé)
Réalise l'analyse de cohorte complète :
- Construis la matrice de rétention par cohorte mensuelle sur [N_MOIS] mois
- Calcule le taux de rétention à J+7, J+30, J+90, J+180 et J+365
- Identifie les cohortes les plus performantes et les facteurs explicatifs
- Calcule le taux de churn mensuel et annuel par cohorte
- Projette la valeur vie client (LTV) à partir des courbes de rétention
- Compare les cohortes selon [DIMENSION_COMPARAISON] (ex : canal d'acquisition, plan)
- Identifie le "moment aha" : à quel stade les utilisateurs retenus divergent des churners
- Propose 3 actions pour améliorer la rétention à [PHASE_CRITIQUE] jours
Fournis le code SQL ou Python pour construire la matrice.
Personalize this prompt with Léa
Léa rewrites this prompt for your job and your exact goal — 3 quick questions.
Why this prompt works
<p>This prompt is powerful because it integrates aha moment identification, a key concept for improving onboarding, in addition to classic retention metrics. It links descriptive analysis to concrete action.</p>
Use Cases
Expected Output
Cohort matrix, retention rates by period, projected LTV, aha moment identification, and retention action plan.
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
- LéaAI
Pour une analyse plus fine, remplace la rétention brute par la rétention nette (incluant expansions et contractions) si tu utilises le MRR. Et complète avec une analyse de survie (Kaplan‑Meier) sur les cohortes pour estimer le churn sans biais de censure.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Go further
Similar Prompts
Advanced Excel formulas for data analysis
Provides advanced Excel formulas tailored to specific analysis problems with explanations and variants.
Jobs-to-be-Done analysis
Understanding the real job of the user
Evaluate a regression model
Evaluate regression model performance
Prompt Claude to Analyze User Feedback
Analyzing user feedback is a strategic lever for any company looking to improve its products and services. However, manually processing hundreds or even thousands of customer reviews is time-consuming and prone to interpretation bias. Claude excels at this task thanks to its ability to understand natural language nuances, detect implicit sentiments, and automatically categorize feedback along relevant axes. Whether it's product reviews, support tickets, NPS survey responses, or social media comments, Claude can extract actionable insights in seconds. By properly structuring your prompt, you get a systematic analysis that identifies recurring trends, prioritizes problems by impact, and provides concrete recommendations. This approach transforms raw qualitative data into a clear decision-making dashboard, allowing product, support, and marketing teams to act quickly on friction points identified by your users.