ds@mcpanalytics.aiA data scientist you can email your data and question to, and get a reliable response. Not AI slop.A data scientist you can email. Not AI slop.
Upload your customer list, map the start date and churn column, and get your churn rate, a proper survival curve of customer lifetime, cohort-by-cohort churn, and a ranked list of what predicts cancellation. Free.
Free analyses run on up to 10,000 rows. Larger files are randomly sampled to that size, so sign up to analyze your full dataset.
Analysing churn and customer lifetimes...
Sent to . Inside: churn rate and cohort breakdown, Kaplan-Meier survival curve with confidence band, churn drivers ranked by odds ratio, lifetime distributions, R code, and AI insights.
Analyze another fileThe practical guide behind this tool: when it applies, how to read the output, and the traps that make it say the wrong thing.
Each customer's lifetime runs from their start date to their churn date (or to the latest date in the file if still active — a censored observation). The analysis computes the overall churn rate, groups customers into signup cohorts and compares churn across them, fits a Kaplan-Meier survival curve — the standard estimator that uses censored customers correctly instead of dropping them — to estimate the median lifetime, and fits a logistic regression of churn on the mapped driver columns to rank them by odds ratio with 95% confidence intervals.
Use it whenever you have customer-level data with a start date and any usable churn signal — subscriptions, memberships, contracts, repeat-purchase customers.
Not for event-level data (aggregate to one row per customer first), and not for comparing survival between predefined groups with formal tests — use the survival analysis tool for log-rank comparisons.
Built for: Founders, growth and retention teams, and analysts working subscription or repeat-purchase businesses
Typical data source: A customer export: one row per customer with signup date, cancellation status, and attributes like plan or region
One row per customer. For example, a subscription customer export:
Minimum 30 rows · Best with 200-10,000 customers with 1-8 driver columns
Standard-library analysis: how many customers churn, when they churn, and what predicts it. Map a start date and a churn indicator (a cancel-date column, a 0/1 flag, or yes/no text) and get the overall churn rate, churn by monthly signup cohort, a Kaplan-Meier survival curve of customer lifetime that counts still-active customers correctly, and — if you map candidate driver columns like plan or region — a logistic-regression ranking of churn drivers with odds ratios and confidence intervals.
Churn rate per signup cohort — whether the customers you acquired recently stick better or worse than older cohorts.
The share of customers still active after each number of days, with still-active customers counted correctly; where it crosses 50% is the median lifetime.
Every mapped driver on one odds-ratio scale with confidence intervals — above 1 raises churn odds, below 1 protects.
How long churned customers lasted versus how long active ones have been around — shows whether churn concentrates early.
The exact per-cohort counts and rates behind the cohort chart.
Plain-English interpretation of what the numbers mean, what's significant, and what to do next.
How bad is my churn, really?
Map when customers started and how you know they churned — a cancel date, a flag, or yes/no. You get the churn rate, a survival curve that handles still-active customers properly, and the median customer lifetime.
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data: R analyses, interactive reports, AI insights, and PDF export.
Try Free, No Credit CardYour turn
Bring your own data and the question you actually need answered.
CympleData Scientist Send me your data and question, I’ll send you the analytics. ds@mcpanalytics.ai
Tell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.