Skip to content
ENExplore Calculators

Churn Prediction Value Calculator

Work out churn prediction value instantly with clear inputs, formula shown and shareable results.

About Churn Prediction Value Calculator

The value of a churn model is not its AUC but the customers a retention action actually saves. That chain has three multipliers: how many churn, what share the model catches (recall), and what share of contacted churners the intervention rescues — typically only 20 to 30 percent. Multiplying through usually reveals a much smaller prize than the model's accuracy metrics suggest.

Formula

Retention value

churners = customers x churn rate; identified = churners x recall; saved = identified x save rate (25%); value = saved x value per retained customer

Worked example

With the default values below, Churn Prediction Value Calculator returns Annual value retained of $240,000.00. Change any input above and every figure here is recalculated in your browser.

Inputs used

Customers in the baseminimum 1
50,000
Annual churn rateaccepts 0.01–100 %
8 %
Share of churners the model identifiesaccepts 0–100 %
60 %
Value of retaining one customerminimum 0
400

Results

Annual value retained
$240,000.00
Customers expected to churn
4,000
Churners the model flags
2,400
Customers actually saved at a 25% save rate
600

Step by step

  1. 1Values used
  2. 2Retention value
  3. 3Annual value retained= 240,000.00
  4. 4Customers expected to churn= 4,000
  5. 5Churners the model flags= 2,400
  6. 6Customers actually saved at a 25% save rate= 600

Assumptions and limits

  • The result is derived only from the 4 inputs listed above. Anything not among them is not part of the calculation.
  • In particular, this calculator does not take inflation, tax or fees or charges into account.
  • Figures are rounded for display to 2 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Why assume only a 25 percent save rate?

Most flagged customers have already decided, and outreach converts a minority. Measure your own save rate with a randomised holdout rather than assuming the intervention always works.

Should I chase higher recall?

Only up to the point where precision keeps the contact cost sensible. Contacting the whole base gives 100 percent recall and destroys the economics.

Churn Prediction Value Calculator | Calcrivo