Skip to main content
Analyze Propensity to Churn
Updated today

The Analyze Propensity to Churn notebook in AI Workbench helps marketing teams evaluate and compare churn predictions across different customer segments. By analyzing churn rates based on profile attributes, businesses can identify trends, assess risk factors, and refine retention strategies.

Before you begin, make sure you have customer contract or subscription start and end dates stored in BlueConic profile properties.


Add an Analyze propensity to churn notebook

  1. Navigate to More > AI Workbench > Add notebook.

  2. Choose Analyze propensity to churn notebook from the pop-up window.

  3. Give your notebook a name.

  4. Save your settings.


Set the Analyze propensity to churn notebook parameters

  1. Select the Parameters tab.

  2. For the segments to compare parameter, choose one or more customer segments for the notebook to predict churn probability.

  3. Select profile properties for contract start and end dates in date-time format.

  4. (Optional) Adjust the maximum profiles the model examines. Higher numbers improve accuracy but increase processing costs. Use 0 to include all profiles in the segment.

  5. (Optional) You can change the propensity to churn model and color map used to display your results. Options include:

  6. Save your settings.


Run an Analyze propensity to churn notebook

  1. Select the Schedule and run history tab.

  2. Click Run now to run the notebook analysis manually.

  3. To schedule the import and export for a future date, activate Enable scheduling.

    1. Click the Settings icon to select how to schedule the notebook by choosing an option from the drop-down list.

    2. Set a time for the import. Click OK.

  4. Save your settings.

After running the notebook, you can view its output by clicking Preview. Scroll all the way to the bottom to see a graphical representation of the churn analysis. You can use the Notebook all cells insight to create a sharable dashboard with churn prediction graphics.


Next steps

Did this answer your question?