MicroStrategy ONE

Telco Churn Example (Using Decision Tree Analysis)

You are reviewing your telecommunication trends and are interested in the likelihood of customers to churn based on psychographics and communication habits.

Use a decision tree to analyze the following inputs:

  • Average Minutes during Off-Peak times
  • Average Minutes during Peak times
  • Dropped Calls
  • Helpdesk Calls
  • Renewals
  • Age Range
  • Gender
  • Household Count
  • Marital Status
  • Income Bracket

You will need to create metrics for each attribute form. These metrics will be used as inputs into the training metric. Examples are:

	Max([Customer Age Range]@ID) {Customer}
	Max([Customer Gender]@DESC) {Customer}
	Max([Household Count]@DESC){Customer}

The example Tutorial project includes reports, metrics, and other objects created for this telco churn example (search the project for "Telco Churn"). You can use the objects in the Tutorial project to step through the example and determine how it can be applied to your reporting environment.

Use the Training Metric Wizard to design a training metric, following the procedure below.

To Create a Training Metric for Decision Tree Aanalysis

This procedure assumes you have already created a TelcoChurn metric to use as the dependent metric.

  1. Choose Tools > Training Metric Wizard.

    To skip the Introduction page when creating training metrics in the future, select the Don't show this message next time check box.

  2. Click Next.
  3. Select Decision tree as the type of analysis.
  4. Specify the k value for k-Fold Cross Validation.
  5. Click Next.
  6. Select TelcoChurn metric as the Dependent Metric.
  7. Add the following metrics to the list of Independent Metrics:
    • AvgMinOffPeak
    • AvgMinPeak
    • DroppedCalls
    • HelpdeskCalls
    • Renewals
    • Age Range
    • Gender
    • Household Count
    • Marital Status
    • Income Bracket
  8. Click Next.
  9. Select the Automatically create on report execution check box.
  10. Select Predicted Value.
  11. Click Finish. You can now include the metric in a training metric to create a predictive metric, as described in Creating a Predictive Model Using MicroStrategy.
  12. Create a new report containing the training metric and the Customer attribute. Filter the report on every seventh customer. (Which customers to include is arbitrary but must offer a decent sample size of the data.)
  13. Execute the report to generate a decision tree model.

    A predictive metric is created in the folder you specified in the Training Metric Wizard. The default location is the My Objects folder.

    When applied to all customers, the predictive metric reveals hundreds of customers out of thousands of customers that are likely to churn. Efforts can now be made to target these customers for extra deals or value analysis.