CART® Classification for Predict Service Level

Use CART® Classification to use complex relationships with multiple predictors to predict whether a service level agreement is likely to be met.

This example applies to the Customer Contact Center Module. For more information, go to www.minitab.com/customer-contact-center-module.

Example

Service level is the ability to meet the standards in a Service Level Agreement (SLA).

In this worksheet, Service Level is the response. The response event is Not met. Schedule Adherence is a continuous predictor, and Call Center Location and Department are categorical predictors.

C1-T C2 C3-T C4-T
Service Level Schedule Adherence Call Center Location Department
Not met 70 East Billing
Met 80 East Customer service
Met 82 West Billing
Met 76 West Customer service

How-to

  1. Choose Solutions Modules > Functions > Customer Contact Center KPIs, then select Launch.
  2. Under Service Level, select Service level.
  3. Select Predict service level, then click OK.
  4. Select CART® Classification, then click OK.
  5. In Response, enter the binary variable that contains the service level agreement data. Binary variables are categorical variables that have two possible levels, such as pass/fail or true/false. The response is also called the Y variable.
  6. In Response event, select the value that represents an unmet service level agreement.
  7. In Continuous predictors, enter the continuous variables that may explain or predict whether a service level agreement is not met. The predictors are also called X variables.
  8. In Categorical predictors, enter the categorical variables that may explain or predict whether a service level agreement is not met. The predictors are also called X variables.
  9. Click OK.
Tip

For more information about this analysis, click Help in the main dialog box.