Creating an adaptive model

Create an adaptive model to predict customer behavior. Refer to your adaptive model in a strategy to use the propensity that the model returns. When you run the strategy, adaptive models are created automatically for each unique combination of model identifiers in the Adaptive Model rule instance.

  1. Open Analytics Center portal.
  2. Click Create > Adaptive model.
  3. Enter a name for your model.
  4. Select the applicable business issue.
  5. In the Positive outcome section, perform the following actions to indicate which customer responses to use as indicators of positive behavior from which the predictors learn:
    • Place the cursor in the empty field and select an available outcome for the Adaptive Model rule by pressing the Down Arrow key.
    • Click Add outcome to define a new positive outcome for the Adaptive Model rule.
    Accept
  6. In the Negative outcome section, perform the following actions to indicate which customer responses to use as indicators of negative behavior from which the predictors learn:
    • Place the cursor in the empty field and select an available outcome for the Adaptive Model rule by pressing the Down Arrow key.
    • Click Add outcome to define a new negative outcome for the Adaptive Model rule.
    Reject
  7. Enter the applicable class of the Adaptive Model rule.
  8. Select a rule set and a branch.
  9. Click Create.
    You can access the model that you created on the Models tab of the Analytics Center portal.
  10. Configure the model in the Adaptive Model rule by performing the following actions:
    1. In the Models tab of the Analytics Center portal, browse to the Adaptive Model rule that you created.
    2. Click the rule to open it.
    3. Configure the Adaptive Model rule to meet your business objectives by adding a list of candidate predictors on the Adaptive model tab of the Adaptive Model rule form.

      It is recommended that you add an extensive list of candidate predictors for your adaptive model instances to learn from. In the course of the learning process, adaptive models automatically select the best-performing predictors. These predictors become active. The remaining predictors become inactive.

      For more information, see Adaptive Model rule.