Adaptive model tab on the Adaptive Model form
On the Adaptive Model tab, you can define the basic settings of an Adaptive Model rule instance by performing the tasks, such as defining the model context and potential predictors. You can also view the parameterized predictors.
- Define Service Package form – Completing the Context tab
- An adaptive model rule is a configuration that controls multiple ADM models. The model context consists of one or more model identifiers, for example, issue, group, and proposition name. This configuration generates models for each unique set of model identifiers. If separate models are needed in different channels, then that channel can be added to the model context.
- Define potential predictors
- Predictors are fields from within the primary page context that act as input for adaptive learning. For each model, the ADM service selects active predictors from the list of potential predictors, based on the performance of the predictors and their correlations. For more information, see Adding adaptive model predictors.
- View the parameterized predictors
- Parameterized predictors are parameters from outside of the primary page context that you can configure as additional input in the adaptive learning process. These parameters can be proposition attributes from the Strategy Results (SR) class. For more information, see Parameterized predictors.
- Service Package form – Completing the Context tab
Complete the Context section to indicate whether stateful or stateless processing applies to this package, and to identify an access group for listeners and requestors.
- Adding adaptive model predictors
Create predictors which are input fields for the adaptive models. When creating an adaptive model, select a wide range of fields that can potentially act as predictors.
- Parameterized predictors
To use input fields that are not available on the primary page where the rule is defined, but which are on the Strategy Results page (SR), configure these input fields as parameterized predictors for an adaptive model. If you do not specify parameterized predictors, your adaptive model can learn only from properties that are defined within the primary page context.
- About Adaptive Model rules
Adaptive models are self-learning predictive models that predict customer behavior.