Adaptive models are a core component of Pega's real-time, self-learning decisioning capability. They operate by continuously capturing customer responses (outcomes) to various propositions, such as accepting or rejecting an offer. This data is then used to automatically update and refine the underlying predictive models. This iterative learning process ensures that the recommendations made by the decision strategy adapt to changing customer behaviors and market trends, thereby maintaining and improving their effectiveness over time.

A. Adaptive models are a component for predicting behavior within a decision strategy; they do not automate all decision-making processes in an application.

C. The purpose of adaptive models is to enable personalization by learning from individual customer behavior, which is the opposite of standardizing interactions.

D. This describes a static, rule-based approach. Adaptive models specifically learn and evolve beyond predefined rules to keep predictions relevant.

---

1. Pega Documentation: Adaptive models. In the section "How adaptive models work," it states, "Adaptive models are self-learning, which means that they can automatically detect changes in customer behavior and adjust their predictions accordingly... The models learn from every customer response and become more accurate over time."

Source: Pega Community > Documentation > Pega Platform 8.8 > Decisioning > Analytics > Adaptive models.

2. Pega Academy Courseware: Pega Decisioning Consultant (24.1) Mission. The module "Predicting customer behavior using real-time data" explains that adaptive models capture customer responses in real-time. It details how the Adaptive Decision Manager (ADM) service uses these responses to update the models, improving the accuracy of future predictions.

Source: Pega Academy > Missions > Pega Decisioning Consultant (24.1) > Predicting customer behavior using real-time data > Module: Adaptive modeling.