You can monitor the adaptive models in the Adaptive Decision Manager (ADM) system on the Monitoring tab of the Adaptive Model rule form. Information that you obtain from the reports, such as predictive performance and success rate of individual models, is useful for business users and strategy designers, and might result in changes to the decision strategies and adaptive models.
Notes:
In the bubble chart that is displayed on the Models tab, each circle represents a model for a specific proposition. The size of a circle represents the number of responses (positive and negative). When you place the cursor on the circle, you can view the number of responses, the performance, and the success rate.
The Model Performance axis indicates the accuracy of the outcome prediction. The model performance is expressed in coefficient of concordance (CoC), which has a range between 50 and 100. A high CoC means that the model is good at predicting the outcome; a low CoC means that the model is not good at discriminating between positives and negatives.
The Proposition Success Rate axis indicates the success rate expressed in percentages. This rate is the number of positive responses divided by the total number of responses. When customers receive propositions for which they have a high propensity score, the success rate of a model increases.
The data that is used to visualize the models in the bubble chart is displayed below the chart. The data includes the model in the model context (business issue and group), response count, performance, and success rate. You can use the reporting actions to generate a behavior report or a performance overview report.