Skip to main content

Adaptive model outputs

Model outputs

Adaptive models produce four outputs: Propensity, Evidence, Performance, and Positives.

Propensity is the predicted likelihood of positive behavior, for example, the likelihood of a customer accepting an offer. The propensity for every action starts at 0.5 or 50% (the same as a flip of a coin) because in the beginning, the model has no response behavior on which to base its predictions.

Evidence is the number of responses used in the calculation of the Propensity.

Performance is how well the model can differentiate between positive and negative behavior. Again, the initial value is 50%, with 100% being perfect performance. As a result, the performance value is somewhere between 50 and 100.

Positives is the number of positive outcomes that has been received by the model.


In strategies, model propensity is automatically mapped to the strategy property called .pyPropensity. There is no automatic mapping for the Evidence, Performance or Positives outputs, but a strategy designer can manually map the outputs to any of the strategy properties under the Output mapping tab.


This Topic is available in the following Modules:

If you are having problems with your training, please review the Pega Academy Support FAQs.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice