Skip to main content

Module

Model governance

4 Topics

50 mins

Visible to: All users
Beginner Pega Customer Decision Hub '23 English
Verify the version tags to ensure you are consuming the intended content or, complete the latest version.

AI has the potential to deliver significant benefits, but improper controls can result in regulatory issues, public relations problems, and liability. The Pega T-Switch™ settings in Prediction Studio, which define the transparency thresholds for business issues, help companies to enable users to deploy AI algorithms responsibly and safely.

U+ Bank uses Pega Customer Decision Hub™ to personalize the offers that customers see when they log in to the U+ Bank website. Customer Decision Hub provides tools to give local and global explanations for the behavior of the adaptive model, such as Customer Profile Viewer for local explanations and the ADM predictor importance report for global explanations. An ethical bias simulation enables you to test your engagement policies for unwanted bias.

After completing this module, you should be able to:

Explain how Prediction Studio reflects the model transparency policy of the company.
Provide local explanations in Customer Profile Viewer for a single propensity calculation of an adaptive model.
Use the ADM predictor importance report to provide global explanations of the factors that drive predictions.
Explain the function of an ethical bias simulation.
Detect unwanted bias in engagement policies.

Practice what you learned in the following Challenge:

Detecting unwanted bias in engagement policy conditions v4

Available in the following mission:

AI for 1:1 Customer Engagement v3

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