Monitoring adaptive models

It is a regular data scientist task to inspect the health of the adaptive models and share the findings with the business. The predictive performance and success rate of individual adaptive models provide information that can help business users and decisioning consultants to refine business processes. The content of this module showcases adaptive models used in Customer Decision Hub predictions that aim to optimize customer engagement but is equally relevant for case management predictions.

Learn how to monitor the performance of the adaptive models and how to export the raw data that adaptive models have processed to inspect and validate the predictors.

Beginner

Inglês

Depois de concluir este módulo, você deverá ser capaz de:

Name the key metrics of adaptive models visualized in the bubble chart

Inspect individual active and inactive predictors

Explain how predictors with similar predictive performance are grouped

Examine the propensity distribution and the trend for the whole model

Export the raw data that is used by adaptive models

Pratique o que aprendeu no seguinte Desafios:

Monitoring adaptive models v2 Exporting historical data v2

Disponível na seguinte missão:

Pega Process AI Essentials v2

Tópicos

Regular monitoring of adaptive models

10 min

Inspecting adaptive models

10 min

Exporting historical data

10 min

Quiz do módulo

10 min