Custom Machine Learning Models

The Custom Machine Learning Models integration allows users to deploy any type of model and use input data from OpenPages® fields to generate predictions that are used as insights in OpenPages views.

This feature is available in OpenPages version 8.3.0.2 and later.

To configure the model in OpenPages, you need the Custom Machine Learning Models application permission. If you don't have this permission, the Administration menu > Integrations > Custom Machine Learning Models menu item is not visible.

You can use AI models that are built with AutoAI on Watson Studio or developed by a data science team, and then deployed on IBM Watson® Machine Learning on IBM Cloud. You can connect data from OpenPages fields as inputs to the model to generate live predictions and display the insights in OpenPages views and workflows.

The following models are examples of use cases that are supported:
  • Cognitive control models to evaluate the quality of controls during time of creation.
  • Issue similarity models to identify if new issues created already exist in OpenPages.
  • Regression models that can estimate the loss of a loss event.
The following are prerequisites for configuring Custom Machine Learning Models in OpenPages:
  • Models that are deployed on IBM Watson Machine Learning must be trained and tested by a data scientist to ensure that the models have sufficient accuracies before they are deployed on IBM Watson Machine Learning.
  • You must be familiar with the model output format on IBM Watson Machine Learning.
  • You must understand which components of the models output you want to extract.
  • You must understand JSONata (https://try.jsonata.org) syntax to extract relevant pieces of information.