Taxonomy Icon

Artificial Intelligence

Monitor WML model With AI OpenScale

Get the code View the demo


In this developer code pattern, we will continue from “Predict heart medicine using machine learning” using the model for best drug treatment that was created and deployed. We will create a data mart for Watson™ Machine Learning deployments and include steps for performance, bias, and quality monitor configurations.


When you have completed this code pattern, you will understand how to:

  • Set up AI OpenScale data mart
  • Bind Watson Machine Learning to the AIOS data mart
  • Add subscriptions to the data mart
  • Enable payload logging and performance monitor for both subscribed assets
  • Enable quality (accuracy) monitor for best heart drug asset
  • Enable fairness monitor for best heart drug asset
  • Score the best heart drug model using Watson Machine Learning
  • Use data mart to access tables data via subscription


  1. The developer creates a Jupyter Notebook on Watson Studio, using the existing project from “Predict heart medicine using machine learning.”
  2. The Jupyter Notebook is connected to a PostgreSQL database, which is used to store AI OpenScale data.
  3. The notebook is connected to Watson Machine Learning, where the existing ML model for Heart Medicine Predictor is used.
  4. AI OpenScale is used by the notebook to log payload and monitor performance, quality, and fairness.



For detailed instructions, please see the README.