Skip to main content

Tutorial 3A: Build, deploy, score, and monitor an H2O Driverless AI model with H2O Driverless AI and H2O MLOps

Overview​

In this tutorial, you'll explore how to build, deploy, score, and monitor an H2O Driverless AI model with H2O Driverless AI and H2O MLOps.

Throughout the tutorial, we'll harness the renowned Default of Credit Card Clients Dataset to construct a classification model predicting clients' probability of defaulting on their next credit card payment. Unlike previous tutorials, right after building an H2O Driverless AI model, our primary focus will be understanding how to deploy, score, and monitor an H2O Driverless AI model with H2O MLOps.

H2O Driverless AI and H2O MLOps streamline model development and monitoring, empowering you to leverage a complete, end-to-end solution that automates and optimizes the entire machine learning lifecycle. From model creation to deployment and continuous monitoring, these tools ensure models are built efficiently and maintained effectively in production.

Objectives​

  • Workflow: Understand the general flow from building an H2O Driverless AI model to monitoring the model after deployment in H2O MLOps.
  • Share model with H2O MLOps: Learn how to make an H2O Driverless AI model available in H2O MLOps for deployment.
  • Score model: Learn how to score an H2O Driverless AI model deployed in H2O MLOps.
  • Monitor model: Learn how to monitor an an H2O Driverless AI model deployed in H2O MLOps.

Prerequisites​

  • Access to H2O AI Cloud containing:
    • H2O Driverless AI v1.10.7
    • H2O MLOps v0.66.1
  • Familiarity with H2O Driverless AI is essential. Alternatively, completion of the following tutorial is also acceptable: Tutorial 1A: Introduction to H2O Driverless AI.
  • Basic understanding of Python.
Feedback