End-to-end Data Science on CloudPak for Data

Login to enroll
  • Course Number
  • Classes Start
    Any time, Self-paced
  • Audience
  • Course Level
  • Language
  • Badge Earned
  • Tell Your Friends


This course takes you through an end-to-end AI example where you will start with the data and end up with a deployed AI model which is constantly monitored for quality. Through this journey, you'll also gain hands-on experience with IBM Cloud Pak for Data and explore how to implement different aspects of the AI pipeline within it. At the end of this course, you will have gained and intermediate level of proficiency with IBM Cloud Pak for Data and will have exercised the four layers of AI Ladder: Collect, Organize, Analyze, Infuse


  • After completing this course, you will be able to:
  • Understand the basics of Cloud Pak for Data
  • Understand the AI Ladder: Collect
  • Make data simple and accessible Create connections to remote data sources Access you remote data using Data Virtualization Perform data wrangling using Data Refinery Organize
  • Create business-ready analytics foundation Organize and catalog your data with Watson Knowledge Catalog Analyze
  • Build and scale AI with trust & explainability Build AI Models using Jupyter Notebooks Automatically build AI Models using AutoAI Infuse
  • Operationalize AI throughout the business Deploy AI models as APIs Deploy AI models and perform Batch jobs Use your deployed models within you applications Monitor and explain your models using OpenScale


Module 1:

  • Understanding the platform
  • Understanding the AI ladder and Cloud Pak for Data
  • Getting a preview of Cloud Pak for Data

Module 2:

  • Setting up your project
  • Creating your first project space
  • Creating your first Deployment Space

Module 3:

  • Collect: making data simple and accessible
  • Accessing remote data with Data Virtualization
  • Adding data to your project space

Module 4:

  • Organize: creating a trusted analytics foundation
  • Organizing, accessing, and finding the right data using Watson Knowledge Catalog

Module 5:

  • Analyze: creating AI models
  • Training AI Models in Jupyter Notebooks
  • Automatic AI Model training using AutoAI

Module 6:

  • Infuse: Model deployment
  • Deploying your model as a web API
  • Accessing and using your deployed models within applications

Module 7:

  • Infuse: Model explainability and debiasing
  • Monitoring your deployed models for bias, drift, quality, and explainability
  • Create debiased endpoints from a biased model - Application Modernization


  • This course is free.
  • It is self-paced.
  • It can be taken at any time.
  • It can be audited as many times as you wish.
  • There are TWO chance to pass the course, but multiple attempts per question (see the Grading Scheme section for details)


  • Some familiarity with Python
  • Some familiarity with AI workflow


  • Omid Meh
  • Javier Torres
  • Scott D'Angelo

Other Contributors

Samaya Madhavan