

Customer Churn Lab for Cloud Pak for Data

Step 1: Getting Started

• 1. Dataset and sample code
• 2. Dataset and Initial Setups for IBM Cloud Pak for Data

Step 2: Data Ingestion, Organization and Governance for Customer Churn

• 1. Data Discovery
• 2. Data Governance - Creating Business Glossary, Policies and Rules
• 3. Data Ingestion from Flat Files to a Project
• 4. Data Organization using PySpark in Notebook

Step 3: Customer Churn Model Development and Deployment

• 1. Model Development using PySpark in Jupyter Notebook
• 2. Model Development using Auto AI
• 3. Model Development using SPSS
• 4. Model Deployment in MMD
• 5. Model Deployment in WML using API
• 6. Python Function accessing Model in MMD Deployed in WML using API

Step 4: Weekly Churn Scoring using the deployed Model

• 1. Churn Scoring using Model Deployed in WML
• 2. Churn Scoring using MMD Model function Deployed in WML

Step 5: Monitoring Churn Model using Open Scale

• 1. Configuring Datamart and Deployment Infrastructure
• 2. Adding Deployment and Configuring Model
• 3. View Monitoring Results in Dashboard
• 4. Access Monitoring Results using API