Applied AI Modeling and Product Fit

This unit introduces practical supervised modeling concepts through a k-Nearest Neighbors example, an end-to-end churn prediction case study, and day-to-day AI/ML product activities. Students will learn to map product problems to AI capabilities, evaluate model performance, and apply an AI-experiences PM toolkit to find and scope opportunities across the user journey, building on foundational coding concepts and preparing for implementation and deployment in subsequent units.

Learning Objectives

• Analyze how k-Nearest Neighbors and related supervised learning methods learn from data, including their assumptions, limitations, and suitable problem contexts
• Apply capability-matching techniques to map product and business problems to appropriate AI/ML approaches and outline end-to-end solution components using a subscription churn example
• Evaluate model performance using relevant metrics, validation techniques, and trade-off analyses to inform product decisions and prioritize improvements
• Demonstrate identification of AI opportunities across a user journey and create an AI-Experiences PM Toolkit checklist detailing required skills, data, and workflow steps to advance an idea toward implementation