This unit introduces core AI methodologies and practical workflows used to solve retail problems, including supervised, deep, and reinforcement learning, plus computer vision. Students learn to design and run proofs of concept, evaluate AI-driven merchandising and fulfillment strategies, and plan execution with specialist roles and bake-off structures.
Learning Objectives
- Analyze the strengths, limitations, and retail use cases of supervised learning, deep learning, computer vision, and reinforcement learning to select appropriate approaches for store-level problems
- Apply a structured proof-of-concept (POC) bake-off process to compare AI solutions, including dataset exploration, evaluation metrics, and success criteria for pilot stores
- Demonstrate how to map AI capabilities to merchandising and fulfillment scenarios (e.g., inventory placement, planograms, dark stores, and autonomous delivery) and justify solution choices with data-driven reasoning
- Evaluate team roles, resource needs, and execution steps required to move from POC to production, including responsibilities of AI specialists and operational integration tasks
Curriculum
- 1 Section
- 12 Lessons
- 30 hours
Expand all sectionsCollapse all sections
- Unit 3 — Applied AI Methods for Retail12
- 1.1Supervised Learning Approach to Solving Retail20 mins
- 1.2Think One Store at a Time20 mins
- 1.3Explore20 mins
- 1.4AI Specialists20 mins
- 1.5How to Structure the POC Bake‐off20 mins
- 1.6Computer Vision Revolutionized by AI in 201220 mins
- 1.7Myth 3: We Won’t Need Grocery Stores Anymore; Online Shopping, Dark Stores, and Autonomous Delivery Will Hit 100% Market Share20 mins
- 1.8Deep Learning20 mins
- 1.9Reinforcement Learning20 mins
- 1.10Reinforcement Learning Approach to Solving Retail20 mins
- 1.11How to Apply AI to Merchandising20 mins
- 1.12Execute20 mins
Instructor
Leave a Reply