Applied AI for Retail Operations

This unit deepens technical and managerial understanding of AI approaches—supervised learning, deep learning, computer vision, and reinforcement learning—and their specific applications to store-level retail problems and merchandising. Students will learn to design and execute proof-of-concept (POC) bake-offs, define specialist roles and team workflows, and prepare operational rollout plans that bridge AI capability and retail business objectives.

Learning Objectives

• Analyze and compare supervised learning, deep learning, computer vision, and reinforcement learning approaches for common retail problems by producing a written matrix that lists use cases, data needs, strengths, limitations, and expected business impact
• Apply computer vision and deep learning techniques to a defined store-level use case by developing a prototype pipeline or detailed design that specifies inputs, preprocessing steps, model type, evaluation metrics, and expected performance thresholds
• Demonstrate the ability to design and manage a POC bake-off by creating a rubric, baseline models, evaluation criteria, timeline, and resource plan, then use that rubric to score at least two candidate solutions
• Evaluate merchandising and operational strategies using reinforcement learning concepts by formulating a simulated policy or experiment, measuring outcomes with key retail KPIs (e.g., sales lift, stockouts, shrinkage), and recommending an executable rollout and monitoring plan