Foundations of Retail AI

This unit introduces core concepts of artificial intelligence as applied to retail, covering historical context, computational foundations, basic modeling techniques, data quality, and decision cycles that shape retail operations. It establishes foundational skills in supervised learning, scoring, and system-level thinking to prepare students for applied model development, deployment, and optimization in subsequent units.

Learning Objectives

• Analyze the historical and industry context of AI in retail by comparing pre- and post-2000 advertising and evaluating the practical impact of innovations (e.g., Amazon Go) on cashier roles and store operations using case-study evidence.
• Demonstrate understanding of computational foundations by comparing CPUs and GPUs and explaining how hardware choices affect model training, inference, and retail system design for given workloads.
• Apply supervised learning and linear regression concepts to build, evaluate, and score simple predictive models for common retail problems (e.g., demand forecasting, customer scoring) using provided datasets and performance metrics.
• Evaluate data quality, decision-making cycles (e.g., OODA loop), simulation approaches, and optimization challenges to identify core inefficiencies in retail workflows and recommend data-driven mitigation strategies.