Smart communities are deploying data-driven systems to address critical housing affordability challenges. This course introduces students to the mathematical modeling and optimization techniques used to design, evaluate, and improve housing subsidy programs. Students will learn to formulate housing affordability as an optimization problem by maximizing households served while targeting vulnerable populations and achieving geographic equity under real-world financial and market constraints. Students will work with real housing datasets translating technical optimization results into actionable insights for housing agencies and policymakers.

Prerequisite(s): N/A

Credits: 3

The rapid proliferation of data centers to service AI models is driving unprecedented growth in energy demand. This course introduces practical machine learning applications for smart energy analytics using real-world device-level data. Students will learn to transform raw energy time series into actionable intelligence through three core problem domains: forecasting household electricity consumption, detecting building occupancy patterns, and segmenting customer energy behaviors for targeted interventions.

Prerequisite(s): APMA 3110 or APMA 3120

Credits: 3