Peter Zhang

Decision Analytics for Business and Policy: This course introduces modeling frameworks and computational tools to address complex, ill-defined, large-scale decision-making problems that arise in policy and business. Through lectures and case studies, it covers advanced methods of decision-making under uncertainty in four major areas: (large-scale) deterministic optimization, stochastic/robust optimization, sequential decision making, and simulation. It will focus on modeling (how to formulate models to address policy or business problems), computation (how to solve large-scale problems), and applications in policy and business (how to integrate viewpoints of different stakeholders, how to select the scope of the model, etc.). Applications are drawn from a variety of real-world settings in transportation, energy, health, supply chain management, etc. Participants are expected to take "active learning" roles in the computational application of the materials presented in class using the python programming language and the Gurobi optimization solver. A term project simulates realistic and challenging issues where new solutions need to be developed, implemented and communicated. The prerequisites are an introductory course in Operations Research, such as Management Science I and II or Decision-Making under Uncertainty, and an intermediate Python course.

Learning Outcomes: The learning objectives of this course fall into the following categories — Methods: learning advanced quantitative modeling and solution algorithms from the fields of Operations Research and Management Science (OR/MS) — Modeling: applying OR/MS methods systematically to model complex decision-making problems faced in practice — Computations: implementing simulation and optimization methods with large-scale datasets using state-of-the-art software — Analysis: evaluating the challenges and trade-offs in quantitative modeling — Communication: communicating technical models and results effectively based on the context and the audience.