The course introduces students to Markov Decision Processes, numerical dynamic programming, dynamic structural models, and offline+online reinforcement learning and control. In the first module, we will focus on how to model intertemporal trade-offs made by consumers and firms using Dynamic Discrete Choice models under the assumption that consumers/firms made decisions using an optimal policy. In the second module on Reinforcement Learning, we will focus on how agents can learn good policies in a dynamic environment.
In the process, the course will introduce students to advanced Markov Decision Processes, Estimation methods for Dynamic Discrete Choice Models, Identification, Problem formulation, Policy Evaluation and Learning, and Value Function Approximation methods. The course will also touch upon the recent developments in this space.
This course introduces the fundamentals of Large Language Models (LLMs) with a focus on business applications. Students will explore key LLM techniques — prompting, embeddings, fine-tuning, and alignment methods — and apply them to real-world tasks such as market research surveys, sentiment analysis, content creation, and exploring emerging GenAI tools. Through lectures, hands-on exercises, and a final group project, students will develop practical skills to leverage LLMs for data-driven decision-making in business contexts.
Marketing is evolving from an art to a science. Many firms have extensive customer databases, but few firms have the expertise to intelligently act on such information. In this class, you will learn how to be a data-savvy manager. You will learn how firms can use data analytics to optimize their marketing mix decisions or the 4 Ps – Product Design, Pricing, Promotion and Advertising, and Placement. In the process, you will also gain expertise in methodologies for developing statistical models for descriptive, causal, and predictive models for large-scale data. The class will conclude with a discussion of the implications and costs of automating marketing decisions, new developments in analytics, and privacy concerns in storing and handling data with sensitive consumer information.