This is a PhD-level course on using machine learning methods to model and solve problems relevant to management and marketing science. In particular, those problems involving machines that autonomously make decisions on the behalf of the modeler, as in online settings. The course is based mainly on reinforcement learning (when we model states and transitions) and multi-armed bandits (when states are not modeled). Students design, solve, and implement learning methods for sequential decision-making under uncertainty. Sequential decision problems involve a trade-off between exploitation (acting on the information already collected) and exploration (gathering more information). These problems arise in many important domains, including online advertising, clinical trials, website optimization, marketing campaign and revenue management.
This is a new MBA course. In advertising, the impact of AI and ML was both deep and wide, offering a multitude of benefits such as personalized targeting, dynamic ad optimization, improved ad relevance, automated ad creation, enhanced ad placement, predictive analytics, fraud detection, and optimized budget allocation. In this course, I explore these opportunities and challenges, examining the transformative effects of AI on advertising. The course is structured around four main themes: digital and technological trends, applications of machine learning in advertising, the impact of AI on measurement, ad creation, targeting, and placement, and the ethical issues surrounding targeting and algorithmic biases in ML models.
This is a hands-on undergraduate course on text analytics and online experiments. Bachelor students learn how to design, run, and analyze their own multi-arm bandit experiments