Data Science and Machine Learning for Finance

4 units · Graduate courses (200-299)

Lecture, three hours. Preparation: linear algebra, elementary probability and statistics, programming experience. Project-based study that covers topics pertaining to applications of data science and machine learning to the field of statistical finance, which combine both theoretical and practical approaches. Students gain understanding at a high level of the mathematical foundations behind some of the state-of-the-art algorithms for a wide range of unsupervised and supervised learning tasks arising when dealing with financial data, including linear and nonlinear dimensionality reduction, network analysis, clustering, and ranking. Selected literature exposes students to a spectrum of regression techniques—spanning both linear and nonlinear models—used in financial modeling. Focus on handling high-dimensional, noisy data, while assessing their robustness, and balancing predictive power with interpretability. S/U or letter grading.