Drawing on the rich body of literature in Machine Learning (ML) and Large Language Models (LLMs) developed by Computer Science scholars and Finance professionals (e.g., Vaswani et al., 2017; Kelly et al., 2025 NBER), this course explores the transformative applications of AI-driven technologies in the field of finance. Students will gain a solid foundation in key concepts such as machine learning (including unsupervised learning and supervised learning), natural language processing (NLP), and language models, while examining their practical applications across major financial domains. The curriculum bridges theoretical frameworks with hands-on, task-specific implementations in areas including financial disclosure analysis, ML-based time‑series forecasting, etc. The course also covers ethical considerations, regulatory challenges, and the evolving role of business professionals in an increasingly AI-driven world.

Financial analytics is the use of business analytics methods and tools on financial data to solve problems such as investment and risk analysis, portfolio optimization, valuation, default modeling, and so on. This course introduces a contemporary tool (R or Python) and its use in solving these problems. In this hands-on course, students also learn about the field of fintech.

Special topics seminars offer an in-depth examination of current events, issues and problems unique to finance. Specific topics will vary depending upon student and faculty interests and on recent events in the business world. Seminar topics for a specific semester will be announced prior to the course offering. These seminars may be repeated for credit since topics will normally vary from semester to semester. (instructor-determined)

This course provides a survey of financial analytics applications in contexts such as investment analysis, portfolio construction, risk management, and security valuation. Students are introduced to financial models used in these applications and their implementation using popular languages such as R, Matlab, and Python, and packages such as Quantlib. A variety of data sources are used: financial websites such as www.finance.yahoo.com, government sites such as www.sec.gov, finance research databases such as WRDS, and especially Bloomberg terminals. Students will complete projects using real-world data and make effective use of visualization methods in reporting results. There are no pre or co-requisites; however, instructor permission is required – student aptitude for quantitative work will be assessed; waived for students enrolled in quantitative programs such as the MS-Computational Finance which have pre-requisites in the areas of calculus, linear algebra, and programming.