FIN 6776 · Fall 2026
Big Data and Machine Learning in Finance
Learn financial big data workflows and the machine learning toolkit through lectures, labs, and projects you can add to your portfolio.
- Term
- Fall 2026
Aug 24 – Nov 13, 2026 · 12 weeks - Level
- Graduate · 3 credits
- Meets
- Monday 18:30–22:15 · BSN 2305
- Sections
- 901 (CRN 91184) · 340 / 345, MS FinTech (CRN 91185 / 91186)
- Office hours
- By appointment · BSN 3127
Overview
A rigorous, hands-on look at financial technology through big data analytics and machine learning. Each session combines lecture and lab, and most of the work happens in projects rather than problem sets. My hope is that you’ll leave with two or three portfolio-ready finance projects you’re proud of. Along the way, we’ll use AI-powered programming tools as a natural part of the workflow: to speed up development, debug code, and implement financial models.
The course is taught primarily in R. If you already have substantial R experience, especially if you’ve taken the undergraduate big data and machine learning course, you’ll join the Python track and do labs, homework, and projects in Python, so you’re still learning something new. If you’re coming in with Python experience, you’ll work in R. In-class quizzes are in R for everyone.
Per university policy, the syllabus and course materials (handouts, slides, code, and course repositories) aren’t posted publicly. Enrolled students receive the course page by invitation through Canvas. If you’d like a syllabus or have any questions about a course, I’m happy to help. Just email me at gson@usf.edu.
Schedule
| Wk | Topic | Materials |
|---|---|---|
| 1 | Course introduction · FinTech and AI/ML · financial data manipulationModules 0 and 1 | — |
| 2 | Portfolio construction and CAPM estimation · financial data visualization · technical documentation with Quarto · pivoting and tidying financial dataModule 1 · asynchronous | — |
| 3 | Big data and financial databases · cloud and high-performance computing · overview of joins, SQL, and efficient workflowsModule 2 · Quiz 1 (in person) · big data project released | — |
| 4 | Code demonstrations for week 3: SQL and joins, including rolling and overlap joins · remote database practiceModule 2 · asynchronous | — |
| 5 | Efficient programming, code benchmarking, and parallel processing · special lecture on AI codingModule 2 and special topic · asynchronous | — |
| 6 | DueMachine learning in finance · supervised and unsupervised learning · ML from scratch with linear regressionModule 3 · big data project soft deadline · Quiz 2 (in person) | — |
| 7 | Unsupervised learning with k-means clustering · credit risk analysis · stock classificationModule 3 | — |
| 8 | DuePCA and hierarchical clustering · linear models and regularization · Fama–French models · house pricing and credit decision modelsModules 3 and 4 · ML project 1 due · Quiz 3 | — |
| 9 | Supervised learning with logistic classification · decision treesModule 4 | — |
| 10 | DueEnsemble methods · random forests and gradient boostingModule 5 · ML project 2 due | — |
| 11 | Machine learning presentations · course review · artificial neural networks, time permitting | — |
| 12 | ExamFinal examML project 3 due | — |
Grading
| Component | Weight |
|---|---|
| Participation and ML presentation | 15% |
| In-class quizzes | 25% |
| Homework assignments | 10% |
| Big data / machine learning projects | 25% |
| Final exam | 25% |
Resources
- R for Data Science, 2nd editionWickham & Grolemund; free online
- Machine Learning in Business, 3rd editionJohn C. Hull; recommended reference
- Practical Machine Learning with H2ODarren Cook; recommended reference
- Python Polars: The Definitive GuideRecommended reference