Machine Learning in Financial Mathematics
Zhipeng Huang
Zhipeng Huang
| Events | Date/Time | Room |
|---|---|---|
| Seminar Zhipeng Huang | Monday 16:00 - 18: 00 First meeting: 12, Oct. | C 113 |
The course will be organised via Moodle. If you want to attend the course, please register in Moodle.
This seminar explores machine learning methods, particularly deep learning, and their applications in financial mathematics. Topics may include derivative pricing, hedging, portfolio optimization, model calibration, and applications in energy finance. The seminar begins with several introductory sessions on fundamental machine learning concepts, including neural networks and their training methods. Participants then choose a research paper from a provided reading list, study its mathematical ideas, and implement the proposed method in Python. At the end of the seminar, they give a presentation and submit a written report explaining the approach, their numerical results, and the method’s strengths and limitations.
The focus is on connecting mathematical ideas with practical implementation and gaining experience with modern machine learning methods in financial mathematics through the study of selected research papers.
Relevant materials can be found on the seminar’s Moodle page.
Target Participants: Master students in Financial and Insurance Mathematics.
Pre-requisites: Knowledge of probability theory, statistics, and differential equations, as well as basic Python programming skills.
Applicable credits: 3 ECTS. Students may apply the credits from this course to the