课程信息

Course Description:

This onsite course offers an in-depth exploration of modern financial risk management, derivative valuation, and the growing role of machine learning in finance. Combining rigorous theoretical foundations with practical applications, the course is designed for students aiming to develop strong quantitative and analytical skills relevant to careers in risk management, quantitative finance, and fintech.

The course begins with Market Risk, introducing key measures such as Value at Risk (VaR), stress testing techniques, and Expected Shortfall, with a focus on their practical implementation and limitations.

The Credit Risk component covers both individual and portfolio perspectives. Students will learn to apply logistic regression for credit scoring and explore structural and portfolio credit risk models, including the Merton Model and CreditMetrics.

In Derivatives Valuation, the course examines pricing and risk management of equity and interest rate derivatives, including structured products and exotic options such as barrier, digital, and basket options.

The final part of the course introduces Machine Learning and Fintech, covering core techniques such as K-Nearest Neighbors (KNN), K-Means clustering, and neural networks, along with their applications in financial markets and an overview of the fintech ecosystem.

Assessment and Grading:

• Group Term Paper (50%)
  Students will work in groups of 3–4 to produce a term paper (15–20 pages) on a topic of their choice related to the course material. The paper should demonstrate analytical depth, proper use of quantitative methods, and clear structure.
• Group Presentation (50%)
  Each group will deliver a 30-minute presentation based on their term paper. All group members are required to present, and individual contributions must be clearly identifiable in both the written paper and the presentation.
• Presentation Schedule
  Presentations will take place during the three days preceding the term paper submission deadline of August 14.