Seminar: Investment Case Studies (3 ECTS)
Students team up in a group to solve an investment related real-world case study. This seminar is ideally suited for students who want to deepen and apply their knowledge from classes like investments and statisics. Some case studies provide students with an opportunity to implement statistical investment concepts using financial software; while other case studies are more qualitative.
Bachelor Thesis Seminar (0 ECTS)
Students who write a bachelor thesis at the Chair present their findings and state open questions on a regular basis. All Bachelor thesis writers are invited to participate to learn from the research of their fellow students and to benefit from the professor's and PhD student's feedback.
Lecture: Computational Risk and Asset Management (4.5 ECTS, 2/1); (Executive Summary as PDF)
From all lectures that we offer to the KIT students, this is in the professor's point of view the most important one. It teaches students how to estimate expected returns, risk and risk densities of different investment instruments. We further estimate linear and non-linear financial models using methods such as least squares, maximum likelihood and the Kalman Filter algorithm. This course is especially work intensive as we further steepen student's learning curve by providing ample opportunity to implement all of these methods using Python. An introduction to programming with Python is part of this course.
If you want to learn how to manage your own money or the money of others, or if you want to learn how financial econometrics and asset management mingle, this course will be for you.
Lecture: Bayesian Risk Analytics and Machine Learning (4.5 ECTS, 2/1)
This course is the 'bigger brother' of the lecture "Computational Risk and Asset Management". While the "younger brother" (see above) focuses on teaches students how to use classical statistical methods (ARMA-GARCH, MLE, Kalman Filter) to predict risk densities, risk premia, stochastic volatility and Markowitz optimal portfolios, this course introduces students to estimate the same quantities within the Bayesian framework. Bayesian estimation techniques have the advantage that they extend easily to highly nonlinear and non-Gaussian return dynamics. Hence, any type of realistic dynamic will be most likely estimated using Bayesian methods. Last but not least, the Bayesian way of thinking is the basis for several important machine learning algorithms. Bottom line: a very useful tool for your toolbox, applied to several real-world risk management problems.
Seminar: Applied Risk and Asset Management (3 ECTS)
Students will work on a quantitative problem related to risk and asset management. This seminar is ideally suited for students who want to deepen and apply their statistics / programming skills and knowledge about financial markets. Industry-relevant problems will be solved with financial data and modern statistical tools in close collaboration with a supervisor. Topics which students solved in the past include the option-based pricing of dividends during the Euro crisis, the estimation of risk neutral moments with high-frequent data and the application of a particle filter to estimate stochastic volatility. The current topics will be presented during the first meeting. The seminar consists of an introductory meeting, biweekly meetings with the advisor, an intermediate meeting to present the current progress, a final presentation and a written seminar thesis.
Master and PhD Thesis Seminar (0 ECTS)
Students who write a master or PhD thesis at the Chair present their findings and open questions on a weekly basis. All thesis writers are invited to participate to learn from the research of their fellow students and to benefit from the professor's and PhD student's feedback.