Modul

The module examination takes the form of a one-hour written comprehensive examination on the two courses "Dynamic Capital Market Theory" and "Essentials for Dynamic Financial Machine Learning".

Dynamic Capital Market Theory:

Professional competence:

• Understanding of the principles of Dynamic Asset Pricing Theory
• Mastery of concepts such as stochastic calculus and dynamic modeling in discrete and continuous time
• Application of dynamic programming theory to portfolio and investment decisions
• Knowledge of pricing bonds, stocks, futures and options markets.

Interdisciplinary skills:

• Develop analytical skills for working on and solving complex problems in finance
• Ability to apply theoretical models to real financial market scenarios.

Essentials for Dynamic Financial Machine Learning:

Professional Competence:

• Competencies in Multivariate Time Series Modeling and Dynamic Volatility Modeling.
• Skills in dealing with big financial data.
• Knowledge in the estimation of risk premia and the application of Kalman Filtering.

Interdisciplinary skills:

• Analytical skills in applying machine learning algorithms to dynamic financial market data.
• Development of problem-solving skills through the practical application of Python in financial data analysis.

Dynamic Capital Market Theory:

The course "Dynamic Capital Market Theory" offers an introduction to the modeling of dynamic capital markets.  Portfolio holdings and asset prices move dynamically across time and states. This course teaches basic financial economic thinking to help understand why this is the case and how to optimally act in such environments.
Next to the asset pricing focus, the second focus of the course is on optimal portfolio choice (robo advisory). For that, this course develops the theory of dynamic programming in discrete and continuous time and applies it to solve portfolio choice and corporate investment decisions. These concepts are key for financial engineering and the machine learning branch of Reinforcement Learning.

Students obtain proficiency in the following topics:

• Dynamic Valuation and Optimal Dynamic Asset Allocation
• Dynamic modeling in discrete time and continuous time
• Stochastic Calculus
• Markov Decision Processes and Dynamic Programming in discrete time and continuous time
• Pricing of bonds, equity, futures and options

Lectures (2 SWS) develop all concepts on the whiteboard, while exercises are solved during weekly tutorials (2 SWS).

Essentials for Dynamic Financial Machine Learning:

The course "Essentials for Dynamic Financial Machine Learning" teaches students to work with financial data, algorithms and statistical concepts.
Students are exposed to algorithms to learn key quantities of dynamic capital markets, such as time-varying risk premia, time-varying volatility and unobserved realizations of random states. The course covers the following concepts:

• Multivariate time series modeling
• Dynamic volatility modeling
• Handling big financial data
• Estimating risk premia
• Kalman Filtering

Weekly lectures (2 SWS) develop all algorithmic material on the whiteboard. Weekly tutorials (2 SWS) solve and discuss Python solutions to selected problems.

Recommendation: Knowledge in the fields of Advanced Statistics, Deep Learning, Financial Economics, Differential Equations, Optimization.

Total workload for 9 credit points: approx. 270 hours. The exact distribution is based on the credit points of the courses in the module:

• Dynamic Capital Market Theory: 4.5 CP
• Essentials for Dynamic Financial Machine Learning: 4.5 CP

The module consists of two weekly lectures and respective tutorials:

1. Dynamic Capital Market Theory and
2. Essentials for Dynamic Financial Machine Learning.