• Fundamentals of financial markets
o Wealth maximization
o Portfolio theory
o Factor models
• Distributional modeling of asset returns
o Stylized facts of asset returns
o Appropriate distributions for asset returns
o Maximum-Likelihood estimation of asset returns
o Distributional “free” estimation of expected returns, covariances and tail risks
• Univariate time series modeling of asset returns
o AR models
o GARCH models
o Forecasting of returns and realized volatility
• Neural Networks
o Forward neural networks (Forward pass, backpropagation)
o Recurrent neural networks
o Overfitting and cross validation
o Forecasting volatility with recurrent neural networks
• Possibilities and limitations of deep learning in the domain of financial markets

Students who participated in the course:
- Understand fundamental concepts of wealth optimization
- Know common characteristics of financial data and take them into account when analyzing it, i.e., moderate autocorrelation, volatility clustering, heavy tails
- Gain a fundamental understanding of statistical modeling
- Learn general principles of machine learning such as overfitting and cross validation
- Understand the possibilities and challenges of modern deep learning models