Optimalizace portfolia na evropských akciových trzích s využitím Pythonu

Abstract

The aim of this thesis is to analyze and compare four approaches to portfolio optimization using different methods of risk measurement: standard deviation, semivariance, Conditional Value at Risk, and Conditional Drawdown at Risk. The analysis is based on historical data of stocks included in the DAX 30 index and is conducted using the Python programming language. The models are implemented and evaluated based on achieved returns and selected risk metrics. The results show that the models outperform the index itself and highlight differences between the individual approaches in the context of investment strategies. The thesis may serve as a foundation for further development of multifactor, statistical, or other alternative risk models.