Development of a program for optimizing a securities portfolio on the Russian stock market

Effective portfolio management is paramount for investors seeking to achieve optimal returns while managing risks in the dynamic environment of the Russian stock market. This thesis addresses to develop a Python program for identifying the optimal portfolio of Russian stocks using two widely known models: Mean-Variance and Mean-Semivariance model. The research is divided into two main parts. In the initial phase, we delve into the modern portfolio theory, identifying key parameters and methodologies for portfolio optimization. This includes an exploration of risk-return trade-offs, performance evaluation metrics, and optimization techniques. Subsequently, the focus shifts to the practical implementation of the theoretical concepts discussed. We outline the process of retrieving real-time data using API and leveraging Python programming to formulate and solve the mathematical model for portfolio optimization. Through empirical analysis and comparative studies, we evaluate the effectiveness of the developed Python program in constructing optimized portfolios tailored to the Russian stock market. In the concluding section, we synthesize the findings, highlight the practical implications of the research, and provide recommendations for investors seeking to leverage technology-driven solutions for portfolio management.