The purpose of the article. The application of multi-objective optimization in portfolio management has gained significant attention in asset management. This study aims to uncover the potential advantages of dynamic portfolio optimization using a multi-objective genetic algorithm to address the challenges of ever-changing market conditions. Methodology. By incorporating multi-objective optimization, this paper comprehensively examines three key portfolio objectives: minimizing two risk types and maximizing returns. The approach involves constructing portfolios, initializing the population using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II), and employing crossover and mutation steps to achieve Pareto optimality. Additionally, this study compares the performance of two risk minimization strategies through traditional portfolio backtesting. Results of the research. The results indicate that the multi-objective risk genetic algorithm not only effectively explores the portfolio space but also handles conflicting optimization objectives, thereby enhancing the comprehensiveness and flexibility of investment decisions. However, its performance depended on the chosen risk measurement methods, and the backtesting returns were unstable.
Read full abstract