In today’s complex financial markets, the need for advanced computational methods in portfolio optimization is critical for keeping economic stability and enhancing social well-being. Traditional approaches, such as mean-variance optimization in Modern Portfolio Theory (MPT), often struggle to handle the non-linearities and volatility presented by modern assets. With the development of technology, artificial intelligence is now capable of contributing to sophisticated financial tools, enabling more individuals and institutions to make informed investment decisions. The evolutionary algorithm is significant in this domain, as it offers a robust approach to navigating the complexities of financial systems that are dynamic and often unpredictable. We implemented the evolutionary algorithm and validated it against real-world stock market data. The algorithm performs better by achieving a higher Sharpe Ratio than the traditional mean-variance method, indicating more effective risk-adjusted returns. By integrating advanced computer science techniques with financial optimization, this work contributes to the development of resilient and inclusive economic systems. However, the high degree of randomness in evolutionary algorithms underscores the need for further refinement to enhance the stability and consistency of outcomes.