Portfolio optimization plays a crucial role in finance, aiming to maximize returns and minimize risk for a given set of assets. Evolutionary algorithms, given their heuristic nature, have become popular tools to tackle this optimization problem. In this study, we conduct a comprehensive comparative analysis of two such algorithms: Rao-1 and Rao-2, focusing on their effectiveness in determining optimal asset allocations. Using historical stock data from prominent companies, both algorithms were evaluated based on solution quality, convergence speed, and reliability. Our results reveal distinct strengths and weaknesses of each approach, providing valuable insights for financial analysts and algorithm developers. Furthermore, this research paves the way for future studies that can integrate the strengths of both algorithms or apply them to alternative financial scenarios.