This study aims to optimize capital allocation across several stocks to maximize expected returns while minimizing risk. By enhancing the portfolio selection model with new constraints and a unique objective function, the research introduces improved strategies for achieving these financial objectives.
This research uses a Sharpe ratio index for portfolio comparison and introduces a self-adjusting algorithm based on a genetic algorithm, eliminating the need for manual parameter adjustments. The effectiveness of this methodology is assessed across various test cases, demonstrating its applicability and robustness in dynamic financial market conditions.
This study confirms that the proposed algorithm consistently outperforms traditional models, offering robustness across different market conditions. Results indicate significant risk management and return maximization, and improvements have been attributed to the innovative model enhancements and algorithmic adjustments.
Incorporating a new objective function prioritizing the price-to-earnings ratio and introducing technical analysis constraints significantly enhance portfolio profitability and risk management. Another key contribution is the self-adjusting algorithm streamlining parameter adjustments, fostering more dynamic and accurate responses to market changes. These contributions have not been observed in prior research, providing a novel approach to the portfolio selection problem.
