<![CDATA[This study investigates the performance of portfolio optimization algorithms in robo-advisory systems within the digital finance landscape. The research compares three approaches Modern Portfolio Theory (MPT), Post-Modern Portfolio Theory (PMPT), and a heuristic equal-weight model using a simulation-based computational framework with synthetic financial data under controlled marketconditions. Key evaluation metrics include Sharpe ratio, Sortino ratio, and maximum drawdown to assess risk-adjusted performance and downside protection. The results show that optimization-based models outperform the heuristic approach across all metrics. MPT achieves the highest Sharpe ratio (1.25), indicating strong overall risk-adjusted returns, while PMPT provides superior downside risk management with a higher Sortino ratio (1.60) and lower maximum drawdown (0.14). The heuristic model demonstrates the weakest performance due to its lack of adaptive allocation. These findings highlight the trade-offs between return optimization and risk sensitivity across different algorithms. Despite their effectiveness, the models are limited by reliance on historical data and simplified assumptions in the simulation environment. This study suggests that future robo-advisory systems should integrate artificial intelligence and behavioral finance to enhance adaptability, personalization, and decision transparency in dynamic market conditions.]]>
Copyrights © 2026
