This study proposes a Quantum-Inspired Optimization (QIO)-based portfolio optimization model to address financial market dynamics characterized by high volatility and global uncertainty. This model utilizes a Q-bit probabilistic representation and an amplitude rotation mechanism to explore the solution space more adaptively than conventional approaches such as Mean-Variance Markowitz, heuristic Genetic Algorithms, and Particle Swarm Optimization. Daily stock price data from the LQ45 index are used as the test object, with additional external indicators, such as the global volatility index (VIX) and benchmark interest rates, to integrate systemic risk into the optimization process. Simulation results show that QIO produces higher portfolio returns, lower risk, a better Sharpe Ratio, and smaller maximum drawdown compared to benchmark models. These findings demonstrate that the quantum-inspired approach has significant potential for application in modern portfolio management, particularly in volatile market conditions, while also contributing to the development of quantitative methods in finance.
Copyrights © 2024