AI-Powered Portfolio Management: Leveraging Multiple Reinforcement Learning Algorithms for Dynamic Factor Investing in HK market

This study explores the use of reinforcement learning to enhance factor investing in portfolio management in Hong Kong stock market. By applying Design Science principles, this research addresses a key challenge in factor-based investing, and demonstrates the transformative potential of AI in investing. The empirical analysis reveals that factor investing using RL algorithms, such as A2C, PPO, TD3, or DDPG, outperforms traditional factor investing in terms of annualized returns, volatility, and risk-adjusted metrics such as the Sharpe ratio. This research introduces a groundbreaking method for factor investing, and highlights the transformative potential of reinforcement learning in asset management industry.