2025/03/06 by Fengchen Gu, Gu, Fengchen, Zhengyong Jiang +10 · 1 voice · 1 citation
Computer Science · Decision Sciences · #Adaptability #Advanced Bandit Algorithms Research #Investment management #Investment strategy #Market portfolio #Portfolio #Project portfolio management #Reinforcement learning #Risk and Portfolio Optimization #Risk management #Sharpe ratio #Stock Market Forecasting Methods #cs.AI #cs.LG
paper · pdf · doi:10.1177/1088467x261416593
published in Intelligent Data Analysis (IOS Press)
arxiv published 2025/03/06 · arxiv updated 2025/03/06 · openalex created_date 2025/10/10 · openalex publication_date 2026/02/09 · openalex updated_date 2026/08/05
Portfolio management remains a crucial challenge in finance, with traditional methods often falling short in complex and volatile market environments. While deep reinforcement approaches have shown promise, they still face limitations in dynamic risk management, exploitation of temporal markets, and incorporation of complex trading strategies such as short-selling. These limitations can lead to suboptimal portfolio performance, increased vulnerability to market volatility, and missed opportunities in capturing potential returns from diverse market conditions. This paper introduces a Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling (MTS), offering a robust and adaptive strategy for sustainable investment performance. This framework utilizes a novel encoder-attention mechanism to address the limitations by incorporating temporal market characteristics, a parallel strategy for automated short-selling based on market trends, and risk management through innovative Incremental Conditional Value at Risk, enhancing adaptability and performance. Experimental validation on five diverse datasets from 2019 to 2023 demonstrates MTS’s superiority over traditional algorithms and advanced machine learning techniques. MTS consistently achieves higher cumulative returns, Sharpe, Omega, and Sortino ratios, underscoring its effectiveness in balancing risk and return while adapting to market dynamics. MTS demonstrates an average relative increase of 30.67 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mi mathvariant="normal">%</mml:mi> </mml:math> in cumulative returns and 29.33 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mi mathvariant="normal">%</mml:mi> </mml:math> in Sharpe ratio compared to the next best-performing strategies across various datasets.