Regime-Adaptive Continual Learning for Portfolio Management

2026-05-28

AI Summary

Traditional portfolio management approaches struggle to cope with the non-stationarity and regime shifts inherent in financial markets, leading to limited adaptability and suboptimal returns. This work proposes ReCAP, a novel framework that uniquely integrates regime awareness with continual learning. ReCAP employs an adaptive regime detection module to identify prevailing market states and maintains a dynamic library of variable-length policy vectors, which are selectively fused by a regime-gated module to rapidly adjust to new market regimes. Concurrently, it implements selective parameter updating to preserve historical knowledge while enabling efficient online learning. Extensive experiments on five real-world datasets demonstrate that ReCAP significantly outperforms state-of-the-art baselines, achieving higher cumulative returns over the long term and effectively responding to evolving market conditions.

Abstract

Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective. Existing remedies, such as rolling-window retraining and naive online fine-tuning, are hindered by high computational costs and insufficient knowledge utilization, respectively, resulting in low returns and limited adaptability. Continual learning (CL) offers a promising paradigm by enabling trading agents to accumulate and transfer knowledge across sequential tasks. In this paper, we propose \textbf{Re}gime-aware \textbf{C}ontinual \textbf{A}daptive \textbf{P}ortfolio management (\textbf{ReCAP}), a novel framework that integrates CL into PM to address the challenges of dynamic financial environments. ReCAP employs an adaptive regime detection module to segment historical market data into variable-length regimes, enabling regime-specific learning of policy vectors and the construction of a policy library. During continual trading, a regime-gate module adaptively combines policy vectors from the library based on the current market state, facilitating rapid adaptation to newly detected regimes. Only the regime-gate and the current regime's policy vector are continually updated to preserve useful knowledge effectively. Extensive experiments on five real-world datasets demonstrate that ReCAP consistently outperforms popular baselines, achieving superior returns in long-term investment horizons and rapid adaptation to regime shifts.

Problem

• Portfolio Management
• Regime Shifts
• Non-stationary Markets
• Continual Learning
• Adaptability

Innovation

• Continual Learning
• Regime Detection
• Adaptive Portfolio Management
• Policy Library
• Non-stationary Financial Markets