Developing An Attention-Based Ensemble Learning Framework for Financial Portfolio Optimisation

arXiv:2404.08935v1 Announce Type: cross
Abstract: In recent years, deep or reinforcement learning approaches have been applied to optimise investment portfolios through learning the spatial and temporal information under the dynamic financial market. Yet in most cases, the existing approaches may produce biased trading signals based on the conventional price data due to a lot of market noises, which possibly fails to balance the investment returns and risks. Accordingly, a multi-agent and self-adaptive portfolio optimisation framework integrated with attention mechanisms and …

abstract arxiv attention cases cs.ce cs.lg data dynamic ensemble financial financial market framework information investment market optimisation portfolio price q-fin.pm reinforcement reinforcement learning spatial temporal through trading trading signals type