In the evolving landscape of portfolio management (PM), the fusion of advanced machine learning techniques with traditional financial methodologies has opened new avenues for innovation. Our study introduces a cutting-edge model combining deep reinforcement learning (DRL) with a non-stationary transformer architecture. This model is designed to decode complex patterns in financial time-series data, enhancing portfolio management strategies with deeper insights and robustness. It effectively tackles the challenges of data heterogeneity and market uncertainty, key obstacles in PM. Our approach integrates key macroeconomic indicators and targeted news sentiment analysis into its framework, capturing a comprehensive picture of market dynamics. This amalgamation of varied data types addresses the multifaceted nature of financial markets, enhancing the model’s ability to navigate the complexities of asset management. Rigorous testing demonstrates the model’s efficacy, highlighting the benefits of blending diverse data sources and sophisticated algorithmic approaches in mastering the nuances of PM.

Recommendation systems are crucial in navigating the vast digital market. However, user data’s dynamic and non-stationary nature often hinders their efficacy. Traditional models struggle to adapt to the evolving preferences and behaviours inherent in user interaction data, posing a significant challenge for accurate prediction and personalisation. Addressing this, we propose a novel theoretical framework, the non-stationary transformer, designed to effectively capture and leverage the temporal dynamics within data. This approach enhances the traditional transformer architecture by introducing mechanisms accounting for non-stationary elements, offering a robust and adaptable solution for multi-tasking recommendation systems. Our experimental analysis, encompassing deep learning (DL) and reinforcement learning (RL) paradigms, demonstrates the framework’s superiority over benchmark models. The empirical results confirm our proposed framework’s efficacy, which provides significant performance enhancements, approximately 8% in LogLoss reduction and up to 2% increase in F1 score with other attention-related models. It also underscores its potential applicability across accumulative reward scenarios with pure reinforcement learning models. These findings advocate adopting non-stationary transformer models to tackle the complexities of today’s recommendation tasks.

In the evolving landscape of Portfolio Management (PM), the fusion of advanced machine 1 learning techniques with traditional financial methodologies has opened new avenues for innovation. 2 Our study introduces a cutting-edge model combining Deep Reinforcement Learning (DRL) with 3 a Non-stationary Transformer architecture. This model is specifically designed to decode complex 4 patterns in financial time series data, enhancing portfolio management strategies with deeper insights 5 and robustness. It effectively tackles the challenges of data heterogeneity and market uncertainty, 6 key obstacles in PM. Our approach integrates key macroeconomic indicators and targeted news 7 sentiment analysis into its framework, capturing a comprehensive picture of market dynamics. This 8 amalgamation of varied data types addresses the multifaceted nature of financial markets, enhancing 9 the model’s ability to navigate through the complexities of asset management. Rigorous testing 10 demonstrates the model’s efficacy, highlighting the benefits of blending diverse data sources and 11 sophisticated algorithmic approaches in mastering the nuances of PM.12

With the rapid expansion of e-commerce platforms, there is an increasing demand for pricing strategies that jointly optimise sales performance and profitability under highly competitive markets. To address this challenge, we propose a unified deep reinforcement learning (DRL) framework built upon ItaNet (Image, Text, and Attributes Fusion Network) for dynamic pricing in Amazon’s marketplace. By integrating multimodal product context into the DRL architecture, the framework enables pricing agents to reason over heterogeneous product characteristics and demand signals, leading to more adaptive pricing decisions. Extensive simulations across multiple DRL algorithms are conducted and compared against a range of strong baseline strategies. The results show that our approach achieves an average cumulative profit margin growth exceeding 16.7% aggregated across products and time steps, while incurring only a modest 0.3%–2% reduction in sales volume. This indicates a net improvement in total gross profit rather than gains driven by aggressive price undercutting. Overall, the findings demonstrate that ItaNet-based DRL policies deliver a more balanced and economically sustainable pricing strategy than traditional sales-driven approaches. The constructed dataset spans over 40 feature dimensions across 27 Amazon product categories, incorporating textual, visual, and numerical signals. Compared with commonly used review-centric datasets, this multimodal dataset better reflects real-world pricing environments and provides a strong foundation for future research on dynamic pricing and multimodal recommender systems.