A5057656141- Financial Markets and Investment Strategies
- Energy Load and Power Forecasting
- Recommender Systems and Techniques
- Topic Modeling
- Stock Market Forecasting Methods
- Robotics and Sensor-Based Localization
- Power Systems and Technologies
- Advanced Bandit Algorithms Research
- Supply Chain and Inventory Management
- Forecasting Techniques and Applications
- Neural Networks and Applications
- Video Surveillance and Tracking Methods
- Simulation and Modeling Applications
- Information Systems and Technology Applications
- Auction Theory and Applications
- Consumer Market Behavior and Pricing
- Advanced Text Analysis Techniques
- Privacy-Preserving Technologies in Data
- Multi-Agent Systems and Negotiation
- Big Data and Business Intelligence
- Education and Learning Interventions
- Advanced Data Compression Techniques
- Robotic Path Planning Algorithms
Xi’an Jiaotong-Liverpool University
2023-2024
University of Liverpool
2023-2024
South China University of Technology
2017
Given the plethora of available solutions, choosing an appropriate Deep Reinforcement Learning (DRL) model for dynamic pricing poses a significant challenge practitioners. While many DRL solutions claim superior performance, there lacks standardized framework their evaluation. Addressing this gap, we introduce novel and set metrics to select assess models systematically. To validate utility our framework, critically compared three representative models, emphasizing performance in tasks....
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 evolving preferences behaviours inherent interaction data, posing a significant challenge for accurate prediction personalisation. Addressing this, we propose novel theoretical framework, transformer, designed effectively capture leverage temporal dynamics within data. This approach enhances...
Augmented Language Models (ALMs) empower large language models with the ability to use tools, transforming them into intelligent agents for real-world interactions. However, most existing frameworks ALMs, varying degrees, are deficient in following critical features: flexible customization, collaborative democratization, and holistic evaluation. We present gentopia, an ALM framework enabling customization of through simple configurations, seamlessly integrating various models, task formats,...
In the evolving landscape of portfolio management (PM), fusion advanced machine learning techniques with traditional financial methodologies has opened new avenues for innovation. Our study introduces a cutting-edge model combining deep reinforcement (DRL) non-stationary transformer architecture. This is designed to decode complex patterns in time-series data, enhancing strategies deeper insights and robustness. It effectively tackles challenges data heterogeneity market uncertainty, key...
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 evolving preferences behaviours inherent interaction data, posing a significant challenge for accurate prediction personalisation. Addressing this, we propose novel theoretical framework, Non-stationary Transformer, designed capture leverage temporal dynamics within data effectively. This approach...
One of the important factors profitability is volume transactions. An accurate prediction future transaction becomes a pivotal factor in shaping corporate operations and decision-making processes. E-commerce has presented manufacturers with convenient sales channels to, which can increase dramatically. In this study, we introduce solution that leverages XGBoost model to tackle challenge predict-ing for consumer electronics products on Amazon platform. Initial-ly, our attempts solely predict...
In the evolving landscape of Portfolio Management (PM), fusion 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) 3 Non-stationary Transformer architecture. This is specifically designed to decode complex 4 patterns in time series data, enhancing portfolio management strategies deeper insights 5 and robustness. It effectively tackles...
This paper proposes an optimized method of collision detection in web virtual reality (VR) environment. The proposed solution consists two layers. Experimental results demonstrate the effectivity and its significant improvement efficiency (measured by average frame number per second) with proper accuracy guaranteed.