Research
Research Contributions
My research is grounded in both theoretical exploration and practical implementation. One of my most significant contributions is in the field of transportation systems, where I have developed models for optimizing vehicle trajectory control at merging ramps and managing traffic under construction. These efforts have led to publications in high-impact journals like the Journal of Transportation Engineering and Transportmetrica B. Specifically, my work on Organized Traffic Interweaving addresses a critical challenge in urban traffic management, proposing cooperative strategies to enhance safety and efficiency in dense traffic conditions.
Research Projects
Research Statement
As a researcher in supply chain management and transportation systems, my work spans the domains of stochastic optimization, machine learning, queueing theory, and their applications to real-world industrial challenges. My primary research focus is on developing models and algorithms that improve decision-making processes in complex, dynamic systems, especially under uncertainty. My work has applications across various fields, including transportation network optimization, electric vehicle (EV) battery inventory control, online platforms, and appointment scheduling. These areas align with my broader objective of driving operational efficiency and sustainability through innovative problem-solving approaches.
Research Contributions
My research is grounded in both theoretical exploration and practical implementation. One of my most significant contributions is in the field of transportation systems, where I have developed models for optimizing vehicle trajectory control at merging ramps and managing traffic under construction. These efforts have led to publications in high-impact journals like the Journal of Transportation Engineering and Transportmetrica B. Specifically, my work on Organized Traffic Interweaving addresses a critical challenge in urban traffic management, proposing cooperative strategies to enhance safety and efficiency in dense traffic conditions.
In addition to transportation networks, my research on supply chain networks, such as in the paper “Relief and stimulus in a cross-sector multi-product scarce resource supply chain network,” applies stochastic optimization techniques to model and improve decision-making in the context of limited resources. This study, published in Transportation Research Part E, not only contributes to the literature on supply chain resiliency but also offers practical solutions to real-time challenges faced by industries in crisis situations, such as the COVID-19 pandemic.
I have also extended my research into online review platforms, focusing on the economic impacts of compensated reviews and platform policies. This interdisciplinary approach combines my expertise in queueing theory and machine learning to model user behavior and optimize platform operations, an emerging area in operations research. My forthcoming INFORMS conference presentation explores how distinguishing between compensated and non-compensated reviews can improve platform credibility and user engagement.
Methodological Approaches
My research methodologies are primarily grounded in stochastic optimization and queueing theory, both of which are powerful tools for addressing uncertainties in systems. I have applied these techniques to problems like the EV battery inventory control and dynamic pricing models in the retail industry, which improved profitability and efficiency in supply chain management. For example, during my collaboration with Hangzhou LineZone Data Technology, I developed time series forecasting models that reduced inventory costs and optimized pricing strategies for children’s shoes, resulting in a 20% increase in total profit.
Further, my work in machine learning has driven novel approaches in customer segmentation and recommendation systems. At STARCOR Information Technology, I developed a semi-supervised learning algorithm to increase product sales, demonstrating the applicability of advanced algorithms to industry-specific challenges. I am keen to continue exploring how machine learning can be integrated with traditional operational research techniques to yield more robust solutions for real-world problems.
Current and Future Research
I am currently working on several projects that explore emerging challenges in supply chain and transportation networks. These include:
- A Distributionally Robust Optimal Approach for Vaccination Appointment Scheduling Problems: This project addresses the healthcare sector’s need for efficient resource allocation during pandemics, using robust optimization techniques to account for uncertainty in demand and supply.
- Modeling Rare Earth Material Recycling and Policy Uncertainties in Closed-loop Supply Chain Networks: This study focuses on supply chain sustainability, particularly in the recycling of rare materials crucial to technology production, such as semiconductors. It employs a generalized Nash equilibrium approach to model the economic impacts of policy and market shifts, which I aim to submit to the INFORMS Journal on Computing.
Moving forward, I plan to extend my research in three directions:
- Sustainable and Resilient Supply Chains: I am particularly interested in applying game theory and multi-agent systems to study the dynamics of supply chain networks under environmental and economic constraints. By exploring the equilibrium states in closed-loop supply chains, I aim to develop strategies that enhance resiliency and sustainability, particularly in the face of global disruptions like climate change and resource scarcity.
- Integration of AI and Operations Research: With the increasing availability of data and computational power, I see significant opportunities in combining AI-driven techniques with traditional optimization approaches. Specifically, I want to explore how machine learning can be used to address the complexities in real-time decision-making processes within transportation systems and supply chains.
- Healthcare Operations Research: Building on my recent work in appointment scheduling, I plan to expand into healthcare systems optimization. This includes improving resource allocation in hospitals, optimizing patient flow, and developing decision support systems for healthcare professionals using predictive analytics and optimization techniques.
Conclusion
In summary, my research bridges the gap between theory and practice in supply chain management and transportation systems. By applying cutting-edge techniques in stochastic optimization, machine learning, and queueing theory, I aim to tackle pressing issues in today’s interconnected, data-driven world. As I move forward, I am excited to continue addressing real-world challenges through interdisciplinary collaborations and innovative research, contributing to both the academic community and industry advancements.