Skip to content

HKU-IDS Scholar

Dr Wenjie HUANG
Research Assistant Professor
HKU Musketeers Foundation Institute of Data Science and
Department of Industrial and Manufacturing Systems Engineering, HKU  (852) 3917 8255
HW-815, Haking Wong Building, HKU
Department of Industrial and Manufacturing Systems Engineering
Key expertise
Decision-making under uncertainty, Data-driven decision-making, Sequential decision-making
About me
Dr. Wenjie Huang is Research Assistant Professor in Department of Industrial and Manufacturing Systems Engineering, The University of Hong Kong. He received Ph.D. degree from the Department of Industrial Systems Engineering and Management, National University of Singapore (NUS) in 2019 and B.S. degree in the Department of Industrial Engineering from Shanghai Jiao Tong University, China in 2014. Prior to joining HKU, he held joint postdoc positions at School of Data Science, The Chinese University of Hong Kong, Shenzhen and Group for Research in Decision Analysis (GERAD), Quebec, Canada. His research projects have been supported by NSFC research funds, NRF Singapore and NUS Young Investigator Award.
Current Research Project
Data Science is a merging subject which applies knowledge and actionable insights from data, and solves problems in a wide range of application domains. It not only yields good solutions to physical systems, but also learns the intrinsic behaviors of the decision makers, e.g., the risk-sensitive behavior against uncertainty. Data science tools can adjust the automatic decision-making systems to act in consistent with decision maker’s behavior in uncertain environment. In Dr. Huang’s latest project, an inverse reinforcement learning (IRL) framework with robust risk preference is developed and investigated. This method addresses the nature issue that the decision maker does not necessarily have complete information about his own risk-sensitive behavior, also the elicited risk preference produces stronger generalization ability than existing risk-sensitive IRL methods. The framework can be adapted into general class of risk measures (e.g., non-convex, non-parametric and static) to cover a wide range of risk-sensitive behaviors. The IRL problem can also be reformulated as a large-scale convex optimization model. Decomposition method will be developed to solve this convex optimization model to increase the scalability of solution algorithm. The framework has two potential real-life applications: a ride-sharing surge pricing problem and diabetes medical treatment problem. For ride-sharing problem, our method can help attain more reliable reward than existing methods. For medical treatment problem, our method can treat and control extreme severe diseases automatically. In all, the proposed method is expected to produce great academic and social impacts, contributing to create more reliable service systems.
Selected Publications
Research Interests
His research focuses on the quantitative methodologies of decision-making under uncertainty, data-driven decision-making and sequential decision-making, with operations management and social good applications.
Rpg students
Mr. Junjie Lei (PhD student)