Qi Luo receives INFORMS-Sim best student paper award
U-M IOE PhD candidate, Qi Luo, receives PhD Colloquium Best Student Paper Award at the INFORMS Simulation Society’s annual Winter Simulation Conference.
IOE-STAGE SITE
Qi Luo, U-M Industrial and Operations Engineering (IOE) PhD candidate, has received a 2019 Winter Simulation Conference I-Sim PhD Colloquium Best Student Paper Award.
The INFORMS Simulation Society (INFORMS-Sim), is one of several organizations which sponsor the Winter Simulation Conference (WSC) PhD Colloquium. Each year, INFORMS-Sim grants best paper awards to PhD students who are within one year of graduation.
Luo’s paper, titled “Dynamic Congestion Pricing for Ridesourcing Traffic: A Simulation-Based Approach” looks at how simulation and optimization can be used to determine proper congestion pricing for ride-sourcing services, which can significantly increase traffic in densely populated cities.
“I am truly honored to receive this award that recognizes our work on bridging the advances in simulation optimization theory and a pressing social problem in transportation,” Luo said. “It is an exciting time to work on complex decision-making with multiple sources of streaming data.”
“I am truly honored to receive this award that recognizes our work on bridging the advances in simulation optimization theory and a pressing social problem in transportation …”
Qi Luo
PhD Candidate, U-M Industrial & Operations Engineering
The paper uses a simulation optimization based on traffic conditions to compute the optimal congestion pricing in a more efficient way than a randomized stochastic optimization method. Luo hopes that this data-driven approach can be applied on a mass scale to alleviate congestion pricing problems wherever there are ride-sourcing services.
Luo co-wrote the paper with Zhiyuan Huang, another U-M IOE student, and Henry Lam, Associate Professor of Industrial Engineering and Operations Research at Columbia University.
Qi Luo is a U-M IOE PhD candidate and his main research interest is integrating online learning algorithms with game theory. His current research focuses on bandit controls, multiagent dynamic Stackelberg games, and optimization methods for multimodal transportation ecosystem.