Chonghuan Wang 「王崇焕」

I am now a fourth-year PhD candidate in Data Science Lab at MIT, advised by Prof. David Simchi-Levi. I am affiliated with the Laboratory for Information and Decision Systems, Center for Computational Science and Engineering and Department of Civil and Environmental Engineering, MIT. Prior to joining MIT, I received my bachelor's degree in information engineering from Shanghai Jiao Tong University in 2020 advised by Prof. Haiming Jin and Prof. Xinbing Wang.

I am selected as 2023-2024 Accenture Fellow!

My research focuses on leveraging statistical learning techniques to design efficient, reliable and sustainable field experiments in clinical trials, online platforms, healthcare, etc. My research goal is to enhance social good with the power of statistical learning, econometrics theory and experimental design. I am also broadly interested in operations research, machine learning, econometrics and their interplay.

Email: chwang9 [at]

profile photo
You can catch me at INFORMS2023:
  The session I will co-chair:
     SC06. Learning, Operations and Society
     @12:45 PM - 2:00 PM, Oct. 15th, CC-NORTH 121C
  The talk I will give:
     Multi-Armed Bandit Experimental Design: Online Decision-Making and Adaptive Inference
     @12:45 PM - 2:00 PM, Oct. 16th, CC-NORTH 121A
 The papers I co-authoered:
     Context-Based Dynamic Pricing with Separable Demand Models
     Presented by: Prof. Jinzhi Bu
     @2:15 PM - 3:30 PM, Oct. 15th, CC-NORTH 121A
     Context-Based Offline Pricing and Demand Learning with Separable Demand Models
     Presented by: Renfei Tan
     @12:45 PM - 2:00 PM, Oct. 16th, CC-NORTH 121C

Research (* Alphabetical Order)
Multi-armed Bandit Experimental Design: Online Decision-making and Adaptive Inference
David Simchi-Levi*, Chonghuan Wang*
Preliminary version accepted by AISTATS, 2023
Full version Major Revision, Management Science

Multi-armed bandit has been well-known for its efficiency in online decision-making in terms of minimizing the loss of the participants' welfare during experiments (i.e., the regret). In clinical trials and many other scenarios, the statistical power of inferring the treatment effects (i.e., the gaps between the mean outcomes of different arms) is also crucial. In this paper, we investigate the trade-off between efficiency and statistical power by casting the multi-armed bandit experimental design into a minimax multi-objective optimization problem.

Non-stationary Experimental Design under Structured Trends
David Simchi-Levi*, Chonghuan Wang*, Zeyu Zheng*
Preliminary version accepted by NeurIPS, 2023
Full version SSRN Pre-print

One of the primary objectives of classical experiments is to estimate the average treatment effect (ATE) to inform future decision-making. However, in healthcare and many other settings, treatment effects may be non-stationary, meaning that they can change over time, rendering the traditional experimental design inadequate and the classical static ATE uninformative. In this work, we address the problem of non-stationary experimental design under structured trends by considering two objectives: estimating the dynamic treatment effect and minimizing welfare loss within the experiment.

Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk
David Simchi-Levi*, Chonghuan Wang*
Preliminary version accepted by ICML, 2023
Full version SSRN Pre-print

When launching a new product, historical sales data is often not available, leaving price as a crucial experimental instrument for sellers to gauge market response. When designing pricing experiments, there are three fundamental objectives: estimating the causal effect of price (i.e., price elasticity), maximizing the expected revenue through the experiment, and controlling the tail risk suffering from a very huge loss. In this paper, we reveal the relationship among such three objectives.

Context-Based Dynamic Pricing with Separable Demand Models
Jinzhi Bu*, David Simchi-Levi*, Chonghuan Wang*
Preliminary version accepted by NeurIPS, 2022
Full version Major Revision, Management Science

Motivated by the empirical evidence observed from the real-world dataset, we study context-based dynamic pricing with separable demand models, where the price and the context influence the demand separately. We investigate the statistical complexity of the problem under different structural properties.

Optimizing Cross-Line Dispatching for Minimum Electric Bus Fleet
Chonghuan Wang, Yiwen Song, Guiyun Fan, Haiming Jin, Lu Su, Fan Zhang, Xinbing Wang
Undergraduate thesis
IEEE Transactions on Mobile Computing, 2021
DOI: 10.1109/TMC.2021.3119421
Towards Minimum Fleet for Ridesharing-Aware Mobility-on-Demand Systems
Chonghuan Wang, Yiwen Song, Yifei Wei, Guiyun Fan, Haiming Jin, Fan Zhang
Undergraduate thesis
IEEE Conference on Computer Communications (INFOCOM), 2021
DOI: 10.1109/INFOCOM42981.2021.9488862

1.275/IDS.305 Business and Operations Analytics (Spring 2023)
Teaching Assistant
Enrollment: 42 (primarily MIT Sloan MBA students, Supply Chain Management (SCM) Master’s students, and Leaders for Global Operations (LGO) Master’s students)
Organized weekly TA sessions
Invited Talks
  • January, 2023: Multi-armed Bandit Experimental Design. POMS-HK 2023, Hong Kong.
  • October, 2022: Context-Based Dynamic Pricing with Separable Demand Models. INFORMS Annual Meeting 2022, Indianapolis, IN.

Awards and Honors
  • Accenture Fellowship, MIT, 2023
  • Ho-Ching and Han-Ching Fund Award, MIT, 2023
  • Outstanding Graduate of Shanghai, Shanghai Education Ministry, 2020
  • Tang Lixin Scholarship, Shanghai Jiao Tong University, 2019
  • National Scholarship, Chinese Ministry of Education, 2017,2018
  • A-class Academic Excellence Scholarship, Shanghai Jiao Tong University 2017, 2018

  • Session Chair, INFORMS Annual Meeting 2023
  • Reviewer for NeurIPS2023, ICLR2024
  • Organizer, MIT Data Science Lab Seminar Series, Fall 2023

Updated in Sept 2023. Thanks Jon Barron for the source code. Thanks my friend Minkai Xu for letting me know this great template.