I am an assistant professor of Industrial Engineering and Decision Analytics at the Hong Kong University of Science and Technology. My research focuses on online marketplaces, with an emphasis on how technological interventions shape user behavior and market outcomes. I study the causal effects of market policies, the economic dynamics among multiple stakeholders, and the optimization of platform operations—including digital experimentation, recommender systems, and pricing algorithms. Methodologically, my work draws on causal inference, econometrics, statistics, and machine learning.
Previously, I received my BS in mathematics from Peking University (2017), my MS in statistics and PhD in computational and applied mathematics from Stanford University (2021), where my doctoral research was advised by Susan Athey. I was a postdoc fellow at Stanford Graduate School of Business in the Golub Capital Social Impact Lab (2022). I have also spent the summers of 2019 and 2020 at Google Research and have worked full-time at Kuaishou Technology during 2021-2022.
I'm looking for research assistants with strong computational skills. Interested candidates are encouraged to email me their resumes.
Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach. [arxiv]
Ruohan Zhan, Shichao Han, Yuchen Hu, Zhenling Jiang.
Extended abstract appeared in ACM Conference on Economics and Computation (EC'24). Working Paper.
Post-Episodic Reinforcement Learning Inference. [arxiv]
Vasilis Syrgkanis, Ruohan Zhan.
Working Paper.
Policy Learning with Adaptively Collected Data. [arxiv, software]
Ruohan Zhan, Zhimei Ren, Susan Athey, Zhengyuan Zhou.
Management Science. 2023.
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization. [arxiv]
Sanath Kumar Krishnamurthy, Ruohan Zhan, Susan Athey, Emma Brunskill.
Conference on Neural Information Processing Systems (NeurIPS) 2023.
Confidence intervals for policy evaluation in adaptive experiments. [arxiv, software]
Vitor Hadad, David A. Hirshberg, Ruohan Zhan, Stefan Wager, Susan Athey.
Proceedings of the National Academy of Sciences 118.15, 2021.
Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits. [arxiv, software]
Ruohan Zhan, Vitor Hadad, David A. Hirshberg, Susan Athey.
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2021.
Adaptively Learning to Select-Rank in Online Platforms. [arxiv]
Jingyuan Wang, Perry Dong, Ying Jin, Ruohan Zhan, Zhengyuan Zhou.
Short version accepted by International Conference on Machine Learning (ICML) 2024. Working Paper.
Statistical Properties of Robust Satisficing. [arxiv]
Zhiyi Li, Yunbei Xu, Ruohan Zhan.
Short version accepted by International Conference on Machine Learning (ICML) 2024. Working Paper.
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor. [arxiv]
Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, Kun Gai, Bo An.
International Conference on Learning Representations (ICLR) 2023.
Two-Stage Constrained Actor-Critic for Short Video Recommendation. [arxiv]
Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, Peng Jiang, Kun Gai.
Proceedings of the Web Conference (WWW) 2023.
Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation. [arxiv]
Ruohan Zhan, Changhua Pei, Qiang Su, Jianfeng Wen, Xueliang Wang, Guanyu Mu, Dong Zheng, Peng Jiang.
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2022.
Beyond Central Limit Theorem for Higher-Order Inference in Batched Bandits.
Yechan Park, Ruohan Zhan, Nakahiro Yoshida.
NeurIPS Workshop on Causality for Real-world Impact, 2022.
Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities. [arxiv, software]
Ruohan Zhan, Konstantina Christakopoulou, Ya Le, Jayden Ooi, Martin Mladenov, Alex Beutel, Craig Boutilier, Ed Chi, Minmin Chen.
Proceedings of the Web Conference (WWW) 2021.
Distortion Agnostic Deep Watermarking.
[paper]
Xiyang Luo, Ruohan Zhan, Huiwen Chang, Feng Yang, Peyman Milanfar.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.
Machine learning for cardiac ultrasound time series data.
[paper]
Baichuan Yuan, Sathya R Chitturi, Geoffrey Iyer, Nuoyu Li, Xiaochuan Xu, Ruohan Zhan, Rafael Llerena, Jesse T Yen, Andrea L Bertozzi.
Medical Imaging: Biomedical applications in molecular, structural, and functional imaging (SPIE) 2017.
CT image reconstruction by spatial-radon domain data-driven tight frame regularization.
[arxiv]
Ruohan Zhan, Bin Dong.
SIAM Journal on Imaging Sciences 9 (3), 1063-1083, 2016.
IEDA3560: Predictive Analytics.
This course focuses on how companies identify, evaluate, and capture decision analytic opportunities to create value. It covers both foundational analytical methods and real-world corporate case studies. Topics include using data to generate insights and develop predictive capabilities through techniques such as machine learning, data mining, and forecasting. The course also introduces optimization methods to support decision-making in complex environments with numerous alternatives and business constraints. By the end of the course, students will be equipped to recognize opportunities where decision analytics can enhance performance and inform strategic decisions.
IEDA4000D: Introduction to Causal Inference.
This course introduces the fundamental concepts and statistical methods used in causal inference. Understanding causal relationships is essential in fields such as economics, digital marketing, healthcare, and policy evaluation. Students will learn how to evaluate the impact of interventions—such as a new product design on user experience, a price change on sales, or a welfare incentive on employee performance. The course equips students with core tools for estimating causal effects and conducting hypothesis tests using both experimental and observational data. Students will also gain hands-on experience working with real-world datasets. Special topics may include A/B testing on digital platforms and recent advances that integrate causal inference with machine learning.