Runzhe Wan

Runzhe Wan

Senior Applied Scientist

Amazon

Biography

I am a Senior Applied Scientist and tech lead at Amazon Stores’ central science org reporting directly to the CEO. I architect and drive high-stakes, cross-organizational initiatives that bring foundation models, LLMs, and causal AI to some of Amazon’s most critical decision systems — work spanning inventory management, pricing, product selection, delivery-speed optimization, and the company-wide experimentation platform — together delivering over $1B in annual business impact.

My research sits at the intersection of generative AI and causal decision-making under uncertainty — building models that reason about counterfactual effects and long-term consequences, personalize to context, and learn from both online interaction and offline data. My interests span foundation models & LLMs, Reinforcement Learning (incl. bandits), and Causal Inference (incl. causal ML).

I earned my Ph.D. in Statistics at North Carolina State University in 2022, advised by Dr. Rui Song, and my B.S. in Mathematics from Fudan University in 2017.

Experience

  • Senior Applied Scientist, Amazon — Apr 2024 – Present
  • Applied Scientist, Amazon — Apr 2022 – Mar 2024
  • Applied / Research Scientist Intern, Amazon — May 2020 – Feb 2022 (part-time within semesters)
  • Research Intern, Bell Labs — Jun 2019 – Aug 2019
Education

  • Ph.D. in Statistics

    North Carolina State University, 2022

  • B.S. in Mathematics

    Fudan University, 2017

Interests
  • Reinforcement Learning (inc. Bandits)
  • GenAI/LLM
  • Causal Inference (esp. Causal ML)

Research

Publications

Filter by topic:

* : Co-First Author

  1. A Review of Causal Decision Making
    Ge, L.*, Cai, H.*, Wan, R.*, Xu, Y.* and Song, R. (2025). Journal of Artificial Intelligence Research
  2. Zero-Inflated Bandits
    Wei, H.*, Wan, R.*, Shi, L. and Song, R. (2025). ICML 2025
  3. Know When to Fold: Futility-Aware Early Termination in Online Experiments
    Liu, Y.*, Wan, R.*, Huang, Y., McQueen, J., Hains, D., Gu, J., and Song, R. (2025). WWW 2025
  4. Contextual Deep Reinforcement Learning with Adaptive Value-Based Clustering
    Gao, Y., Wan, R., Giannakakis, I., Gu, J., and Song, R. (2025). International Conference on Machine Learning Technologies 2025
  5. Robust Offline Policy Evaluation and Optimization with Heavy-Tailed Rewards
    Zhu, J. , Wan, R., Qi, Z., Luo, S. and Shi, C. (2024). AISTATS 2024
  6. Effect Size Estimation for Duration Recommendation in Online Experiments: Leveraging Hierarchical Models and Objective Utility Approaches
    Liu, Y.*, Wan, R.*, McQueen, J., Hains D., Gu, J., and Song, R. (2024) AAAI 2024 Oral
  7. Experimentation Platforms Meet Reinforcement Learning: Bayesian Sequential Decision-Making for Continuous Monitoring
    Wan, R.*, Liu, Y.*, McQueen, J., Hains D. and Song, R. (2023). KDD 2023
  8. Multiplier Bootstrap-based Exploration
    Wan, R.*, Wei, H.*, Kveton, B. and Song, R. (2023). ICML 2023
  9. A Review of Reinforcement Learning in Financial Applications
    Bai, Y.*, Gao, Y.*, Wan, R.*, Zhang, S.*, and Song, R. (2024). Annual Review of Statistics and Its Application
  10. Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework
    Wan, R*., Ge, L.* and Song, R. (2023). AISTATS 2023
  11. Batch Policy Learning in Average Reward Markov Decision Processes
    Liao, P.*, Qi, Z.*, Wan, R., Klasnja, P. and Murphy S. (2022). Annals of Statistics (AoS)
  12. A Multi-Agent Reinforcement Learning Framework for Treatment Effects Evaluation in Two-Sided Markets
    Shi, C., Wan, R., Song, G., Luo, S., Song, R. and Zhu, H. (2022). Annals of Applied Statistics (AOAS)
  13. Mining the Factor Zoo: Estimation of Latent Factor Models with Sufficient Proxies
    Wan, R., Li Y., Lu, W. and Song, R. (2022). Journal of Econometrics (JOE)
    🏆 Best Student Paper Award Business & Econ Section, ASA — declined per one-award-per-year policy
  14. Safe Exploration for Efficient Policy Evaluation and Comparison
    Wan, R., Kveton, B. and Song, R. (2022). ICML 2022
  15. Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models
    Wan, R., Ge, L. and Song, R. (2021). NeurIPS 2021
  16. Deeply-Debiased Off-Policy Interval Estimation
    Shi, C.*, Wan, R.*, Chernozhukov, V. and Song, R. (2021). ICML 2021 Long Oral (3%)
  17. Multi-Objective Model-based Reinforcement Learning for Infectious Disease Control
    Wan, R., Zhang, X. and Song, R. (2021). KDD 2021 🏆 Norman Breslow Young Investigator Award
  18. Pattern Transfer Learning for Reinforcement Learning in Order Dispatching
    Wan, R.*, Zhang, S.*, Shi, C., Luo, S. and Song, R. (2021). IJCAI 2021, RLITS Workshop 🏆 Best Paper Award
  19. Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making
    Shi, C., Wan, R., Song, R., Lu, W. and Leng, L. (2020). ICML 2020

Under Review / Revision

  1. STEEL: Singularity-aware Reinforcement Learning
    Chen, X., Qi, Z. and Wan, R.
  2. Heterogeneous Synthetic Learner for Panel Data
    Shen, Y., Wan, R., Cai, H. and Song, R.

Internal Publications (Amazon)

  1. Inventory Long-Term Value for Inventory Health: An Offline Causal Reinforcement Learning Approach
    Wan, R., Yao, J., Zeng, Y., Liu, C. and Gu, J. (2025) AMLC 2025
  2. Know When to Fold: Futility-aware Early Termination in Online Experiments.
    Wan, R.*, Liu, Y.*, Huang Y., McQueen, J., Hains D., Gu J. and Song, R. (2023) CSS 2024 🏆 Best Paper Award
  3. Experimentation Platforms Meet Reinforcement Learning: Bayesian Sequential Decision-Making for Continuous Monitoring.
    Wan, R.*, Liu, Y.*, McQueen, J., Hains D. and Song, R. (2023) CSS 2023 🏆 Best Paper Award and AMLC 2023
  4. Data-driven substitution aware promise tuning model and promise extension experiment
    Giannakakis, I., Svoboda , R., Wan, R.*, Gu, J., Yao, J. (2023) AMLC 2023
  5. Effect Size Estimation for Duration Recommendation in Online Experiments: Leveraging Hierarchical Models and Objective Utility Approaches
    Liu, Y.*, Wan, R.*, McQueen, J., Hains D., Gu, J., and Song, R. (2023) Econ Summit 2023
  6. Continuous Monitoring of A/B Tests: A Meta Analysis
    Liu, Y.*, Wan, R.*, McQueen, J., Song, R, Hains D. and Richardson, T. (2023) AMLC 2023
  7. Deep Inventory Control Policy for Perishables
    Wan, R., Giannakakis, I., Sisikoglu E., Jiang T., Goyal, V., Song, R. and Gu, J. (2022). CSS 2022 Long talk and AMLC 2022
  8. Reinforcement Learning for Replaceability Index Estimation and Assortment Optimization.
    Wan, R., Giannakakis, I., Gu, J. and Song, R. (2021). CSS 2021 Spotlight (4.8%) and AMLC 2021

Other Contributions

Awards / Honors

Professional Services

Reviewer:

  • Conferences: NeurIPS, ICML, ICLR, UAI, AISTATS, KDD, IJCAI, AAAI, SDM
  • Journals: Annals of Statistics, Journal of the American Statistical Association (T&M), Journal of the American Statistical Association (book review), Journal of the Royal Statistical Society (Series B), EJS, STPA, Transactions on Machine Learning Research (TMLR)

PC member: RLITS Workshop at IJCAI 2021, Online Marketplaces Workshop at KDD 2022/2023