Involved Research Projects

Open Bandit Project

Open Bandit Dataset is a public real-world logged bandit feedback data. The dataset is provided by ZOZO, Inc., the largest Japanese fashion e-commerce company. It is especially suitable for off-policy evaluation (OPE), which attempts to predict the performance of hypothetical policies using data generated by a different, past policy. The data contain the ground-truth about the performance of several bandit policies and enable the fair comparisons of different OPE estimators.

Open Bandit Pipeline is a series of implementations of dataset preprocessing, offline bandit simulation, and evaluation of OPE estimators. This pipeline allows researchers to focus on building their OPE estimator and easily compare it with others’ methods in realistic and reproducible ways. Thus, it facilitates reproducible research on bandit algorithms and off-policy evaluation.

[Paper] [Open Bandit Pipeline] [Docs] [Open Bandit Dataset]

Scholarships and Awards

Professional Service

Conference Program Committee

Workshop Program Committee

Journal Reviewer

Conference Oral Presentations

  1. A Large-scale Open Dataset for Bandit Algorithms
    RecSys 2020 Workshop on Bandit and Reinforcement Learning from User Interactions (REVEAL2020)

  2. Doubly Robust Estimator for Ranking Metrics with Post-Click Conversions
    ACM Conference on Recommender Systems (RecSys2020)

  3. Unbiased Pairwise Learning from Biased Implicit Feedback’’
    International Conference on the Theory of Information Retrieval (ICTIR2020)

  4. Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback
    International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2020)

  5. A Large-scale Open Dataset for Bandit Algorithms
    ICML 2020 Workshop on Real World Experiment Design and Active Learning (RealML2020)

  6. Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback’’
    International Conference on Web Search and Data Mining (WSDM20)

  7. Unbiased Pairwise Learning from Implicit Feedback’’
    NeurIPS 2019 Workshop on Causal Machine Learning (CausalML)

  8. Doubly Robust Prediction and Evaluation Methods Improve Uplift Modeling for Observational Data’’
    SIAM Conference on Data Mining (SDM2019)