Yuta Saito
PhD Candidate
City of Ithaca, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolYuta Saito is a PhD candidate in Computer Science at Cornell University researching counterfactual learning under Prof. Thorsten Joachims, focused on leveraging biased logged bandit feedback and interactive human behavior data to enable safer, more reliable decision making in real-world systems. With a background in Industrial Engineering and Economics from Tokyo Institute of Technology and eight years of industry and research experience, he blends rigorous causal inference with practical machine learning. Based in Ithaca, he explores methods to correct for real-world biases in datasets and translate counterfactual insights into deployable policies. Notably, his work targets the often-overlooked interplay between human feedback loops and algorithmic recommendations, aiming to improve both effectiveness and trustworthiness in interactive systems.
8 years of coding experience
Cornell University
Github Skills (26)
algorithms10
python10
reinforcement-learning10
datasets10
indexof10
multilabel-classification9
recommender-system9
implicit8
matrix-factorization8
causality8
pairwise8
causal-inference8
fairness-ml7
asymmetric7
recommender6
Programming languages (3)
Github contributions (5)
st-tech/zr-obp
Jun 2020 - Nov 2022
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
Contributions:10 releases, 36 reviews, 671 commits in 2 years 5 months
pythondatasetsoff-policy-evaluationcontextual-banditsmulti-armed-bandits
usaito/unbiased-implicit-rec
Nov 2019 - Jun 2020
(WSDM2020) "Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback"
Contributions:9 commits, 7 pushes, 1 branch in 7 months
recommenderrecommender-systemmachine-learningimplicit-feedbackmatrix-factorization
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.