Pavel Metrikov
Data Scientist
Bellevue, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolPavel Metrikov is a data scientist with five years of industry experience and a deep research background bridging applied physics, mathematics, and computer science. Based in Bellevue, he works at Microsoft on data-driven products and has longstanding ties to academic research through roles at the Institute for Problems of Information Transmission and a PhD program at Northeastern. His early internships at Yandex and Microsoft focused on learning-to-rank and search-layout effects on ad engagement, reflecting a strong specialty in statistical modeling, simulation, and noisy-label learning. Pavel combines production-oriented software engineering experience (J2EE, Oracle) with rigorous scientific software development, enabling him to translate complex models into deployable solutions. An understated strength is his continuity across research and product environments, allowing him to tackle both foundational algorithmic challenges and real-world system constraints.
5 years of coding experience
4 years of employment as a software developer
MS, Appl. Physics & Mathematics, MS, Appl. Physics & Mathematics at Moscow Institute of Physics and Technology (State University) (MIPT)PhD, Computer Science, PhD, Computer Science at Northeastern University
Github Skills (17)
gbm10
catboost10
kaggle10
parallel10
python10
microsoft10
classification10
r10
data-mining10
machine-learning10
gradient10
gradient-boosting10
boosting10
lightgbm10
ranking10
Programming languages (1)
Github contributions (2)
metpavel/LightGBM
Sep 2020 - Sep 2023
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Contributions:1 PR, 80 pushes, 7 branches in 2 years 11 months
gbmclassificationmulti-label-classificationdistributed-traininglinear
microsoft/LightGBM
Oct 2020 - Oct 2020
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Contributions:17 reviews, 1 commit, 2 PRs in 1 day
kagglepythondata-mininglightgbmmicrosoft
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.