David Guanhua
Data Scientist
Massachusetts, Singapore
Summary
👤
Senior🎓
Top SchoolDavid Guanhua is a data scientist with a decade of technical experience blending NLP, machine learning, and full-stack engineering across cloud and distributed systems. He has applied lexical and vector semantics, probabilistic and deep learning models (including Transformer-based NMT), and classic supervised/unsupervised methods in Python and R to productionized ML tasks, often leveraging PySpark, Spark MLlib, and AWS/GCP for scale. He complements modeling expertise with practical data engineering—building ETL pipelines in Oracle SQL, querying NoSQL with Spark, and creating BI dashboards in Tableau and OBIEE—as well as front-end and mobile experience in PHP/Node and Flutter. Educated across institutions in China, Korea, Singapore and the US (Boston University MSCIS), he pairs a multidisciplinary academic background with hands-on implementation. An active GitHub presence (leebond) surfaces his engineering-first approach to data science and product-focused solutions.
10 years of coding experience
Master of Science, Computer Information Systems, MSCIS, Master of Science, Computer Information Systems, MSCIS at Boston UniversityBachelor of Engineering (B.Eng.) with Honours, Engineering Systems and Design, Bachelor of Engineering (B.Eng.) with Honours, Engineering Systems and Design at Singapore University of Technology and Design (SUTD)Econometrics and Macroeconomics, 4.0/4.0, Econometrics and Macroeconomics, 4.0/4.0 at Hanyang UniversityProduct Innovation and Design, Product Innovation and Design at Zhejiang University
Chinese, English
Github Skills (16)
ide7
anaconda6
language-server-protocol6
python6
development-environment5
qt5
web-application5
prediction-model5
prediction5
react4
pyqt3
simulation3
simulations3
baduk3
python-development2
Programming languages (3)
Github contributions (5)
leebond/function-of-best-fit-line
Jul 2017 - Dec 2019
Contributions:2 pushes, 1 branch in 2 years 5 months
docligot/CoronaTracker-simulteModel
Feb 2020 - Mar 2020
Simulations model for outbreak prediction
Contributions:50 commits, 2 PRs, 5 pushes in 1 month
outbreakpredictionsimulationssimulationbaduk
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.