Hao Chun Chang
Software Engineer at KURA care
Taiwan
Summary
👤
Senior🎓
Top SchoolHao Chun Chang is a pragmatic software engineer with nine years of experience building machine learning-driven backend systems for healthcare. He combines a bioinformatics background from National Taiwan University with hands-on ML work—ranging from ultrasound-based liver cirrhosis classifiers to patient-facing reminder systems integrated with vital-sign devices—to improve home care compliance for cardiac patients. At KURA care he designs APIs and feedback loops informed by behavioral and vital-data analysis, and previously built medical text-mining and data-collection tooling to address dataset shortages. An active contributor to scikit-learn, he has improved documentation and added algorithmic features such as staged prediction for gradient boosting and LocalOutlierFactor clarifications, showing both production focus and attention to ML tooling. Based in Taiwan, he blends clinical-domain insight with backend engineering to turn noisy medical data into actionable, deployable systems.
9 years of coding experience
2 years of employment as a software developer
Master's degree, Bioinformatics, Master's degree, Bioinformatics at National Taiwan UniversityGarage+
Chinese, English
Stackoverflow
3reputation
919reached
6answers
1question
Github Skills (17)
python10
data-science10
scikit10
machine-learning10
scikit-learn10
documentation9
statistics8
pip6
nlp6
playback6
aws-lambda6
buffer6
amazon-web-services6
pytest6
amazon-rds6
Programming languages (9)
Github contributions (5)
scikit-learn/scikit-learn
Apr 2020 - Sep 2022
scikit-learn: machine learning in Python
Role in this project:
Data Scientist
Data ScientistContributions:19 reviews, 11 commits, 7 PRs in 2 years 5 months
Contributions summary:Hao primarily contributed to improving documentation and adding new features related to machine learning algorithms within the scikit-learn library. Their commits focused on the `LocalOutlierFactor` implementation, enhancing documentation to clarify its usage, parameters, and available functionality, especially in the context of novelty detection. They also added staged prediction capabilities to the `HistGradientBoosting` classes, allowing for monitoring performance at each iteration. Furthermore, the user fixed an error message related to the `coverage_error` metric.
data-analysispythonstatisticsdata-sciencelearn-machine-learning
haochunchang/scikit-learn
Apr 2020 - Jan 2024
scikit-learn: machine learning in Python
Contributions:60 pushes, 17 branches in 3 years 10 months
pythondata-sciencelearn-machine-learningneural-networksmachine-learning
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.