Hazrul Hazarudin
Associate Economist
Kuala Lumpur, Malaysia
Summary
🤩
Rockstar🎓
Top SchoolHazrul Hazarudin is an Associate Economist at Bank Negara Malaysia with four years of experience translating quantitative analysis into policy-relevant insights for monetary and financial market decisions. Trained at LSE in Mathematics, Statistics and Business (First Class), he blends rigorous statistical foundations with practical data-science skills honed through rotations across investment operations, monetary policy and financial surveillance. A machine-learning enthusiast and active open-source contributor, he improved documentation, metrics, benchmarking and hyperparameter tuning in the prominent time-series ML project sktime — work that reflects attention to reproducibility and forecasting performance. Based in Kuala Lumpur, Hazrul combines central-bank exposure to macro-financial risks with hands-on coding and metric design, making him effective at turning complex time-series and market data into actionable policy signals.
4 years of coding experience
SPM Pure Science Stream, MRSM Tun Ghafar Baba, Melaka, 7A+ 1A 1A-, SPM Pure Science Stream, MRSM Tun Ghafar Baba, Melaka, 7A+ 1A 1A- at MARA Junior Science College (MRSM)A-level, Economics, Physics, Mathematics, Further Mathematics, Extended Project Qualification, A*A*A*A*A, A-level, Economics, Physics, Mathematics, Further Mathematics, Extended Project Qualification, A*A*A*A*A at Kolej Tuanku Ja'afar (KTJ)London School of Economics and Political Science
English, Malay
Github Skills (11)
scikit-learn10
forecasting10
pandas10
machine-learning10
time-series10
forecast10
sktime10
python10
scikit10
benchmark9
benchmarking9
Programming languages (3)
Github contributions (5)
sktime/sktime
Feb 2023 - Sep 2023
A unified framework for machine learning with time series
Role in this project:
Data Scientist
Data ScientistContributions:60 reviews, 24 PRs, 182 comments in 7 months
Contributions summary:Hazrul primarily contributed to improving documentation and implementing enhancements related to performance metrics within the `sktime` repository. Their work involved refining docstrings for Mean Absolute Percentage Error (MAPE) and Median Absolute Percentage Error (MdAPE) metrics, clarifying their mathematical formulations, and expanding documentation to include additional parameters. They also worked on extending the forecasting benchmarking framework and adding test coverage. Furthermore, they addressed a bug in the BaseGridCV class, and implemented hyperparameter tuning using `scikit-optimize`.
forecastingtime-series-analysistime-series-regressiondata-sciencedeep-learning
hazrulakmal/sktime
Feb 2023 - Sep 2023
A unified framework for machine learning with time series
Contributions:163 pushes, 39 branches in 7 months
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.