Data Science graduate (GPA 4.09/4.5, First Class Honours) seeking a Data Analyst / Data Engineer role in Ho Chi Minh City. I build end-to-end data systems — SQL pipelines, statistical modeling, and ML — with an emphasis on honest results over impressive-looking numbers.
Previously an AI Data & Engineering Intern at Agents2Agents (US), where I shipped 26 merged PRs to a public open-source AI agent framework.
| Project | What it does |
|---|---|
| VN30 Stock Movement Prediction | Leak-free ML pipeline predicting next-day direction for all 30 VN30 stocks, with time-aware validation and honest error analysis |
| QuakeScope | End-to-end ELT pipeline + analytics on 124k+ global earthquakes (PostgreSQL, DBSCAN, Gutenberg-Richter, FastAPI, interactive map) |
| RationIQ | Least-cost feed formulation web app — FastAPI + React + linear programming optimizer |
| depwatch | CLI + GitHub Action that scans a Python project's dependencies and ranks the risky ones (supply-chain health) |
| Fraud Detection API | Real-time credit card fraud scoring API — XGBoost, FastAPI, Discord alerts |
| CPU Benchmark Predictor | Predicts CPU PassMark scores from hardware specs (XGBoost, R² = 0.983) with a SHAP-explained Streamlit app |
Analytics & BI: SQL · Excel · Streamlit · statistical testing · A/B analysis Programming: Python · Pandas · NumPy · FastAPI Machine Learning: XGBoost · LightGBM · Random Forest · Scikit-learn · PyTorch · SHAP Data Engineering: ELT pipelines · PostgreSQL · REST APIs · CI/CD