Nguyen Quy Trong

Ha Noi,Viet Nam

Summary

Data Science student with academic projects in data preprocessing, feature engineering, machine learning, and financial data analysis. Interested in applying Python and machine learning to financial time-series data, model evaluation, and data-driven research. Strong focus on preparing clean, useful, and model-ready datasets.

Overview

year of professional experience

Work History

Financial Data Preparation

Tesla Stock Price Forecasting

03.2026 - 05.2026

Supported forecasting experiments by preparing model-ready data for ARIMA, Prophet, XGBoost, LSTM, and TCN.
Applied chronological train/test split with 3,400 training records and 502 testing records, minimising risk of data leakage in forecasting models.
Conducted EDA to analyse long-term trend, volatility clustering, and drawdown risk, revealing maximum drawdown of -73.63% for risk assessment.
Prepared 3,902 daily TSLA trading records (2010-2025) for financial time-series forecasting project, enhancing data availability for analysis.

Machine Learning Classification

Stroke Risk Prediction

09.2025 - 12.2025

Evaluated 5 machine learning models: Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and XGBoost to identify optimal solutions for classification tasks.
Selected Logistic Regression as the best screening model, achieving 82% Recall and 0.847 AUC-ROC.
Addressed severe class imbalance, with only 4.9% positive stroke cases, using SMOTE on the training set.
Managed data preprocessing tasks including missing values, outliers, one-hot encoding, feature scaling, and stratified train/test split to ensure robust model training.
Developed machine learning pipeline processing 5,110 patient records, integrating 11 medical and demographic features to enhance predictive analytics.

Education

Data Science

VNU University of Science - Vietnam National University

Hanoi, Vietnam

Skills

Financial Data: OHLCV Data, Daily Return, Moving Average, Volatility, Time-Based Train/Test Split
Data Processing: Pandas, NumPy, Data Cleaning, Missing Value Handling, Outlier Handling, Feature Engineering
Programming: Python, SQL, Bash, Scala
Machine Learning: Scikit-learn, Classification, Regression, Model Evaluation, Cross-Validation, SMOTE

Big Data: Apache Spark, Spark DataFrame, Spark SQL, Window Functions Visualization: Matplotlib, Seaborn
Data Visualisation
Tools: Google Colab, Jupyter Notebook, VS Code, Linux/WSL, Docker, Git/GitHub

Timeline