TRAN MINH DUC

My passion goes beyond programming and data exploration. With an evident goal of becoming a Data Engineer at initial phase, I devoted time to building foundations in data infrastructure, pipelines, and scalable systems. Concurrently, I actively develop my skills in Data Science, solidify my understanding of machine learning and analytical thinking. My long-term ambition is to advance into Natural Language Processing (NLP), and ultimately acquire Deep Learning techniques to solve real-world complex problems and contribute to the broader potential of AI.

• GPA: 3.38 / 4.00

• Over 3.5 million clan records consisting of clan properties (war league, wins/losses/ties, member stats, etc.).
• Perform EDA on both surface-level and rigorous performance per region.
• Explore the cultural behavior of clans through description text.
• Expect to dive into war metrics modeling and NLP-based analysis.

• Developed an end-to-end machine learning pipeline for house price prediction using actual Vietnamese real estate data (BatDongSan.vn) in 2025.
• Performed data collection, preprocessing, feature engineering, and exploratory analysis to observe patterns.
• Built and evaluated multiple models (notably regression models and gradient-boosting machines) with cross-validation and leakage control.
• Implemented a stacked ensemble achieving human performance (RMSE ≈ 0.783, R² ≈ 0.47), improving model stability and generalization.
• Designed a structured, reproducible project workflow with modular pipelines, testing, and Streamlit-based reporting.

• Programming Languages: Python, SQL, Java (educational)
• Tech Stack: Python libraries (Numpy, Pandas, Matplotlib, Seaborn, etc.), Web Technologies for Data Applications (HTML, CSS, JavaScript), Linux (Ubuntu), LaTeX
• Relevant University Coursework: Calculus, Linear Algebra, Probability – Statistics & Random Process, Discrete Mathematics, Object-Oriented Programming, Data Structures & Algorithms, Principles Of Database Management, Web Application Development
• Additional Learning: Exploratory Data Analysis, Web Scraping & APIs, Machine Learning
• Language: English (Advanced)

• Datastorm Competition 2025 - Qualifying Round 1
  Data Science competition concetrating on real-world problem solving and EDA
  
• HackerRanl SQL Skills Certification
  Demonstrated proficiency in SQL querying, data manipulation, and relational database concepts