Thailand Domestic Tourism
Date Originated: June 15th, 2025This dataset reveals the total revenue, number of tourists and accommodation expenses of Thailand tourism, showcasing how the tourism contributes to the Thailand's overall economy
About Me
Duc Tran Minh (he/him/his) Undergraduate of Computer Science
Greetings all for coming across my personal website, where i share my insights into hands-on projects and academic milestones. There are decent sections to explore about my work and contribution to Data Science field.
Currently, i'm an undergraduate majoring in Computer Science at International University, VNU-HCM with a concentration on becoming quintessential Data Scientist and bridging the gap between modeling techniques and real-world applications. My interests lie in the discovery of Natural Language Processing (NLP), inspired by rapid growth of generative AI tools in recent years.
My ultimate goal is to resolve complex real-world problems under the intergration of advanced technical methods.
Projects
Exploratory Data Analysis (EDA)
At the beginning of journey (June 2025 - August 2025), i discovered different Python libraries and analyzed datasets, combining with personal experience to observe the subtle facts. Prior to those, i also did small experiments with simulated numerical features to cultivate my practice.
Clash Of Clans - Elune Project
Date Originated: Aug 24th, 2025This dataset reveals the static properties of over 3 million clans during eco-snapshot in 2023. Through out seasonal peaks and subtle decline, the game remains long-lasting momentum during the rise of RPG-style figures.
Machine Learning / Deep Learning
Built upon exploratory analysis, these projects focus on building all-inclusive machine learning pipelines, with an emphasis on real-world data, robust evaluation, and model generalization. The workflow comprises data collection, feature engineering, model experimentation, and deployment via feasible platforms.
Vietnam Real Estate - Codename: Azeroth
Date Originated: Sep 19th, 2025A house price prediction project using Vietnam real estate data collected from BatDongSan.vn. The whole process involves data scraping, preprocessing, feature engineering, and exploratory analysis to capture insightful market patterns.
Trained and evaluated multiple regression and gradient boosting models (LightGBM, XGBoost, CatBoost) with cross-validation and leakage control. A stacked ensemble achieved human-capable performance (RMSE ≈ 0.783, R² ≈ 0.47), indicating decent generalization improvements across diverse property segments. Additionally, EDA section was briefly introduced via Streamlit.
Miscellaneous
Besides the mainstream, i also learn Mathematics during idle time as a complementary to sharpen my relevant concepts, which is addressed to numerous sample tests solved in revision. Branches involves Calculus, Linear Algebra and Probability. In the long run, the investment will not be as active as before, specifically only updating several sample tests for core subjects.
Mathtoolkit Repository
Date Originated: Jan 5th, 2025State-of-the-art & Revolting Mathematical Museum
Ongoing Plans
I am currently working on expanding further knowledge in Data Engineering and Artificial Intelligence, while also solidifying my understanding of Data Science
- Acquiring supplementary Data Engineering concepts and tools
- Preparing for internship opportunities
- Cultivating Machine Learning workflows via end-to-end projects
- Upcoming themes: Deep Learning, and possibly huge revamp on Mathematics