HA GIA HUY

Intro

Hi, I'm Ha Gia Huy — a final-year Information System student at UIT – Vietnam National University. I'm deeply interested in Machine Learning and Data Science, and I’m flexible working across Data Engineering and Data Analyst roles depending on the problem and product.

I enjoy building scalable solutions using big data technologies like Apache Kafka, Spark, and PostgreSQL. I love working with data end-to-end — from cleaning and transforming it to building models that deliver real-world impact.

Outside of tech, I cultivate planted aquariums and work on sustainability-driven projects that combine creativity, science, and care for the environment. Feel free to explore my projects or connect with me on LinkedIn and GitHub!

Work

📍 GeoSegmentation

A logistics‑optimization tool for the U.S. market that combines customer segmentation, demand forecasting, and cost‑based regional analysis to recommend the most cost‑effective freight hub locations. Built with KNN for segmentation, Random Forest for forecasting, and integrated freight-cost datasets, it identifies ideal states per region.

📄 RagResearch

A Retrieval-Augmented Generation tool designed to recommend relevant research papers. Powered by GPT‑4o, MiniLM‑v6 embeddings, and Pinecone as the vector DB. Wrapped in a Streamlit frontend, it embeds papers, processes queries, and returns curated recommendations in real time.

🩺 EHRAgent

A GPT‑powered agent tailored for Electronic Health Record querying. It dynamically generates, executes, and iteratively refines Python code to answer complex, multi‑table clinical questions—achieving up to a 30% boost in success rate over baselines.

These are just a few examples of my work. Visit my GitHub to explore more projects in ML, data engineering, NLP, and beyond.

🎓 Academic & Team Work

I led a team at the AISC competition hosted by UIT, where we tackled AI and data challenges in a time-constrained setting. I also completed several academic projects focused on data preprocessing, visualization, and machine learning, using Python libraries such as pandas, scikit-learn, and matplotlib.

I’m comfortable using tools like Docker, GitHub, and cloud platforms, and I enjoy collaborating through clean Git workflows and clear communication.

About

I’m Ha Gia Huy, a final-year Information Systems student at the University of Information Technology – VNU HCM. My core interests lie in Machine Learning, Data Science, and Data Engineering, with hands-on experience building real-time data pipelines and developing AI-powered systems.

I enjoy working across the full data stack — from transforming raw data into usable formats, to creating ML solutions that solve real-world problems. My toolkit includes Python, Apache Spark, Kafka, PostgreSQL, and cloud tools, and I’m comfortable in both Linux and containerized environments like Docker.

Outside of tech, I’m passionate about environmental sustainability. I create natural aquascapes, grow aquatic plants, and design eco-friendly systems — including ideas for a green café and plant-based reward ecosystem. I find joy in slow, steady growth — whether it's in nature, learning, or code.

I thrive in collaborative environments, love tackling tough problems, and am always looking to improve both as a developer and a person. Curious to connect? Reach out via LinkedIn, GitHub, or email!

Contact

• Linkedin
• Instagram
• GitHub

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';