Welcome to my GitHub profile! I'm a data scientist and software developer with a background in computational mathematics and information technology management. I recently graduated from the University of Waterloo and am eager to continue leveraging my skills in data science, data analysis, data engineering, and software development.
🔍 Currently exploring opportunities in data science, analytics, and engineering, and always open to collaborating on interesting projects.
- Languages: Python, Java, SQL, R, MATLAB, JavaScript, TypeScript, React.js, Ruby, Bash, HTML/CSS, C/C++, Assembly
- Tools & Technologies: AWS, GCP, Kubernetes, Docker, Jupyter Notebook, Tableau, Looker, Power BI, Git, Linux/Unix
- Specialties: Software Development, Data Science, Data Analytics, Data Engineering
📊 Check out my repositories for projects involving machine learning, NLP, web scraping, and more!
- Developed a patent landscape tool using machine learning and NLP techniques like TF-IDF, Principal Directional Analysis (PDA), and Sentence Transformers to extract and analyze key trends from patent data. This project improved trend analysis accuracy by 60% and was presented to the Canadian Intellectual Property Office.
- Built a concert price prediction tool that scrapes ticket pricing, event details, and artist social media statistics using Selenium and BeautifulSoup. Leveraged scikit-learn to develop a machine learning model with Random Forest Regression to predict concert ticket prices based on gathered data.
- Designed a custom protocol for reliable file transfer over UDP in Python. This protocol includes error detection and correction mechanisms, achieving a 70% improvement in transfer reliability, even under high-noise conditions.
- Implemented a Huffman algorithm in Java to optimize data storage and transmission. This project achieved a 50% reduction in file size while maintaining data integrity.
Data Scientist
May 2022 - April 2024
- Developed metrics and visualizations to enhance research reports using Pandas, NumPy, PyTorch, and TensorFlow
- Built robust data cleaning scripts, improving data quality by 70%, and categorized unstructured data through machine learning algorithms, boosting visualization accuracy by 30%
Software Developer
May 2021 - August 2021
- Contributed to the CI/CD process for a remote desktop access solution, reducing deployment time by 20%
- Optimized application performance by 25% for NVIDIA hardware and resolved critical bugs, enhancing user satisfaction by 15%
Data Analyst
January 2020 - August 2020
- Deployed ETL pipelines and automation workflows in SQL on GCP, reducing operational time by 25%
- Created data-driven marketing reports with Tableau and Looker, increasing campaign efficiency by 20%
Don't hesitate to reach out if you're interested in collaborating or discussing potential opportunities.