I'm Jaewon Shim, an aspiring data scientist fueled by curiosity and a knack for turning numbers into narratives. With a blend of analytical expertise and creative thinking, I transform raw datasets into meaningful insights that drive innovation and impact.
As a Data Science major at UC Berkeley, I've honed my skills in machine learning, statistical analysis, and data visualization, while gaining hands-on experience through my internship as a Data Scientist Intern at Spectra-Physics Lasers, MKS Instruments. There, I tackled real-world challenges, such as uncovering discrepancies in enterprise data systems and optimizing data workflows. Step into my portfolio to explore the intersection of technology, innovation, and the art of data science.
Feel free to connect with or contact me via
LinkedIn.
Explore the future of financial markets with this cutting-edge project on forecasting Samsung's stock prices. Leveraging deep learning architectures built with TensorFlow in Python, the model achieved an impressive R-squared value of 0.95, showcasing its predictive accuracy and potential for real-world financial applications.
Dive into the dynamic world of California real estate with an exploratory data analysis of housing costs. Using advanced predictive modeling techniques in Python and the Scikit-learn library, uncover patterns and predict housing prices in one of the most competitive markets in the U.S.
Gain valuable insights into the global pandemic with a comprehensive exploration of COVID-19 data. Harness the power of advanced SQL queries to reveal trends, uncover anomalies, and make data-driven observations about one of the most impactful events of our time.
Navigate the evolving job market for data professionals with a deep dive into the world of Data Scientists. This project explores trends, skills, and opportunities in the data-related job market, presenting an engaging overview for aspiring and experienced data scientists alike.
Dive into the intricacies of data preparation with this project, focused on cleaning Nashville's housing data using advanced SQL queries. This project demonstrates efficient data wrangling techniques, ensuring clean and actionable datasets for insightful analysis and decision-making.
Developed a web scraping tool to extract product names and average customer ratings from the Amazon website. This project showcases the ability to monitor and analyze rating trends over time, providing valuable insights into customer sentiment and product performance.
