I’m focused on learning and growing in data analysis, SQL and machine learning through practical projects.
In this project, I analyzed 2024–25 NBA playoff and play-in matchups using the NBA API, focusing on team strengths, key player matchups, and regular season performance comparisons. I visualized the insights using Python to highlight competitive advantages.
This project is a deep learning application developed using TensorFlow 2. The goal is to build a model that classifies bottles in images, videos, or camera streams by type. The project also includes experimentation with different model trainings, visualization of results, and analysis of performance metrics.
In this project, I compared five of the greatest NBA players of all time using both modern and historical stats from the NBA API and award data from Wikipedia. I developed a custom metric to evaluate their all-around impact and visualized the results to support the final comparison.
In this project, I analyzed the top MVP candidates of the 2023–24 NBA regular season using NBA API data. I compared their statistical performance, consistency, and impact metrics, and visualized the comparisons to identify the strongest contenders.
In this project, I analyzed the nutritional values of Starbucks food items to explore category patterns and calorie distribution. I then built a machine learning model to classify food types (bakery, hot breakfast, lunch, etc.) based on their nutritional features using algorithms like Decision Tree and Logistic Regression.
Using the Spotify API, audio features and genre data were extracted from user playlists. These were matched with a 1-million-song dataset from Kaggle to identify songs similar to the playlist. A content-based machine learning model then recommended 10 new songs tailored to the user’s taste. The project combines data analysis, visualization, and recommendation systems to personalize music discovery through technology.