B.S., Data Science | Universitat Carlemany de Andorra (March 2025)
Utilized the Top 100 Night Clubs 2024 dataset to perform an exploratory data analysis (EDA) using Python. This comprehensive analysis involved cleaning and processing the data, followed by detailed visualization and insights generation. Key findings include trends in club rankings, geographic distribution, and influential factors contributing to club popularity. This data-driven approach provides valuable insights for business owners to enhance their strategies and for the general public to understand the nightlife industry dynamics. The project showcases a robust methodology to derive actionable business intelligence from raw data.
Analyzed marketing campaign data from a Portuguese bank to identify effective strategies for promoting term deposits. Conducted comprehensive data cleaning and processing, followed by SQL-based analysis and visualization. Key findings include the effectiveness of campaign sizes, customer segmentation by job and education level, and seasonal trends in campaign success. This project provides actionable insights to optimize future marketing efforts and improve customer targeting, showcasing a robust approach to deriving business intelligence from raw data.
In this project, I developed a machine learning model to detect fraudulent credit card transactions. I used Python, leveraging libraries like Pandas for data preprocessing, Scikit-learn for model training, and GridSearchCV for hyperparameter tuning. A Random Forest classifier was selected and optimized, achieving a 99% precision, recall, and F1-score. This demonstrates the model's effectiveness in accurately identifying fraudulent transactions with minimal errors.
For a COMPLETE list of projects visit Projects Section