Here are two key projects I contributed to during my volunteer work, showcasing my data analysis and machine learning skills.

A comprehensive comparative study of health expenditure data for 192 countries over the past two decades. This project covered the entire data pipeline—from data collection and cleaning to analysis and visualization—with the goal of generating actionable insights. Visualizations included bar charts and filled maps for summary dashboards, and point maps for detailed views.

This project focuses on detecting fraudulent credit card transactions using anomaly detection techniques. I built a machine learning model to analyze transaction patterns, identify suspicious outliers, and evaluate model performance with metrics like precision, recall, F1-score, and AUC-ROC. Visualizations such as ROC curves and confusion matrices helped assess the model's ability to detect fraud.