Fraud Detection (ML)
Supervised classification project using Python to identify potentially fraudulent transactions. Includes data cleaning, feature engineering, and model comparison (Logistic Regression, Random Forest).
View on GitHub →About Me
I am currently pursuing an M.S. in Data Science at the New York Institute of Technology, and I hold a B.A. in Economics and Political Science from Stony Brook University. My main interests are machine learning and data analysis.
Projects
UN Refugee Data Finder
Exploring data from the United Nations Refugee Data Finder tool. Includes country-level analysis, regional trends, and data cleaning for migration and asylum indicators.
View on GitHub →World Bank Population Data
Exploring global population trends using World Bank data. Includes indicators, transformations, and visualization of demographic patterns across regions.
View on GitHub →Wave Data Cluster Analysis
Compared K-Means, Hierarchical, and DBSCAN clustering using Silhouette Score, Adjusted Rand Index (ARI), and Normalized Mutual Information (NMI).
View on GitHub →NYC LEP Population Data
Analysis of Census-based data on over 1.7 million limited English proficient (LEP) residents. Includes demographic segmentation and language-access insights.
View on GitHub →Zillow Home Value Index (ZHVI)
Exploring the Zillow Home Value Index (ZHVI), analyzing typical home values and market changes across regions and housing types using time-series trends.
View on GitHub →United Nations M49 Regions
Standard country and area codes (M49) used for statistical analysis and geographic classification. Includes region mapping and categorical encoding for ML workflows.
View on GitHub →NYC DHS Shelter Data
Analysis of data from the NYC DHS Shelter System, including trends, occupancy breakdowns, and visualization of demographic patterns using open-data sources.
View on GitHub →Contact
Email: martinmilonvelarde@gmail.com
LinkedIn: linkedin.com/in/martin-milon/
GitHub: github.com/martinmmv
CV
You can download a full version of my curriculum vitae here:
Download CV (PDF)