← Home

Data Science

Exploratory analysis, machine learning, and statistical modeling projects.

Projects

CONUS Real Estate EDA

Exploratory analysis of ~700,000 U.S. rental listings. Covers regional pricing patterns, property size distributions, amenity breakdowns, and geospatial visualization overlaid on Stadia Maps tiles.

R ggplot2 ggmap tidyverse Geospatial EDA

Recession Prediction ML

Machine learning models trained on macroeconomic indicators to predict U.S. recession probability. Compares multiple classifiers with feature importance and evaluation metrics.

Python scikit-learn pandas matplotlib Classification Feature Engineering

U.S. Housing Price Feature Analysis

Ensemble regression models on ~385,000 Craigslist rental listings to identify which property features drive pricing. Pipeline covers EDA, IQR-based cleaning, K-Means location clustering, and target encoding.

Python scikit-learn pandas K-Means Ensemble Models Feature Engineering

Skills & Tools

Languages

R · Python · SQL

Visualization

ggplot2 · matplotlib · seaborn

Data Wrangling

tidyverse · pandas · dplyr · NumPy · SciPy

Machine Learning

scikit-learn · Random Forest · Gradient Boosting · classification · regression

Clustering

K-Means · target encoding · feature importance

Geospatial

ggmap · Stadia Maps · coordinate filtering

Statistics

IQR outlier removal · Pearson & Spearman correlation · feature engineering

Environment

Jupyter · RStudio · Git

Contact

Open to data science opportunities. Reach out via email or GitHub.