Academic & Personal Projects

A collection of my work in data analysis, machine learning, and visualization.

Forecasting Short Term COVID-19 cases

Time-SeriesDecision TreeSVRRegression

Created two time-series models to predict daily COVID cases in CA counties. While the models did not achieve high accuracy, the project was a deep-dive into the challenges of feature selection and model limitations with real-world, noisy data.

UFO Sightings Analysis (1914-2010)

Data VisualizationPandasGeo-analysis

Analyzed a dataset of UFO sightings reported by the US Government. Used scatterplots, correlation matrices, and PCA to visualize report densities and investigate relationships between variables like shape, time of day, and location.

Predicting the 2016 Election

ClassificationRandom ForestK-Means

Utilized voter demographic data to predict county-level election outcomes. Compared various models (Logistic Regression, Random Forest, AdaBoost) achieving up to 92.2% accuracy. Used K-Means to identify distinct demographic clusters.