Projects

Applied statistics and machine learning, from a live health-tech product to graduate research projects.

Tick Mitt · Data Science & AI Engineering Intern · Summer 2026

TiCK Heatmap

A live, community-powered tick-encounter and Lyme disease-prevalence tracking platform, backed by a hierarchical Bayesian engine and built privacy-first. I was the sole engineer.

Bayesian StatisticsAWSReactPrivacy by Design

ROC curves for logistic regression, linear SVM, kernel SVM, and a PyTorch MLP, all near AUC 0.82.

Fordham · CISC 5800, Machine Learning · Spring 2026

Type 2 Diabetes Prediction

A comparison of four ML classifiers on 253K CDC BRFSS survey records, tuned for screening: minority-class recall rose from 76% to 86% at ROC-AUC ≈ 0.82.

PyTorchScikit-LearnClassificationImbalanced Data

Scatter plot of FinBERT sentiment score against 5-day abnormal return, colored by sector, showing near-zero correlation.

Fordham · CISC 5352, ML in Finance · with Patricia Angeles · Spring 2026

FinBERT Sentiment vs. Price-Based ML

An NLP pipeline over 480 SEC filings, tested against price-based classifiers to see whether filing sentiment predicts post-earnings returns. It barely does, which is consistent with semi-strong market efficiency.

NLPFinBERTHuggingFaceXGBoost

Heatmap of the estimated traversability grid, with most visited cells traversable and two low-traversability cells in red.

Fordham · CISC 6525, Artificial Intelligence · Spring 2026

Terrain Traversability with a Dynamic Bayesian Network

A per-cell recursive Bayes filter that maps where a mobile robot can safely drive using only its wheel-slip readings. Built in ROS/Gazebo and validated on a TurtleBot3.

Dynamic Bayesian NetworksProbabilistic ReasoningPythonNumPy / SciPy