Hey, I’m
I am a recent graduate from New York University with a dual major in Data Science and Computer Science. I am a results-oriented individual with a demonstrated track record of designing and developing ML frameworks, data pipelines, and business intelligence tools. The power in influencing the future is the drive that propels my pursuit to identify, design, and develop frameworks across the vast uncharted potentials of the data-driven world. When not in the classroom I delegate my time to research in the discovery of applying new technologies to solve real-world problems. Among other things I am also a passionate skier, DJ, pianist, and aspiring music producer.
Jun 2023 - Aug 2023
New York, NY
Jan 2023 - Present
New York, NY
Jan 2023 - Jan 2024
New York, NY
Jun 2022 - Jun 2023
New York, NY
Dec 2021 - Jan 2023
New York, NY
Oct 2017 - Sep 2020
McLean, VA
Nov 2018 - May 2019
Mercersburg, PA
Aug 2020 - May 2024
New York, NY
Aug 2016 - Jun 2020
Purcellville, VA
This project explores the impact of model complexity on the performance of a pairs trading strategy over forecasted spreads. Various models, from simple regressors to complex transformers, are trained, evaluated, and backtested.
This repository contains a collection of notebooks on various advanced topics in machine learning and deep learning, created as part of NYU studies. Topics include bias-variance tradeoff, logistic regression regularization, neural network architectures, transfer learning, and more.
This repo contains files related to a Special Topics in Quantum Computing course, including quantum based algorithmic proofs and qiskit based quantum simulations such as the Elitzur-Vaidman bomb detector and various quantum game strategies.
This repository explores the correlation between news headlines' textual embeddings and their political orientation. Using clustering and transformer-based embeddings, the goal is to classify news sources based on headline content. Key features include clustering visualizations, BERT embeddings, and comparisons between K-Means, Spectral, and DBSCAN.
Streamlit webapp to analyze the US real estate market. Featuring interactive maps and statistical visualizations, explore property data, identify emerging trends, monitor macro developments, and track changes in property data.
This is a Streamlit app developed using a multimodal framework to valuate properties. The models are trained using data sourced from a large-scale web scraping ETL framework. The app is associated with PropertizeAI, a startup focused on property valuation.
This repository contains mathematical derivations of various ML theory concepts, including gradient of multi-class classifiers, MLE, hinge loss gradients, logistic regression gradients, and properties of various distrubtions.
This repository contains a Zillow Listing Web Scraper capable of scraping all US based real estate listings. The scraper extracts detailed property information from Zillow, including general data, address data, property features, foreclosure data, listing agent information, nearby schools, and price history.
This script allows you to scrape Yelp restaurant data. The data acquired from this scraper was used to identify potential correlations with localized housing market fluctuations.
