Projects

These projects complement my finance experience with hands-on work in forecasting, customer analytics, and statistical modeling.

Financial data infrastructure

SEC Financial Data Infrastructure - KPMG Practicum
In progress

An ongoing Columbia QMSS practicum building SEC 10-K/10-Q data infrastructure. I own database and integration work, with a PostgreSQL foundation and a partial manual sample for future RAG/GraphRAG research.

Forecasting & business analytics

Wave Height Prediction — Surf Vacation Planner
Forecasting

A time-series forecasting app that predicts ocean wave heights using Facebook Prophet and NOAA buoy data, helping surfers find optimal locations and dates for their next trip.

Predicting Customer Churn Using KNN
Customer Analytics

A Kaggle project using K-nearest neighbors to predict customer churn, exploring a business question relevant to customer retention and revenue planning.

Machine learning & research

LLM Evaluation Pipeline for Robust QA
LLM Evaluation

Designed an end-to-end LLM evaluation pipeline for noisy QA inputs: prompt repair, multi-model benchmarking, automated metrics, and error analysis to quantify robustness and deployment risk.

COVID-19 Chest X-Ray Classification with Deep Learning
Deep Learning

Built and compared six CNN architectures (custom and transfer learning) to classify chest X-rays as COVID-19, Normal, or Viral Pneumonia — achieving 95.7% accuracy and 0.99 AUC.

Natural Language Processing for Student Rating Prediction
NLP

How do students really think about their professors? I used NLP on 20k+ RateMyProfessor reviews to predict star ratings from the text — and got accuracy up to ~69%.

Statistical & technical explorations

KMeans Clustering with Visualization

KMeans clustering algorithm with visualization. Includes demo video.

Search Engine

Search engine project with demo video.

Kaggle: Amazon Movie Review Star Rating

Kaggle competition — predicting star rating for Amazon movie reviews.

Linear Regression Experiments

Linear regression experiments with demo video.

Hypothesis Testing and Confidence Intervals in Linear Regression

Hypothesis testing and confidence intervals in linear regression. Includes demo video.

Logistic Regression Cluster Shift Experiment

Logistic regression cluster shift experiment with demo video.

Visualizing Neural Networks

Visualizing neural networks with demo video.

Identifying Credit Card Fraud

Identifying credit card fraud using machine learning.