Document Intelligence Hub
Offline document Q&A system that ingests PDFs, Word docs, and spreadsheets and answers questions with cited sources. Combines BM25 and dense vector retrieval using Reciprocal Rank Fusion — no cloud APIs required.
Customer Churn Analytics Platform
End-to-end ML system for churn prediction. XGBoost model with SHAP explainability, served via FastAPI, visualized across five React dashboard views, and containerized with Docker Compose for one-command deployment.
A/B Testing & Experimentation Platform
Full-stack experimentation engine supporting power analysis, Welch t-tests, SPRT sequential testing, and Holm-Bonferroni correction for multi-variant experiments — built for statistical rigor at scale.
CareSight — Hospital Readmission Prediction
Predicts excess readmission ratios across ~18,000 US hospitals using CMS data. Benchmarks Ridge, Lasso, XGBoost, and neural network models (best R² = 0.975) with SHAP feature explanations to support quality improvement decisions.
QuantifyAI — Quant Alpha Research
ML-driven backtesting platform that fetches live market data, computes RSI, MACD, and Bollinger Band signals, trains a Random Forest classifier for buy/sell decisions, and runs portfolio simulations via Backtrader with a Streamlit dashboard.