Projects
Filter the gallery by domain, then open each case study for the problem, data, approach, results, technology stack, and lessons learned.
State-aware AI email assistant with gated tool execution
An AI safety-focused email agent using LangChain, LangGraph, prompt middleware, and human-in-the-loop controls to prevent unauthorized email actions.
LangGraph workflow for vendor sourcing, constraints, and text-to-SQL
A multi-agent coordinator that automates event-planning workflows with LangChain, LangGraph, LangSmith tracing, MCP tools, Tavily Search, and a self-correcting SQLite text-to-SQL agent.
Gemini and FAISS app for transcript-grounded video Q&A
A RAG video analysis tool that chunks YouTube transcripts, embeds retrieval context with FAISS, and serves interactive summaries and question answering through Streamlit.
ETL and statistical learning workflow for air-quality prediction
A forecasting project that automates public data retrieval, compresses large environmental datasets, and models short-term PM2.5 air pollution outcomes.
Power BI dashboard across 479K job-market records
A Power BI analytics dashboard that visualizes data job trends, skill demand, and role-level market patterns across monthly CSV datasets.
K-Means segmentation for investment propensity strategy
A customer analytics project that uses multivariate EDA and K-Means clustering to identify customer segments and recommend targeted investment strategies.
Dimension reduction and imputation for noisy high-dimensional data
A machine learning project comparing Group Lasso and KNN-style imputation under missing-not-at-random settings and high-dimensional feature spaces.
A/B testing and root-cause analysis on large-scale ridesharing data
An analytics project that designs and evaluates a cancellation policy using A/B testing, root-cause analysis, and statistical validation.
Classification pipeline for first-stage landing outcomes
A data science workflow predicting whether a Falcon 9 first stage will land successfully, using feature engineering, exploratory analysis, and model comparison.
LSTM-based sequence model for generated music notes
A PyTorch deep learning project that encodes note sequences and trains an LSTM model for music generation.
Bayesian GBM and HMC for JNJ stock analysis
A quantitative research project under Professor Jazi using Bayesian Geometric Brownian Motion and Hamiltonian Monte Carlo to estimate and forecast Johnson & Johnson stock behavior.
Survey-based analysis of traditional and AI-enabled study tools
A survey research project under Professor Labadi analyzing how students use traditional resources, online platforms, and LLM tools for learning.