Portfolio

Portfolio

Machine Learning • NLP • Software Development

Professional Work

Energy Load Prediction System

Developed a machine learning system to forecast energy consumption patterns, achieving 92% accuracy for 24-hour predictions using ARIMA, XGBoost, and LSTM models.

Python XGBoost LightGBM LSTM

NLP Pipeline for Quotation Extraction

Engineered an end-to-end NLP pipeline for extracting quotes, identifying speakers, and classifying entities from unstructured text documents.

spaCy Stanford CoreNLP Python Transformers

Protein Language Models for Biological Insights

Leveraging protein language models and graph neural networks to predict protein properties and interactions for drug discovery applications.

PyTorch PyTorch Geometric Transformers DeepSpeed

Personal Projects

ScenicBayMapper

An interactive mapping application for discovering and navigating to scenic locations around the Bay Area with personalized recommendations.

Google Maps API React Node.js MongoDB

Expo v1

An open-source framework for building universal native apps with React that runs seamlessly on Android, iOS, and the web.

React Native JavaScript Android iOS

Audio App

A modern Next.js application for audio processing and playback with a sleek UI and advanced features.

Next.js React Web Audio API Tailwind CSS

H&M Fashion Recommendation System

A machine learning recommendation system for H&M products, using collaborative filtering and content-based approaches.

Python Scikit-learn PyTorch Collaborative Filtering

Yelp Restaurant Recommendations with GNNs

A Graph Neural Network (GNN) based recommendation system for restaurants using the Yelp dataset.

PyTorch PyTorch Geometric Graph Neural Networks Recommendation Systems

Notion RAG

A Retrieval-Augmented Generation (RAG) system that leverages Notion data for AI-powered question answering and knowledge retrieval.

Python Flask Qdrant OpenAI