Parker Hayashi

Full-stack recruitment platform for fraternities and student organizations with real-time voting and candidate tracking.

• Built a full-stack recruitment platform for fraternities and student organizations serving 230+ members with real-time voting and candidate tracking, reducing voting cycle time by 50% and saving 10+ hours per recruitment round
• Designed a PostgreSQL schema in Supabase with row-level security, role-based access control (RBAC), and real-time subscriptions across 15+ tables, enabling vote tallying for 800+ candidates vs. multi-hour spreadsheet workflows
• Built a responsive front end with Next.js App Router and TypeScript using server components, optimistic updates, and role-based middleware auth, achieving sub-second page loads across 30+ routes with 20+ reusable components

SourcePreview

Machine learning pipeline that predicts professional ATP tennis match outcomes from decades of historical data.

• Developed a machine learning model to predict ATP tennis match outcomes using 50+ years of match data
• Engineered 100+ features including Elo ratings, surface stats, and head-to-head history
• Achieved high prediction accuracy via XGBoost with cross-validation and isotonic calibration

Source

Full-stack dashboard for macroeconomic indicators with data from the Federal Reserve Economic Data (FRED) API.

• Developed a full-stack economic dashboard with React for interactive visualization of 500+ economic time series
• Engineered a scalable FastAPI backend to retrieve and serve data from the FRED API
• Implemented client-side filtering, multi-series comparisons, and adaptive layouts using React hooks, conditional rendering, and Flexbox/Grid

SourcePreview

Multimodal machine learning framework for overall survival prediction in non-small cell lung cancer (NSCLC).

• Developed a multimodal XGBoost-based model to predict NSCLC overall survival using 36 NLP-processed clinical and genomic features
• Achieved up to 0.84 AUROC, outperforming previous state-of-the-art NSCLC survival models by up to 16.67%
• Provided a tool to help physicians personalize treatment strategies and improve patient quality of life
• Awarded 1st Place Overall and Human Health Category at the 2024 International Forum on Research Excellence

Source

IoT fill-level monitoring system for CompostNow compost stations with real-time telemetry and web dashboard. With Dan Li, Deep Patel, and Ryan Shin.

• Built an IoT fill-level monitoring system for CompostNow, a startup that diverted 17M lbs of food waste in 2023, using ESP32 microcontrollers and HC-SR04 ultrasonic sensors to stream real-time bin telemetry to Firebase and web dashboard
• Achieved 95% data upload success rate and <5% fill estimation error at high capacity across 3 load configurations; client adopted the <$100 prototype for potential deployment across 15 compost stations in the RDU/Triangle region

SourcePreview