Materials Informatics
Predicting the Vickers microhardness of metal-ceramic nanocomposites with XGBoost and physics-informed features (Hall-Petch, Orowan, CTE mismatch), plus group-aware validation, ensemble uncertainty, and SHAP interpretability.
Ronnie Wang Predicting the Vickers microhardness of metal-ceramic nanocomposites with XGBoost and physics-informed features (Hall-Petch, Orowan, CTE mismatch), plus group-aware validation, ensemble uncertainty, and SHAP interpretability.
A project pairing Spotify audio features with Billboard Hot 100 chart data, backed by PostgreSQL 16 on AWS RDS with a Node/Express API, a React + Recharts frontend, and a Python/pandas cleaning pipeline.
A forecasting system that compares live Kalshi player prop prices against probabilistic NBA player projections, surfacing the largest gaps between market and model.
A self-hosted feature flag service with an Express API, PostgreSQL persistence, Redis-backed evaluation caching, a React admin dashboard, and a small JavaScript SDK.
An end-to-end laundry notifications feature for the Penn Mobile Android app: a UI toggle, a reboot-safe background polling architecture, push notifications, state persistence across reboots, and rate-limited API polling.
A single-process, multi-threaded operating system with a priority scheduler, process lifecycle, interactive shell, PennFAT filesystem, and syscall abstraction.