Eight projects across AI, software, data, and social platforms.
Wysdom AI turns passive studying into active recall: upload notes or slides and it builds a personalized, infinite feed of questions in a TikTok-style format. Built with React Native and Expo over an AI pipeline that generates quizzes, flashcards, and open-response prompts.
Signal scores any website for classic search (SEO) and AI answer engines (GEO), returning a deterministic 0–100 score plus a Gemini-written action plan.
robots.txt / llms.txt.
A portfolio of high-growth Instagram accounts totaling 15M+ followers — including @ocean.destinations (5M+) — generating 100M+ organic impressions monthly, built over 8+ years through content strategy, audience analytics, and trend forecasting.
An AI-writing detector trained on 500,000 human- and AI-written essays. A Python machine-learning pipeline — decision trees and ensemble models — learns the stylistic signals that separate the two, then scores any pasted text on how likely it is to be AI-generated.
A cinematic 3D atlas of ~25,000 real stars, built from the HYG astronomical database and rendered in the browser with three.js and bloom. Fly through a glowing cosmic web, then dive into any star to watch its real confirmed exoplanets circle it on clean orbital rings.
An R-based study of Formula Hybrid / FSAE endurance data modeling total score against lap time and energy use. Two linear models combine into one objective, optimized to maximize points — endurance fit R² = 0.988.
A full chess engine built from scratch for CMU's 15-112 course. Handles the complete rule set — castling, en passant, promotion, check, checkmate, and stalemate — with an AI opponent that prioritizes capturing high-value pieces. Built on cmu_graphics with a menu-driven interface.
cmu_graphics package and place it alongside the source.Main_Menu.py to start.
A Python analysis of bias and emotion in political social-media posts — pandas for cleaning, NLTK for sentiment scoring, and matplotlib to visualize trends by hashtag.
pandas, matplotlib, and nltk.hw6_social.py.runWeek1(), runWeek2(), etc.