My Projects
Below is a selection of personal and academic projects I’ve worked on.
Combat Cognition
A progressive BJJ training application that accelerates skill acquisition through spaced repetition (SM-2 algorithm) and evidence-based mental visualization techniques. Combines physical training logs, guided 5-minute visualization sessions, smart scheduling, research protocols (nutrition, cardio, strength), and comprehensive progress tracking.
Technologies Used:
- React
- TypeScript
- Vite
- TailwindCSS
- shadcn/ui
- React Native
- Expo
- Express.js
- PostgreSQL
- Drizzle ORM
- Supabase
NFL Quarterback Evaluation Framework: 25-Year Performance Analysis
A comprehensive analytical framework for evaluating NFL quarterback performance and contract decisions through advanced statistical modeling and era-adjusted metrics. Combines systematic data collection from Pro Football Reference with ridge regression analysis to reveal organizational biases in quarterback evaluation and predict contract outcomes.
Technologies Used:
- Python
- Pandas
- Scikit-learn
- Ridge Regression
- Statistical Hypothesis Testing
- Tableau Public
- Feature Engineering
Jira-Claude Automation System
An intelligent project management automation system that integrates Jira with Claude AI to automatically analyze requirements, generate implementations, and evaluate deliverables, reducing manual effort by 70-90% while maintaining high quality and consistency.
Technologies Used:
- Node.js
- JavaScript
- Claude AI API
- REST APIs
- Webhooks
- GitHub Actions
- Anthropic SDK
News Intelligence Pipeline
An automated news aggregation and analysis system that uses Claude AI to generate targeted search queries, fetches articles from NewsAPI, synthesizes summaries, and delivers reports via GitHub Issues with intelligent caching.
Technologies Used:
- Python
- Claude AI API
- APIs
- Data Aggregation
- Semi-structured Data Caching
- Natural Language Processing
MMA Pre-Fight Prediction: ELO + Multinomial Handicapping
In progressAn interpretable pre-fight MMA handicapping pipeline that estimates a calibrated six-outcome probability distribution (win/lose by finish or decision) from tiered fight and fighter data. Combines cross-promotion ELO construction, ELO-weighted style features, matchup interactions, multinomial logistic regression, and explicit confidence intervals—using only information available before the opening bell.
Technologies Used:
- Python
- NumPy
- SciPy
- Multinomial Logistic Regression
- ELO Rating System
- Feature Engineering
- Statistical Modeling
Enron Email Graph: GNN-Based Anomaly Detection
In progressA research-oriented pipeline that models the Enron corpus as a communication graph and aims to surface behaviorally unusual actors from structure and metadata alone (headers, timing, threading, CC patterns)—not email body content. The design uses person-level nodes, a directed multigraph, rolling temporal windows with per-person baselines, and self-supervised graph autoencoders with optional temporal drift; evaluation is planned around held-out indicted executives and event-aligned sanity checks. The repo currently ships an installable Python package scaffold, documented architecture decisions, corpus extraction from the public maildir tarball, a root-level runner with per-stage rebuild vs cache flags, tests, and a plain-language roadmap for parsing, graph build, features, training, and eval.
Technologies Used:
- Python
- NetworkX
- NumPy
- Pandas
- Scikit-learn
- PyTorch Geometric
- PyGOD
Airbnb Investment Analysis Framework: Cross-City Short-Term Rental ROI Evaluation
Cross-city market analysis of short-term rental investment opportunities across 22 US cities, combining Airbnb listing data with Zillow real estate prices. Identifies profitable property segments, competitive landscape dynamics, and market entry barriers through statistical modeling and market professionalization metrics.
Technologies Used:
- Python
- Pandas
- Statistical Hypothesis Testing
- Feature Engineering
- Data Visualization
- Market Research
- Financial Modeling
FlowState: Jiu-Jitsu Strategy Generator
An AI-powered application that analyzes jiu-jitsu techniques and generates personalized training strategies, flow charts, adversary response plans, and analytical insights for practitioners of all levels.
Technologies Used:
- Python
- Streamlit
- OpenAI API
- HTML/CSS
- JavaScript
- Natural Language Processing
- User Experience Design
Penn State Football Calendar Generator
A robust web scraper application that extracts Penn State football schedules and creates standardized calendar files, allowing fans to automatically sync game information with their personal calendars.
Technologies Used:
- Python
- Flask
- BeautifulSoup
- iCalendar
- HTML/CSS
- Regular Expressions
Yale Football Calendar Generator
A Python web scraper that automatically extracts Yale football schedule information and generates an iCalendar file for easy integration with calendar applications.
Technologies Used:
- Python
- Flask
- BeautifulSoup
- iCalendar
- HTML/CSS
Documents
Below are documents related to my work:
TGIF Frozen Snacks Customer Insights: Driving Growth by Activating Beliefs and Goals
Research whitepaper applying consumer-aligned product management methodologies to drive growth for TGIF Frozen Snacks. Conducts multi-method user research including online ethnography, in-depth interviews, and quantitative A/B testing with 4,051 survey respondents. Uses Yale's Beliefs-Goals-Choices framework to identify emotional and functional drivers of consumer behavior, translating insights into actionable product positioning and messaging strategies.
DownloadFlowState: AI-Powered Grappling Strategy Generator with Adversarial Game Planning
Technical documentation for an AI-powered grappling strategy application built through consumer-aligned product management. Identifies gaps in existing solutions (static instructional content vs. dynamic training needs) and translates user pain points into product features. Includes context-aware interfaces that adapt to individual user attributes, iterative user experience design, and modular feature development including adversarial game planning for counter-strategy generation.
DownloadVuori Outside-In Personalization Assessment
Outside-in assessment of Vuori's personalization in practice. Grades publicly observable customer experience (website, email, checkout, loyalty, in-store) and recommends the next pilot step.
Download