About
I'm a data scientist with a Master of Science in Data Science from the University of Colorado Boulder and over two decades of operational leadership in high-stakes environments. Before data science, I led diplomatic security missions at the U.S. Embassy in Baghdad, managed infantry squads through combat deployments, and coordinated cross-functional teams where failure wasn't an option.
That background shaped how I approach data problems: structured planning, rigorous validation, and clear communication of results. I build data pipelines, predictive models, and analytical tools that turn complex datasets into clear, actionable decisions.
Education
M.S. Data Science
University of Colorado Boulder, 2026
B.S. Business Management
Portland State University, 2017
Background
Projects
Prop Trading Dashboard
FeaturedDesktop analytics platform that ingests raw trade CSVs, aggregates fills using interval overlap analysis, computes per-day statistics (expectancy, profit factor, drawdown), and models firm-specific payout eligibility rules in real time. Built end-to-end with TypeScript, React, SQLite, and Electron.
View on GitHub →Falcon 9 Landing Prediction
End-to-end classification project predicting SpaceX first stage landing success. Includes data collection via API, EDA, feature engineering, SQL analysis, and an interactive Plotly Dash dashboard. Achieved 83.3% accuracy.
View on GitHub →Histopathologic Cancer Detection
CNN-based medical image classifier for identifying metastatic cancer in histopathologic scans. Built and compared multiple deep learning architectures with data augmentation and transfer learning. Kaggle score 0.7961.
View on GitHub →NLP Disaster Tweets
Binary text classification to distinguish real disaster tweets from non-disaster tweets using BiGRU and BiLSTM architectures. Includes text preprocessing, embedding layers, and model evaluation. Kaggle rank 377.
View on GitHub →Monet Style Transfer
Photo-to-painting transformation comparing DCGAN, CycleGAN, and Neural Style Transfer approaches. Trained generative models to produce Monet-style artwork from photographs. Kaggle rank 20th, MiFID score 53.14.
View on GitHub →Rotten Tomatoes Predictor
Predicting critic scores from movie review text using BERT-based transformer models. Covers tokenization, fine-tuning, and regression evaluation on real Rotten Tomatoes data.
View on GitHub →Maevie Project Manager
Full-stack project management application built for an interior design company. Features task tracking, client management, and team coordination with a responsive UI.
View on GitHub →Technical Skills
Languages
ML & Statistics
Data Engineering
Visualization
Tools
Contact
Open to data science roles, collaborations, and consulting opportunities.