• Computer Science & Russian Studies | Davidson College
• Learning & practicing ML architectures, Russian, real-time systems, mathematical modelling, and optimisation techniques
• Interests primarily lie in computational optimisation, quant finance, national security, geopolitics, and open-source intelligence

Collection of applied ML projects spanning medical diagnostics, environmental forecasting, agricultural analysis, and aerospace systems:

• Cancer Classification: 95%+ accuracy identifying 6 cancer types from miRNA data
• E. coli Forecasting: Recreation of USGS models for Great Lakes beach safety
• Farmland Analysis: Computer vision for agricultural feature detection from aerial imagery
• NASA Telemetry Anomaly Detection: Unsupervised ensemble learning for spacecraft monitoring

• March Madness bracket optimization system with machine learning models & Monte Carlo simulations, maximizing probability of finishing 1st in bracket pools rather than just prediction accuracy
• Data pipeline combining advanced team metrics, historical tournament data, and public pick distributions to identify high-leverage, contrarian selections outperforming the field
• Designed & evaluated multiple bracket strategies through large-scale simulations, optimizing for expected value, variance, and pool-specific dynamics (e.g., size, ownership overlap)

Applied mathematical modelling portfolio, following along with MAT-210 - Mathematical Modelling (Davidson College)

• Central Limit Theorem Sim: Monte Carlo dice experiments showing convergence to normality under varying distributions
• Monte Carlo Methods: Buffon’s Needle for π estimation, fish tank simulations, and probability puzzle modeling
• Poisson Processes & Queuing: Pharmacy arrival/service simulation to estimate wait times and closing delays
• Linear Programming in Excel: Resource allocation and scheduling problems solved with simplex and integer programming
• Bracketology & Colley Rankings: Linear-algebra-based NCAA team ratings, weighting experiments, and bracket prediction tests
• Integer Programming: Discrete optimisation models solved with integer and binary decision variables
• Clustering & Unsupervised Learning: K-means and hierarchical clustering on movie ratings and customer data, with technique comparison and dendrogram visualisation